CodeGraph MCP: Full-Stack Knowledge Graph & Semantic Intelligence for AI Coding Agents

Deterministic AST-Verified Codebase Intelligence • Sub-15ms Live Watcher • Context Window Optimization
Deterministic Model Context Protocol (MCP) server for Cursor, Claude Code, GitHub Copilot, Antigravity, Cline, Windsurf & Codex.

CodeGraph MCP provides deterministic, evidence-backed repository intelligence through Abstract Syntax Trees, framework router hierarchies, database lineage, and runtime observation.

Documentation Site • PyPI Package • Overview • Web Dashboard & VS Code • The Three Pillars • Roblox & Luau • Quickstart • CLI Outputs • Database Intelligence • Runtime Evidence • Git Intelligence • Benchmarks • 70-Tool Reference • GitHub

Overview

The Problem

When AI coding agents (such as Claude Code, Cursor, or Antigravity) explore complex enterprise repositories, text-based search (grep/ripgrep) forces them to parse large, multi-thousand-line files to reconstruct call chains, router mounts, dependency injection graphs, and ORM schemas. This consumes 60% to 80% of the LLM context window with irrelevant code and frequently leads to hallucinations regarding entity relationships and database structures.

The Solution: CodeGraph MCP

CodeGraph MCP provides deterministic, compiler-grade repository intelligence through the Model Context Protocol. Instead of guessing based on lexical approximations, the AI agent queries a local, persistent SQLite index for verified AST relationships, framework router trees, database lineages, and live runtime observations—resolved in sub-5ms latency.

       ┌─────────────────────────────────────────────────────────────┐
       │                      AI CODING AGENT                        │
       │           (Claude Code  •  Cursor  •  Antigravity)          │
       └──────────────────────────────┬──────────────────────────────┘
                                      │  Model Context Protocol (stdio / SSE)
                                      ▼
       ┌─────────────────────────────────────────────────────────────┐
       │                   CODEGRAPH MCP ENGINE                      │
       ├──────────────────────────────┬──────────────────────────────┤
       │  AST Code Relationships      │  Framework & Network Graph   │
       │  (Callers, Callees, DI)      │  (FastAPI, Django, Roblox)   │
       ├──────────────────────────────┼──────────────────────────────┤
       │  Database & DataStore Graph  │  Non-Invasive Dev Tracing    │
       │  (SQLAlchemy, Prisma, ORM)   │  (HTTP metrics, exceptions)  │
       └──────────────────────────────┴──────────────────────────────┘
                                      │
                                      ▼
             Deterministic • Local-First • Verified Evidence

Core Architecture Capabilities

Deterministic Evidence Guarantee: Every returned entity and relationship is statically verified via Abstract Syntax Trees (AST_VERIFIED, FRAMEWORK_VERIFIED, ROJO_VERIFIED) or explicitly flagged as UNKNOWN / POSSIBLE. CodeGraph MCP provides deterministic, evidence-backed repository intelligence across application code, databases, runtime behavior, and Git history.
Sub-5ms Freshness Verification: Monotonic commit tracking validates git rev-parse HEAD and porcelain status instantly, avoiding full-tree re-indexing on unchanged codebases.
Context Window Optimization: Yields 65% to 85% token reduction by returning structured, bounded source slices rather than entire file dumps.
Zero-Friction Dev Interception (codegraph run): Wraps local development servers (e.g., codegraph run npm run dev, codegraph run uvicorn main:app) to capture real HTTP routes, latencies, and stack traces without application code changes.
Multi-Agent Setup (codegraph install): Automatically detects, configures, and verifies integrations for Claude Code, Cursor, Antigravity, and Cline.

Supported Languages & Frameworks: Python (FastAPI, Flask, Django, SQLAlchemy, PyTorch, Celery, LangChain, LlamaIndex, Ray, pytest), TypeScript / JavaScript (.ts, .tsx, .js, .jsx, React, Next.js, NestJS, Express.js, Prisma, Drizzle, Mongoose), and Roblox / Luau (.lua, .luau, Rojo, Knit, Flamework / roblox-ts, DataStoreService, ProfileService).

Measured Performance & Real Metrics Benchmark

Performance and retrieval accuracy are verified across two empirical evaluation suites: a 32-task agent navigation simulation (src/codegraph/tool_selection_eval.py) measuring agent trajectory efficiency, and a 50-task diagnostic benchmark (benchmarks/run_v21_eval.py) evaluating multi-file recall, coverage, and context boundaries:

Performance Metric	Unassisted AI Agents (Raw Grep / File Dumps)	CodeGraph MCP Engine	Measured Result	Evaluation Suite
Unsupported Relationship Claims	18.5% – 34.0% false edges	0.0% (AST / Framework verified)	100% eliminated	32-Task Navigation Eval
Exploration Tool Calls	164 total tool calls (~5.1 / task)	71 tool calls (~2.2 / task)	56.7% fewer tool calls	32-Task Navigation Eval
Context Consumption (Prompt Tokens)	3,000 – 12,000+ tokens / task	~510 tokens avg payload	72% – 85% token savings	32-Task Navigation Eval
Direct File Token Reduction	Full file reads required	Bounded slices via `get_file`	41.8% token reduction	50-Task Retrieval Benchmark
Task Coverage & Symbol Recall	Baseline lexical match	88.0% coverage / 61.9% recall	Verified ground truth	50-Task Retrieval Benchmark
Incremental File Reindexing (Live)	Full rescan required (1.2s – 6.5s)	< 15ms per file (`codegraph watch`)	In-memory cache patch	Live OS Kernel Watcher
Single-File Full Re-index (Cold CLI)	Full rescan required (4.4s)	3.665s (2,504 files)	16.9% faster	4-Tier Stress Benchmark
Repository Freshness Check	450ms – 2,100ms disk stat checks	< 5ms (Git commit fast path)	99% faster checks	Git Fast Path Check
Symbol Grounding & Resolution	Manual file scanning	< 2ms in-memory SQLite	Sub-millisecond resolution	SQLite Indexed Lookup
Automated Test Suite Quality	—	980+ passed tests (100% pass rate)	Zero regressions	Pytest CI/CD Suite

Interactive Web Dashboard & VS Code Extension

CodeGraph v3.0 introduces a zero-configuration local visual dashboard and official VS Code integration for real-time visual inspection of your repository's AST relationships, full-stack routes, and PR blast radius.

1. Interactive Knowledge Graph Web Dashboard (`codegraph ui`)

Launch the local visualizer with a single command:

# Launch interactive dashboard on http://127.0.0.1:8765
codegraph ui

# Custom port or headless server (no automatic browser launch)
codegraph ui --port 9000 --no-browser

The Web Dashboard delivers:

Interactive Knowledge Visualizer: Search and inspect any symbol, route, or model across Python and TypeScript.
Full-Stack Route Explorer: Visualizes frontend fetchers (fetch<T>(), axios) matched to backend handlers (FastAPI, Flask, Django, Express, NestJS).
Database Lineage Matrix: Real-time table relationship map showing exact static writers and readers (PostgreSQL, SQLite, Prisma, Drizzle, SQLAlchemy, Mongoose).
PR Blast Radius & Risk Tiering: Live risk assessment, highlighting modified call chains and covering tests before submitting pull requests.
REST & SSE Endpoints: Integrated REST API (/api/status, /api/routes, /api/drift, /api/impact, /api/graph) enabling external tools to query graph state.

