Cross-language code intelligence for AI agents and developers.
CodeGraph
Cross-language code intelligence for AI agents and developers.
CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 31 tools, a VS Code extension, and a persistent memory layer. AI agents get structured code understanding instead of grepping through files.
Quick Start
MCP Server (Claude Code, Cursor, any MCP client)
npm install -g @memoryx/codegraph-mcp
Add to ~/.claude.json (or your MCP client config):
{
"mcpServers": {
"codegraph": {
"command": "codegraph-mcp",
"args": []
}
}
}
The server indexes the current working directory automatically — no --workspace flag needed. It also accepts MCP roots from the client for workspace discovery.
Multi-project indexing — index multiple codebases into a single graph:
{
"mcpServers": {
"codegraph": {
"command": "codegraph-mcp",
"args": [
"--workspace", "/path/to/frontend",
"--workspace", "/path/to/backend",
"--workspace", "/path/to/shared-lib"
]
}
}
}
VS Code Extension
code --install-extension codegraph-0.10.0.vsix
The extension registers 30 tools as VS Code Language Model Tools. To steer Copilot toward using them:
// .vscode/settings.json
{
"github.copilot.chat.codeGeneration.instructions": [
"When analyzing code structure, callers, callees, dependencies, or complexity, prefer codegraph_* tools over file search. CodeGraph has a pre-built semantic graph that returns structured results instantly."
]
}
Tools (31)
Code Analysis (9)
| Tool | What it does |
|---|---|
get_ai_context |
Primary context tool. Intent-aware (explain/modify/debug/test) with token budgeting. Returns source, related symbols (full or signature-only), file imports, sibling functions, debug hints, architecture. |
get_edit_context |
Everything needed before editing: source + callers + tests + memories + git history |
get_curated_context |
Cross-codebase context for a natural language query ("how does auth work?") |
get_dependency_graph |
File/module import relationships with depth control |
get_call_graph |
Function call chains (callers and callees) |
analyze_impact |
Blast radius prediction — what breaks if you modify, delete, or rename |
analyze_complexity |
Cyclomatic complexity with breakdown (branches, loops, nesting, exceptions, early returns) |
find_unused_code |
Dead code detection with confidence scoring |