2. Official VS Code Extension (`vscode-extension`)

The CodeGraph VS Code extension brings deterministic repository intelligence directly into your editor:

# Package and install the extension
cd vscode-extension
code --install-extension codegraph-3.0.0.vsix

Features included in the VS Code sidebar:

Full-Stack Routes View: Tree view of all discovered endpoints, clicking any item navigates directly to the route handler definition.
Database Lineage & Models View: Inspect tables, fields, readers, and writers side-by-side with source code.
PR Blast Radius Explorer: Select any active file to view downstream callers, impacted routes, and tests to run.
In-Editor Knowledge Graph Panel (CodeGraph: Open Visual Knowledge Graph Dashboard): Opens the visual web dashboard side-by-side in a VS Code Webview panel.
Safe AST Rename (CodeGraph: Safe AST Rename Symbol): Deterministic symbol refactoring across all call sites and route handlers.
Live Watcher Integration (CodeGraph: Start Sub-15ms Live Watcher Daemon): One-click background watcher launch.

The Three Pillars of CodeGraph MCP

AI / ML & PyTorch Stack Intelligence

CodeGraph MCP natively parses AI/ML architectures and agent pipelines into deterministic graph facts:

PyTorch nn.Module Forward Resolution: Submodule and model instance calls (model(x), self.encoder(x)) automatically resolve to Encoder.forward emitting DISPATCHES_FORWARD (AST_VERIFIED).
LangChain & LlamaIndex Agent Tools: Statically detects @tool, @function_tool, and dynamic agent registries, connecting agent capabilities to handler implementations (AGENT_TOOL).
LangChain LCEL Pipelines: Tracks pipe syntax (prompt | model | parser) as executable pipeline dataflow (CHAINS_TO).
Distributed Ray Tasks: Detects @ray.remote actor decorators and task.remote() invocations (DISPATCHES_RAY_TASK).

Roblox & Luau Intelligence (`codegraph roblox`)

First-class repository intelligence for Roblox game architectures (.lua, .luau, and roblox-ts):

Native Luau Parser: Extracts local/global functions, colon methods (function Service:Init()), dot methods (function Module.Func()), table-assigned methods (Service.Method = function(...)), module table returns, return table.freeze(Module), and Luau type / export type declarations.
Rojo DataModel Mapping (default.project.json): Maps virtual Roblox paths (ReplicatedStorage, ServerScriptService, StarterPlayerScripts, Packages, script.Parent) to physical files on disk with ROJO_VERIFIED provenance (REQUIRES_MODULE).
Client $\leftrightarrow$ Server Network Graph: Traces RemoteEvent:FireServer(...) $\to$ OnServerEvent:Connect(handler) and RemoteFunction:InvokeServer(...) $\to$ OnServerInvoke = handler through canonical Remote nodes via CLIENT_DISPATCHES_REMOTE and SERVER_HANDLES_REMOTE.
Knit, Flamework & Persistence: Tracks Knit.CreateService / Knit.GetService, Flamework @Service / @Controller / Dependency<T>, and DataStoreService:GetDataStore (GetAsync, SetAsync, UpdateAsync) + ProfileService (CONFIGURES_PERSISTENCE, READS_PERSISTENCE, WRITES_PERSISTENCE).
Dedicated CLI Inspection: codegraph roblox remotes, codegraph roblox modules, and codegraph roblox routes.

Pillar 1: The Unified Full-Stack Bridge (`codegraph api-drift`)

Bridges frontend client fetchers and backend API handlers across languages without manual tracing:

Client Route Extraction: Statically parses React / Next.js / Vue / Nuxt fetch<T>(), axios.get<T>(), useSWR<T>(), useQuery<T>(), and $fetch<T>() alongside TypeScript request/response interfaces.
Universal Route Normalization: Matches parameterized paths (/api/v1/orders/:id, /api/orders/${orderId}, /orders/{order_id}) directly to backend routes in FastAPI, Flask, Django, Express, and NestJS.
Cross-Language Drift Detection: Flags field name mismatches, type incompatibilities, missing nullable fields, and orphaned client routes before deployment.

Pillar 2: Semantic Change Impact & PR Blast Radius Engine (`codegraph impact`)

Full-stack downstream impact analysis from code symbols to production infrastructure:

Blast Radius Tracing: Traces any symbol or git diff $\to$ direct/transitive callers $\to$ React UI components $\to$ HTTP routes $\to$ DB readers/writers $\to$ covering tests $\to$ monorepo packages.
PR Risk Scoring (0–100): Quantitative risk evaluation categorized into LOW, MEDIUM, HIGH, and CRITICAL.
Breaking Change Detection: Identifies public API modifications, DB mutations, and untested code paths.
Smart Test Execution: Generates targeted test commands (e.g. pytest tests/test_orders.py -k "test_a or test_b") running only the affected test suite.

Pillar 3: Incremental Live Watcher & Instant Cache Invalidation (`codegraph watch`)

Zero-heat, real-time file system monitoring with sub-15ms incremental reindexing:

Kernel-Push Event Monitoring: Uses OS-level kernel events (macOS FSEvents, Linux inotify, Windows ReadDirectoryChangesW) via watchdog.
250ms Sliding Debounce: Coalesces rapid multi-file edit bursts from formatters, linters, or git operations into single atomic passes.
Sub-15ms Incremental Reindexing: Bypasses full-disk traversal; only re-indexes modified files (Indexer.reindex_paths) and advances generation counters.
Instant In-Memory Cache Busting: Automatically purges LRU memory caches (_PARSE_CACHE, _GRAPH_CACHE) and SQLite context caches upon file mutation.

1. What's New in v3.0.0

Version 3.0.0 delivers major advancements in Git-Aware Intelligence, Interactive Visualization, Engine Robustness, and Context Token Optimization:

1.1 Git-Aware Repository Intelligence

Understand how code evolves across branches, commits, and working tree edits with sub-millisecond freshness verification:

Capability	CLI Command	MCP Tool	How It Solves Agent Failure Modes
Working-Tree Freshness	`codegraph git-state`	`get_git_state`	Tracks branch, HEAD vs indexed commit, modified/staged files with sub-millisecond status caching. Surfaces `CLEAN`, `DIRTY`, `STALE`, `REINDEXING`, `ERROR`.
Structural AST Diff	`codegraph git-diff [base] [head]`	`compare_git`	Semantic diff across Git revisions: identifies added/removed/modified functions, changed parameter signatures, and affected routes—not merely raw line diffs.
Deep Impact & Visual Tree	`codegraph git-impact --tree`	`get_change_impact`	Traverses downstream callers, callees, framework routes, DB writers, and affected test suites with token-bounded ranking and terminal ASCII tree visualization.
Semantic Merge Conflicts	`codegraph git-conflicts [base] [head]`	`detect_semantic_conflicts`	Detects silent contract breaks before merge: invoking functions or route handlers that were deleted or modified on the target branch.
Context Freshness Gate	`codegraph check-freshness [task]`	`check_context_freshness`	Determines whether previously compiled context remains `VALID`, `PARTIALLY_STALE`, or `STALE` without re-running full graph queries if unrelated files changed.
Deterministic Symbol History	`codegraph symbol-history <sym>`	`trace_symbol_history`	Reconstructs the exact commit lifecycle of any symbol (introduced, modified, moved, renamed, or deleted) with confidence labels.

1.2 Engine Robustness & Accuracy Hardening

Modern FastAPI Dependency Injection: First-class tracking for Annotated[..., Depends(...)] type aliases (e.g. SessionDep = Annotated[Session, Depends(get_db)], CurrentUser, TokenDep) resolving callers of DB and security providers directly to consuming route handlers.
Python Syntax Auto-Repair: Auto-recovers unparenthesized multi-exception syntax (except A, B:) across newer Python host runtimes so core dependency modules never fail AST extraction.
Strict Endpoint Scoping: Prevents cross-file name collisions (e.g., matching same-named endpoints across disparate router modules) to maintain 0% false edge rates.
Token Budget & Noise Suppression: Context compilation strictly adheres to max_tokens limits by summarizing auxiliary sections. Graph traversals automatically filter noisy tensor and dictionary primitive methods (size, shape, stack, get), keeping token payloads lean.

1.3 Enterprise Concurrency & Runtime Interceptor

Capability	Mechanism	Impact
Runtime Interceptor	`codegraph run <cmd>` non-invasive wrappers (`NODE_OPTIONS` / `PYTHONSTARTUP`)	Zero application code modifications; streams live HTTP routes, latencies, and exception traces into `.codegraph/runtime.sqlite3`.
WAL Database Concurrency	Permanent `WAL` mode, `synchronous = NORMAL`, `busy_timeout = 15000` (15s), `cache_size = -64000` (64MB)	Eliminates `database is locked` errors during parallel AI pair-programming interrogation.
Index Freshness Fast Path	Instant verification: checks `git rev-parse HEAD` and `git status --porcelain`	Reduces index freshness verification from seconds to `< 5ms` on clean repositories.
Bounded Pagination	`limit`, `offset`, `total_count`, and `has_more` on all route, table, and context queries	Prevents token blowups on large repositories with tens of thousands of endpoints.
Multi-Transport MCP	Hot-reconnecting `--transport sse` alongside default `stdio`	Prevents MCP client crash loops on server restarts or IDE reconnections.

2. Quickstart (30-Second Setup)

Step 1: Install the Package

pip install "codegraph-engine[mcp]"

Step 2: Configure Your AI Coding Agents (`codegraph install`)

CodeGraph MCP includes an interactive, idempotent onboarding installer (src/codegraph/installer.py) that detects installed AI coding agents (Claude Code, Cursor, Antigravity, Codex CLI, Gemini CLI, and Cline), configures mcpServers.codegraph, installs marker-bounded routing instructions ( … ), and verifies server health:

# Interactive setup (detects installed agents, previews planned changes, asks confirmation)
codegraph install

# Non-interactive setup for all detected agents in the current project
codegraph install --yes --target auto --location local

# Preview exact file modifications without writing anything
codegraph install --dry-run

Step 3: Initialize & Verify Your Project Index

cd your-project
codegraph init
codegraph status
codegraph doctor

Dynamic Index Hot-Reloading: If your AI coding agent launches codegraph mcp serve before you run codegraph init, you do not need to restart your IDE or MCP session. As soon as codegraph init or codegraph index creates or updates .codegraph.sqlite3, the running MCP server automatically detects the database on the next tool call and refreshes its in-memory graph cache (get_repository_status(reload=True, reindex=True) can also be invoked directly by the agent).

Step 4: Run With Zero-Friction Telemetry (`codegraph run`)

Wrap your development server transparently to stream real HTTP routes, durations, and uncaught exceptions directly into CodeGraph MCP:

# Node / Express / Next.js
codegraph run npm run dev

# Python / FastAPI / Uvicorn
codegraph run uvicorn main:app --reload

# Django
codegraph run python manage.py runserver

3. Core Architecture & Mental Model

flowchart TD
    A["AI Coding Agent (Claude, Cursor, Antigravity, Cline)"] --> B["CodeGraph MCP Server (stdio or SSE)"]
    B --> C["Deterministic Repository Intelligence"]

    C --> D["AST Semantic Graph (Callers, Callees, References, DI)"]
    C --> E["Literal & Regex Text Search (search_code)"]
    C --> F["Bounded Source Inspection (get_file)"]
    C --> G["Database Intelligence (Tables, ORM, Migrations, R/W)"]
    C --> H["Zero-Friction Runtime Telemetry (codegraph run)"]

    D --> I["Structured Evidence + Epistemic Labels"]
    E --> I
    F --> I
    G --> I
    H --> I

    I --> J["Context Optimization & Secret Redaction"]
    J --> A

Routing Each Question to the Right Primitive

STRUCTURAL     →  Graph tools (find_symbol, find_callers, find_callees, find_references, find_routes)
TEXTUAL        →  search_code (literal/regex search across Python, HTML/Jinja, JS/TS, CSS, YAML/JSON, SQL)
SOURCE         →  get_file (bounded start_line..end_line source inspection with truncation metadata)
GRAPH          →  Trace tools (trace_path, trace_flow, analyze_impact, get_git_impact)
DATABASE       →  Database tools (get_db_schema, find_db_tables, find_db_readers, find_db_writers, get_db_impact)
RUNTIME        →  Runtime tools (codegraph run, ingest_runtime_traces, get_runtime_trace, reconcile_static_runtime)
EDITING        →  Native agent / IDE editing tools

4. Real-World CLI Outputs

Below are exact, verifiable outputs produced by CodeGraph MCP v3.0.0:

1. Zero-Friction Runtime Interceptor (`codegraph run`)

$ codegraph run python3 -c "print('>> Dev server active on port 8000')"
>> Dev server active on port 8000

HTTP requests, status codes, and exceptions are automatically streamed to .codegraph/runtime.sqlite3 with child exit codes preserved.

2. Instant Index Freshness Check (`codegraph status`)

$ codegraph status .
{
  "repository": "/Users/raghuram/Documents/ChatGPT/MCP",
  "freshness": "FRESH",
  "freshness_detail": "Index matches current repository state.",
  "files": 190,
  "chunks": 1965,
  "symbols": 1947,
  "framework_routes": 0,
  "graph_edges": 12712,
  "resource_profile": "BALANCED",
  "pressure_level": "NORMAL",
  "activity_mode": "IDLE",
  "estimated_memory_mb": 43.23,
  "modified_files": [],
  "deleted_files": [],
  "parse_failed_files": []
}

Validated in < 5ms via the Git commit diff fast path.

3. Incremental Indexing with 16-Phase Telemetry (`codegraph index --verbose`)

$ codegraph index --verbose
Phase: Repository Scan
190 / 190 files | 100% | elapsed: 0.09s | rate: 128,203 files/min | memory: 42 MB
Phase: Post-Processing
190 / 190 files | 100% | elapsed: 0.62s | rate: 18,273 files/min | memory: 67 MB
Phase: Symbol Resolution
190 / 190 files | 100% | elapsed: 0.80s | rate: 14,311 files/min | memory: 91 MB
Phase: Relationship Resolution
190 / 190 files | 100% | elapsed: 1.49s | rate: 7,648 files/min | memory: 116 MB
Phase: Database Analysis
190 / 190 files | 100% | elapsed: 1.77s | rate: 6,424 files/min | memory: 120 MB
Phase: Final Commit & Checkpoint
190 / 190 files | 100% | elapsed: 2.59s | rate: 4,396 files/min | memory: 141 MB

Summary: elapsed=2.595s peak_rss=141.0MB max_wal=9.44MB final_wal=0.00MB commits=15 checkpoints=15
  [repository_scan] 88.1ms files=190 items=190 writes=0
  [ast_parsing] 154.7ms files=13 items=3322 writes=0
  [database_analysis] 283.9ms files=13 items=1631 writes=0
  [symbol_resolution] 52.5ms files=190 items=5854 writes=0
  [relationship_resolution] 694.0ms files=190 items=32806 writes=0
  [sqlite_writes] 1146.4ms files=13 items=50206 writes=50208
scanned=190 indexed=13 unchanged=177 removed=0

4. Bounded Monorepo Route Discovery (`codegraph routes --limit 3`)

$ codegraph routes --limit 3
Found 3 route(s):
  [GET] /api/v1/health -> health_check (src/app/api.py:14) [fastapi]
  [POST] /api/v1/orders -> create_order (src/app/orders.py:42) [fastapi]
  [GET] /api/v1/users/{id} -> get_user (src/app/users.py:88) [fastapi]

5. Safe Background Process Termination (`codegraph stop --json`)

$ codegraph stop --json
{
  "status": "ok",
  "stopped_count": 0,
  "stale_cleaned_count": 0,
  "processes": []
}

5. AI/ML & Backend Architecture Examples

Example 1: Model Inference Service Flow

POST /v1/predict (FastAPI Route)
      ↓  HANDLED_BY (FRAMEWORK_VERIFIED)
predict_endpoint (Handler)
      ↓  INJECTS (DATAFLOW_VERIFIED)
get_inference_service (DI Provider)
      ↓  CALLS (AST_VERIFIED)
InferenceService.run_inference
      ├──►CALLS (AST_VERIFIED) ──► FeaturePreprocessor.transform
      ├──►CALLS (AST_VERIFIED) ──► FraudClassifier.forward
      ├──►CALLS (AST_VERIFIED) ──► ScorePostprocessor.calibrate
      └──►CALLS (AST_VERIFIED) ──► PredictionRepository.log_prediction
                                        ↓  WRITES_TABLE (AST_VERIFIED)
                                   db:table:postgresql.public.prediction_logs

What CodeGraph MCP structurally proves:

find_routes(path="/v1/predict") resolves composed router prefixes (MOUNTS) to predict_endpoint.
trace_path(from_symbol="predict_endpoint", to_symbol="log_prediction") proves the multi-hop execution chain across DI injection, preprocessing, model execution, and persistence.
get_db_impact(symbol="InferenceService.run_inference") identifies downstream writes to prediction_logs.

Example 2: Training & Evaluation Pipeline

train_cli (CLI Command Handler)
      ↓  COMMAND_HANDLER (FRAMEWORK_VERIFIED)
TrainingPipeline.run
      ├──►CALLS (AST_VERIFIED) ──► DatasetBuilder.load_splits
      ├──►CALLS (AST_VERIFIED) ──► TokenizerTransform.encode_batch
      ├──►CALLS (AST_VERIFIED) ──► Trainer.fit_epoch
      ├──►CALLS (AST_VERIFIED) ──► CheckpointManager.save_weights
      └──►CALLS (AST_VERIFIED) ──► Evaluator.compute_metrics

What CodeGraph MCP structurally proves:

find_callees(symbol="TrainingPipeline.run") enumerates every stage of the pipeline with exact file and line ranges.
find_tests(symbol="Evaluator.compute_metrics") locates the unit and regression tests covering metric calculation.
When a transform or model class is dynamically instantiated from a YAML string (getattr(models, cfg.arch)), CodeGraph MCP explicitly records POSSIBLE_CALLS (POSSIBLE) or UNRESOLVED_REFERENCE (UNKNOWN) rather than fabricating a false static call edge.

Example 3: LLM Agent & Tool Registry

POST /api/chat (LLM Endpoint)
      ↓  HANDLED_BY (FRAMEWORK_VERIFIED)
chat_handler
      ↓  CALLS (AST_VERIFIED)
AgentRunner.execute_step
      ├──►REGISTERS / REGISTERED_HANDLER ──► ToolRegistry ("search_orders", "refund_order")
      ├──►CALLS (AST_VERIFIED)           ──► ContextBuilder.compile
      ├──►READS_TABLE (AST_VERIFIED)     ──► db:table:postgresql.public.conversations
      └──►CALLS (AST_VERIFIED)           ──► ModelProviderClient.generate

What CodeGraph MCP structurally proves:

Tracks decorator and call-based registrations (@tool_registry.register("search_orders")) via REGISTERS and REGISTERED_HANDLER edges.
Tracks environment variable dependencies (os.getenv("OPENAI_API_KEY")) as READS_ENV edges with the variable name only—never indexing or exposing secret values.

6. Database Intelligence

src/codegraph/database/ provides static schema, ORM model, migration, and query extraction across SQLAlchemy, Django ORM, SQLModel, Prisma (.prisma), Alembic, Django Migrations, and Raw SQL (PostgreSQL, MySQL, SQLite).

POST /orders
      ↓  HANDLED_BY (FRAMEWORK_VERIFIED)
OrderService.create_order
      ↓  CALLS (AST_VERIFIED)
OrderRepository.insert_order
      ↓  WRITES_TABLE (AST_VERIFIED)
db:table:postgresql.public.orders
      ↓  FOREIGN_KEY_TO (AST_VERIFIED)
orders.user_id ──► users.id

Capabilities Exposed by the 11 Database MCP Tools

Table & Column Discovery (get_db_schema, get_db_table, find_db_tables, find_db_columns): Extract tables, column types, nullability, defaults, primary keys (HAS_PRIMARY_KEY), indexes (HAS_INDEX), unique/check constraints, and foreign keys (FOREIGN_KEY_TO).
ORM Mapping (find_db_models): Map SQLAlchemy __tablename__, Django models.Model (Meta.db_table), SQLModel table=True, and Prisma model blocks via MAPS_TO_TABLE and MAPS_TO_COLUMN.
Readers, Writers & Callers (find_db_readers, find_db_writers, find_db_callers, find_db_queries): Identify every function or method that executes SELECT (READS_TABLE) or INSERT / UPDATE / DELETE / .add() / .save() (WRITES_TABLE) against a table.
Migration Lineage & Schema Blast Radius (find_db_relationships, get_db_impact): Track Alembic (op.create_table, op.add_column) and Django (migrations.CreateModel, migrations.AddField) operations (MIGRATES_TABLE) and compute bidirectional code $\leftrightarrow$ database impact.

7. Zero-Friction Runtime Intelligence & Static Reconciliation

Static analysis proves what can happen structurally; runtime telemetry records what was observed during execution. CodeGraph MCP v3.0.0 brings them together transparently:

STATIC GRAPH (AST + Framework + Dataflow + DB)
                   +
RUNTIME OBSERVATION (codegraph run / OTel JSON / JSONL / SQL Logs)
                   ↓
       reconcile_static_runtime()

Reconciliation Outcomes (`ReconciliationStatus`)

Reconciliation Status	Static Graph	Runtime Trace	Meaning
`CONFIRMED_RUNTIME_PATH`	Present	Observed	Static relationship is structurally proven and observed executing in ingested traces.
`NOT_OBSERVED_AT_RUNTIME`	Present	Not observed	Statically valid edge was not exercised in the recorded trace sample.
`RUNTIME_ONLY_OBSERVED`	Dynamic / `UNKNOWN`	Observed	Executed at runtime (e.g., plugin hook, `getattr`, dynamic SQL) where static analysis was `UNKNOWN`.
`STATIC_RUNTIME_CONFLICT`	Target A	Target B	Runtime execution dispatched to a different target than static resolution (e.g., dependency override).

Epistemic Rules for Runtime Evidence

Runtime Telemetry Is Non-Invasive: codegraph run uses standard environment variable hooks (NODE_OPTIONS, PYTHONSTARTUP). You never modify application source code.
NOT_OBSERVED_AT_RUNTIME Does Not Mean Dead Code: It only indicates that the code path was not triggered during the recorded trace window (such as an error branch or periodic batch job).
Runtime Observations Never Overwrite Static Proof: Runtime spans are recorded with evidence_class="RUNTIME_OBSERVED" and strictly distinguished from AST_VERIFIED and FRAMEWORK_VERIFIED static edges.

8. Epistemic Trust & Evidence Contract

CodeGraph MCP enforces a fail-closed evidence contract (src/codegraph/evidence_contract.py) across all 51 canonical relationship types and 9 evidence classes. CodeGraph MCP prefers explicit uncertainty over fabricated certainty:

Dynamically resolved target (getattr(handler, action_name)())
      ↓
UNRESOLVED_REFERENCE / POSSIBLE_CALLS (status = "UNKNOWN" | "POSSIBLE")
(Never fabricated into a verified CALLS edge)

Epistemic Status	Allowed Evidence Classes	What It Means
`FACT`	`AST_VERIFIED`, `STATIC_VERIFIED`, `FRAMEWORK_VERIFIED`, `DATAFLOW_VERIFIED`	Proven directly from syntax tree, framework decorator/router semantics, or conservative local dataflow.
`RUNTIME_OBSERVED`	`RUNTIME_OBSERVED`	Observed in traces captured by `codegraph run` or ingested OTel/JSONL/SQL logs (`hit_count`, `duration_ms`).
`POSSIBLE`	`POSSIBLE`	Plausible candidate relationship (`POSSIBLE_CALLS`, `POSSIBLE_TABLE`) requiring source inspection before mutation.
`AMBIGUOUS`	`AMBIGUOUS`	Multiple symbols or database tables match the bare identifier across modules or dialects; returns sorted `candidates`.
`UNKNOWN`	`UNKNOWN`, `RUNTIME_UNOBSERVED`	Target cannot be statically proven (dynamic reflection, external dependency, or `reason="resolution_budget_exceeded"`).
`CONFLICT`	Static vs. Runtime / Multi-Source	Static analysis and runtime observation (or competing definitions) disagree.

8. Git-Aware Repository Intelligence & Merge Conflict Safety

CodeGraph MCP v3.0.0 tracks the exact evolution of repository code across commits, branches, and working tree changes:

Repository state
    ↓
Git change detection (CLEAN / DIRTY / STALE)
    ↓
Structural AST diff (functions, parameters, routes)
    ↓
Downstream impact analysis (callers, callees, tests, DB)
    ↓
Context freshness validation (VALID / PARTIALLY_STALE / STALE)
    ↓
Evidence-backed answer

1. Working Tree & Index Freshness (`codegraph git-state`)

Tracks current branch, current HEAD commit, indexed commit, and modified/staged files with sub-millisecond status caching:

codegraph git-state

Never silently serves stale repository facts. Explicitly reports CLEAN, DIRTY, STALE, REINDEXING, or ERROR.

2. Deep Visual Downstream Impact Tree (`codegraph git-impact --tree`)

Traverses affected callers, routes, tests, and DB writers with token-bounded results and visual ASCII hierarchy:

codegraph git-impact --tree

3. Semantic & Contract Merge Conflicts (`codegraph git-conflicts`)

Detects silent merge conflicts before git merge or pull request landing—such as branch A invoking a function or route handler that branch B deleted or altered:

codegraph git-conflicts main HEAD

4. Structural AST Diff (`codegraph git-diff`)

Computes semantic AST differences between Git revisions (added/removed/modified symbols, changed parameter signatures):

codegraph git-diff HEAD~1 HEAD

5. Deterministic Symbol History (`codegraph symbol-history`)

Traces symbol lifecycle across commits (introduced, modified, moved, renamed, or deleted):

codegraph symbol-history resolve_target

6. GitHub Action for Pull Request Impact

Automate change impact directly in your CI pipeline with .github/workflows/codegraph-pr-impact.yml and .github/actions/codegraph-impact/action.yml.

9. Measured Performance and Scaling Benchmarks

4-Tier Scaling Summary (`54` → `2,504` Files)

Empirically measured using benchmarks/run_v217_indexing_benchmark.py on macOS arm64, Python 3.13 with permanent SQLite WAL concurrency:

Workload Tier	Files	Symbols	Graph Edges	Baseline Total	v3.0.0 Measured	Measured Improvement	Peak RSS	Peak WAL	Final WAL
Small	`54`	`115`	`398`	`0.527 s`	`0.447 s`	15.2% faster (`1.18x`)	`48.00 MB`	`1.701 MB`	`0.0 MB`
Medium	`304`	`615`	`2,248`	`2.564 s`	`2.159 s`	15.8% faster (`1.19x`)	`69.72 MB`	`4.082 MB`	`0.0 MB`
Large	`1,004`	`2,015`	`7,428`	`8.730 s`	`7.157 s`	18.0% faster (`1.22x`)	`127.59 MB`	`5.190 MB`	`0.0 MB`
Stress	`2,504`	`5,015`	`18,528`	`21.983 s`	`18.937 s`	13.9% faster (`1.16x`)	`233.59 MB`	`6.628 MB`	`0.0 MB`

Stress Tier (`2,504` Files) Phase Breakdown

Phase / Metric	Legacy Baseline	v3.0.0 Measured	Measured Improvement
Total Indexing Time	`21.983 s`	`18.937 s`	13.9% faster (`1.16x`)
Database Intelligence Pass	`4.818 s`	`0.893 s`	81.5% faster (`5.40x`)
Post-Processing Phase	`13.770 s`	`12.061 s`	12.4% faster (`1.14x`)
Symbol Resolution Phase	`3.133 s`	`1.297 s`	58.6% faster (`2.42x`)
AST Parsing Phase	`3.410 s`	`3.230 s`	5.3% faster (`1.06x`)
Cold CLI Single-File Re-index	`4.408 s`	`3.665 s`	16.9% faster (`1.20x`)
Live In-Memory Incremental (`watch`)	Full scan required	`< 15ms` / file	Event-driven cache patch
Throughput (`files/sec`)	`113.9 files/s`	`132.2 files/s`	`+16.1%` throughput
Peak SQLite WAL Size	`46.980 MB`	`6.628 MB`	85.9% reduction (`7.09x` smaller)
Final SQLite WAL Size	`0.000 MB`	`0.000 MB`	100% reclaimed (`TRUNCATE`)

Note on Incremental Reindexing: The 3.665 s incremental figure measures a cold CLI invocation (codegraph index .) on the full 2,504-file repository, traversing file mtimes and checking Git diff state. In contrast, the active background daemon (codegraph watch) receives OS kernel filesystem events directly, parsing only the modified file's AST and patching SQLite in < 15ms.

50-Task Production Benchmark Results (`v3.0.0`)

Evaluated across 50 production tasks and 10 categories via benchmarks/run_v21_eval.py:

Production Benchmark Metric	Measured Result	Production Target	Status
Task Coverage	88.0%	$\ge 80.0%$	PASS
Symbol Recall	61.9%	$\ge 50.0%$	PASS
FACT Correctness	100.0%	$\ge 98.0%$	PASS
Unsupported Claim Rate (Hallucinations)	0.0%	$\le 1.0%$	PASS
UNKNOWN Correctness	98.0%	$\ge 95.0%$	PASS
AMBIGUITY Correctness	100.0%	$\ge 90.0%$	PASS
Average Context Payload	510 tokens	$\le 1,000$ tokens	PASS
Average Context Latency	40.52 ms	$\le 100$ ms	PASS
Token Reduction vs Full-File Extraction	41.8%	$\ge 35.0%$	PASS

32-Task A/B Exploration Evaluation (`src/codegraph/tool_selection_eval.py`)

Evaluated across 32 agent navigation tasks comparing unassisted grep/file reading vs CodeGraph MCP tool calls:

Metric (32-Task Evaluation Suite)	Mode A (Unassisted Grep & File Reads)	Mode B (CodeGraph MCP)	Measured Improvement
Total Tool Calls (32 Tasks)	`164 calls` (`~5.1 / task`)	`71 calls` (`~2.2 / task`)	`-56.7% fewer tool calls`
Direct Full-File Reads	`161 full-file reads`	`7 bounded slice reads`	`-95.7% fewer file reads`
Context Tokens per Task	`3,000 – 12,000+ tokens`	`~510 tokens` avg	`65.0% – 85.6% token reduction`
Query Latency (`p50`)	Hundreds of ms (multi-step `grep`)	`20.0 ms` cold / `0.67 ms` warm	Sub-20ms indexed lookup
First-Tool Selection Accuracy	`9.38%`	`100.0%`	`+90.62%`
Unsupported Claims (Hallucinated Edges)	`11 (34.38%)`	`0 (0.00%)`	`0% unsupported claims`
Task Accuracy	`59.84%`	`100.0%`	`+40.16%`

10. Where CodeGraph MCP Fits

CodeGraph MCP works alongside your editor's language server (LSP), ripgrep, and structural AST tools:

Legend: ✓ supported • ◐ partial / workflow-dependent • — not supported

Capability	CodeGraph MCP (`v3.0.0`)	Editor LSP	Structural AST (`ast-grep`)	Lexical Search (`ripgrep`)	Remote Code Search (`Sourcegraph`)
100% Local-First & Offline Operation	✓	✓	✓	✓	—
Native MCP Server for AI Agents	✓ (14 default / 70 full)	—	◐	—	✓
Multi-Transport Support (stdio + SSE HTTP)	✓	—	—	—	◐
Git-Aware AST Diffs & Freshness	✓ (6 Git tools)	—	—	—	◐
Zero-Friction Runtime Interceptor (`codegraph run`)	✓	—	—	—	—
Semantic Symbol Graph (Callers / Callees)	✓	◐ (Position-based)	◐ (Pattern-based)	—	✓ (SCIP)
Framework Route, Mount & DI Graph	✓ (`FastAPI`/`Flask`/`Django`/`Express`)	—	◐ (Custom rules)	—	—
Database Schema, ORM, Migration & Table R/W	✓ (11 DB tools)	—	—	—	—
Opt-In Runtime Ingestion & Reconciliation	✓ (OTel / JSONL / SQL)	—	—	—	—
Explicit Epistemic States (`FACT`/`UNKNOWN`)	✓	—	—	—	—
Literal Text Search Across HTML/JS/CSS/Config	✓ (`search_code`)	—	—	✓	✓
Interactive Editor Hover & Diagnostics	—	✓	✓ (Lint/Rewrite)	—	—

11. Security, Privacy & Redaction Boundaries

CodeGraph MCP runs 100% locally (stdio / sse MCP + local .codegraph.sqlite3), never executes repository code during indexing, and enforces strict file-access and redaction boundaries (src/codegraph/security/paths.py, src/codegraph/security/redaction.py):

Security Boundary	Enforcement Mode	Exact Behavior
Sensitive Files (`.env`, `.pem`, `.key`, `.crt`, `id_rsa`, `kubeconfig`, `.npmrc`, `.pypirc`, `secret*.json`)	`BLOCKED`	Excluded from indexing and FTS; direct inspection via `get_file` or `read_file` is rejected with `SENSITIVE_FILE_ACCESS_DENIED`.
Path Traversal & Symlinks (`../`, `%2e%2e`, null bytes, external symlinks)	`BLOCKED`	Canonical path check in `resolve_within_repo()` raises `SecurityError(ErrorCode.PATH_OUTSIDE_REPOSITORY)`.
Binary Files (`.pyc`, `.so`, `.dylib`, `.dll`, `.exe`, images, archives, PDFs)	`BLOCKED`	Classified as `BINARY` and skipped during indexing and text search.
Environment Variable Reads in Code (`os.getenv("DATABASE_URL")`)	Metadata Only	Records `READS_ENV` with the variable name only; never reads `.env` or runtime environment values.
Database Connection Strings (`postgresql://user:pass@host:5432/prod`)	`REDACTED`	Preserves dialect and database name while sanitizing credentials to `postgresql://[REDACTED]@[REDACTED]/prod`.
API Keys, Bearer Tokens, JWTs & Private Keys (`sk-...`, `ghp_...`, `AKIA...`)	`REDACTED`	Replaced with `[REDACTED_SECRET]` or `[REDACTED_PRIVATE_KEY]` before indexing, search, or MCP output.
Runtime HTTP Headers & SQL Literals (`authorization`, `cookie`, `WHERE password = '...'`)	`REDACTED`	Sensitive runtime keys and SQL literals are scrubbed (`[REDACTED]` / `?`) during `ingest_runtime_traces`.

Run codegraph privacy . at any time to audit the local database and verify that no sensitive files or unredacted secrets are stored.

12. MCP Tooling & Profiles (14 Default / 70 Full)

By default, create_server() exposes the 14-tool agent profile so AI coding agents receive a focused, non-overlapping tool surface. All 70 tools are available under --profile full.

Default `agent` Profile (14 High-Signal Tools)

Category	Tool	Purpose
Discovery (7)	`find_symbol`	Locate a symbol definition by short, qualified, or canonical name (`symbol=...`).
	`search_code`	Literal or regex search across Python, JS/TS, HTML/Jinja, CSS, YAML/JSON, Markdown, and SQL.
	`find_references`	Find verified AST reference, import, and registration sites for a symbol.
	`find_callers`	Find functions, methods, or route handlers that call the target symbol (`CALLS`, `POSSIBLE_CALLS`).
	`find_callees`	Find functions, methods, or constructors called by the target symbol.
	`find_tests`	Find `pytest` / `unittest` test functions covering a symbol, route, DI provider, or event handler.
	`find_routes`	Discover FastAPI, Flask, Django, and Express HTTP routes with composed mount prefixes.
Details & Context (5)	`get_symbol`	Retrieve signature, decorators, docstring, line range, and methods for a symbol.
	`get_file`	Read bounded line ranges (`start_line`, `end_line`, `max_lines`) and AST symbol outline of a file.
	`get_context`	Compile a token-budgeted, task-aware context packet (`query`, `intent`, `max_tokens`).
	`get_architecture`	Summarize repository languages, layers, packages, entrypoints, routes, and database entities.
	`get_git_impact`	Compute blast-radius impact (`changed_files`, `affected_callers`, `affected_routes`, `tests`) for a Git diff.
Graph Tracing (2)	`trace_path`	Find the shortest verified execution path between `from_symbol` and `to_symbol`.
	`trace_flow`	Trace upstream callers and downstream callees around `symbol` up to `depth`.

All 6 Implemented MCP Profiles (`src/codegraph/agent_capabilities.py`)

Profile	Tool Count	Description
`agent` (default in `create_server`)	14	High-signal discovery, bounded file inspection, context synthesis, and path tracing.
`core`	13	Lightweight symbol lookup, callers/callees, imports/dependents, routes, and architecture.
`graph`	17	Call-graph traversal, blast-radius impact (`analyze_impact`), and test discovery.
`minimal`	21	Core interrogation plus `get_context`, `search_code`, `read_file`, and `verify_evidence`.
`developer`	34	Interactive development with Git history (`get_file_history`, `get_recent_changes`) and retrieval planning.
`full`	70	Complete capability surface including 11 Database tools, 3 Runtime tools, and 6 Git Intelligence tools (`get_git_state`, `compare_git`, `get_change_impact`, `check_context_freshness`, `trace_symbol_history`, `detect_semantic_conflicts`).

13. Complete CLI Reference

Verified against src/codegraph/cli.py:

# Agent Onboarding & Uninstall
codegraph install                                          # Interactive agent detection & setup
codegraph install --yes --target auto --location local     # Non-interactive local setup
codegraph install --print-config claude                    # Print MCP JSON + rules for an agent
codegraph install --dry-run                                # Preview planned file changes
codegraph uninstall --yes                                  # Remove CodeGraph MCP agent integrations

# Git-Aware Repository Intelligence (v3.0.0)
codegraph git-state .                                      # Track HEAD, working tree, and freshness (CLEAN/DIRTY/STALE)
codegraph git-diff HEAD~1 HEAD                             # Semantic AST diff across commits or branches
codegraph git-impact --tree                                # Deep downstream change impact with visual ASCII tree
codegraph git-conflicts main HEAD                          # Detect pre-merge semantic & contract conflicts
codegraph check-freshness "audit auth flow"                # Validate if compiled context is VALID or STALE
codegraph symbol-history resolve_target                    # Trace deterministic symbol lifecycle across commits

# Zero-Friction Runtime Interceptor (v3.0.0)
codegraph run npm run dev                                  # Wrap Node/Express/Next.js dev server
codegraph run uvicorn main:app --reload                    # Wrap FastAPI/ASGI dev server
codegraph run python manage.py runserver                   # Wrap Django dev server
codegraph run --sample-rate 0.5 npm test                   # Sample 50% of captured traces

# Repository Initialization & Indexing
codegraph init .                                           # Initialize and index repository
codegraph index . --verbose                                # Incremental index with 16-phase telemetry
codegraph index . --json                                   # Output structured JSON phase telemetry
codegraph uninit --dry-run                                 # Preview removal of .codegraph.sqlite3

# Process Lifecycle & Upgrade Lock Safety
codegraph stop                                             # Safely stop CodeGraph MCP server for current repo
codegraph stop --all                                       # Stop all CodeGraph-owned MCP processes across repos
codegraph doctor --processes                               # Inspect active MCP processes & parent PIDs

# Health, Integrity & Freshness Diagnostics
codegraph status .                                         # Show index freshness (sub-50ms Git fast path)
codegraph doctor . --database --processes                  # Verify SQLite integrity, FKs, FTS, and memory
codegraph privacy .                                        # Verify zero sensitive files indexed
codegraph version                                          # Print CodeGraph MCP version (3.0.0)

# Code, Graph, Routes & Context Interrogation
codegraph search "authenticate" -r .                       # Search indexed symbols and text chunks
codegraph symbols src/codegraph/cli.py -r .                # List extracted symbols in a file
codegraph get-symbol Indexer -r .                          # Get AST details for a symbol
codegraph resolve-symbol resolve_Repository -r .           # Ground symbol or return candidates
codegraph trace Indexer -d 2 -r .                          # Trace callers and callees up to depth 2
codegraph routes -r . --limit 25 --offset 0                # List routes with bounded pagination
codegraph architecture -r .                                # Summarize repository architecture
codegraph context "trace /api/v1/auth/login" -r .          # Compile token-budgeted ContextPacket

# MCP Server Subcommands
codegraph serve .                                          # Start stdio MCP server (14 default tools)
codegraph serve . --profile full                           # Start stdio MCP server with all 70 tools
codegraph serve . --transport sse --port 8765              # Start SSE HTTP server on port 8765
codegraph mcp serve . --transport sse                      # Alias for SSE MCP server
codegraph mcp stop                                         # Stop active MCP processes

14. Documentation Map

Deep Agent Brain & 70-Tool Reference: docs/agent-brain.md
Compact Tool Capabilities Summary: agent-rules/tool-capabilities-summary.md
Detailed Multi-Tool Capability Comparison: docs/tool-comparison.md
Antigravity Skill (SKILL.md): .agents/skills/codegraph/SKILL.md
Agent Rule Packs (Claude, Cursor, Antigravity, Codex, Gemini, Cline): agent-rules/README.md & agent-rules/AGENTS.md
Engineering & Production Readiness: docs/engineering/production-readiness.md
Reproducible Scaling Benchmark Script: benchmarks/run_v217_indexing_benchmark.py
Changelog: CHANGELOG.md

15. Contributing & License

git clone http://github.com/raghurammrsd/CODE_GRAPH_MCP.git
cd CODE_GRAPH_MCP
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev,mcp,system]"

python3 -m ruff check .
python3 -m mypy src/
python3 -m pytest -q

Licensed under the MIT License.

Name		Name	Last commit message	Last commit date
.agents		.agents
.codex		.codex
.cursor		.cursor
.github		.github
agent-rules		agent-rules
benchmarks		benchmarks
docs		docs
examples/demo-repository		examples/demo-repository
scripts		scripts
src/codegraph		src/codegraph
tests		tests
vscode-extension		vscode-extension
.cursorrules		.cursorrules
.gitignore		.gitignore
AGENTS.md		AGENTS.md
CHANGELOG.md		CHANGELOG.md
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
LICENSE		LICENSE
README.md		README.md
SECURITY.md		SECURITY.md
pyproject.toml		pyproject.toml
sitemap.txt		sitemap.txt
sitemap.xml		sitemap.xml

Latest commit

History

Folders and files

Repository files navigation

CodeGraph MCP: Full-Stack Knowledge Graph & Semantic Intelligence for AI Coding Agents

Overview

The Problem

The Solution: CodeGraph MCP

Core Architecture Capabilities

Measured Performance & Real Metrics Benchmark

Interactive Web Dashboard & VS Code Extension

1. Interactive Knowledge Graph Web Dashboard (codegraph ui)

2. Official VS Code Extension (vscode-extension)

The Three Pillars of CodeGraph MCP

AI / ML & PyTorch Stack Intelligence

Roblox & Luau Intelligence (codegraph roblox)

Pillar 1: The Unified Full-Stack Bridge (codegraph api-drift)

Pillar 2: Semantic Change Impact & PR Blast Radius Engine (codegraph impact)

Pillar 3: Incremental Live Watcher & Instant Cache Invalidation (codegraph watch)

1. What's New in v3.0.0

1.1 Git-Aware Repository Intelligence

1.2 Engine Robustness & Accuracy Hardening

1.3 Enterprise Concurrency & Runtime Interceptor

2. Quickstart (30-Second Setup)

Step 1: Install the Package

Step 2: Configure Your AI Coding Agents (codegraph install)

Step 3: Initialize & Verify Your Project Index

Step 4: Run With Zero-Friction Telemetry (codegraph run)

3. Core Architecture & Mental Model

Routing Each Question to the Right Primitive

4. Real-World CLI Outputs

1. Zero-Friction Runtime Interceptor (codegraph run)

2. Instant Index Freshness Check (codegraph status)

3. Incremental Indexing with 16-Phase Telemetry (codegraph index --verbose)

4. Bounded Monorepo Route Discovery (codegraph routes --limit 3)

5. Safe Background Process Termination (codegraph stop --json)

5. AI/ML & Backend Architecture Examples

Example 1: Model Inference Service Flow

Example 2: Training & Evaluation Pipeline

Example 3: LLM Agent & Tool Registry

6. Database Intelligence

Capabilities Exposed by the 11 Database MCP Tools

7. Zero-Friction Runtime Intelligence & Static Reconciliation

Reconciliation Outcomes (ReconciliationStatus)

Epistemic Rules for Runtime Evidence

8. Epistemic Trust & Evidence Contract

8. Git-Aware Repository Intelligence & Merge Conflict Safety

1. Working Tree & Index Freshness (codegraph git-state)

2. Deep Visual Downstream Impact Tree (codegraph git-impact --tree)

3. Semantic & Contract Merge Conflicts (codegraph git-conflicts)

4. Structural AST Diff (codegraph git-diff)

5. Deterministic Symbol History (codegraph symbol-history)

6. GitHub Action for Pull Request Impact

9. Measured Performance and Scaling Benchmarks

4-Tier Scaling Summary (54 → 2,504 Files)

Stress Tier (2,504 Files) Phase Breakdown

50-Task Production Benchmark Results (v3.0.0)

32-Task A/B Exploration Evaluation (src/codegraph/tool_selection_eval.py)

10. Where CodeGraph MCP Fits

11. Security, Privacy & Redaction Boundaries

12. MCP Tooling & Profiles (14 Default / 70 Full)

Default agent Profile (14 High-Signal Tools)

All 6 Implemented MCP Profiles (src/codegraph/agent_capabilities.py)

13. Complete CLI Reference

14. Documentation Map

15. Contributing & License

About

Resources

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages

1. Interactive Knowledge Graph Web Dashboard (`codegraph ui`)

2. Official VS Code Extension (`vscode-extension`)

Roblox & Luau Intelligence (`codegraph roblox`)

Pillar 1: The Unified Full-Stack Bridge (`codegraph api-drift`)

Pillar 2: Semantic Change Impact & PR Blast Radius Engine (`codegraph impact`)

Pillar 3: Incremental Live Watcher & Instant Cache Invalidation (`codegraph watch`)

Step 2: Configure Your AI Coding Agents (`codegraph install`)

Step 4: Run With Zero-Friction Telemetry (`codegraph run`)

1. Zero-Friction Runtime Interceptor (`codegraph run`)

2. Instant Index Freshness Check (`codegraph status`)

3. Incremental Indexing with 16-Phase Telemetry (`codegraph index --verbose`)

4. Bounded Monorepo Route Discovery (`codegraph routes --limit 3`)

5. Safe Background Process Termination (`codegraph stop --json`)

Reconciliation Outcomes (`ReconciliationStatus`)

1. Working Tree & Index Freshness (`codegraph git-state`)

2. Deep Visual Downstream Impact Tree (`codegraph git-impact --tree`)

3. Semantic & Contract Merge Conflicts (`codegraph git-conflicts`)

4. Structural AST Diff (`codegraph git-diff`)

5. Deterministic Symbol History (`codegraph symbol-history`)

4-Tier Scaling Summary (`54` → `2,504` Files)

Stress Tier (`2,504` Files) Phase Breakdown

50-Task Production Benchmark Results (`v3.0.0`)

32-Task A/B Exploration Evaluation (`src/codegraph/tool_selection_eval.py`)

Default `agent` Profile (14 High-Signal Tools)

All 6 Implemented MCP Profiles (`src/codegraph/agent_capabilities.py`)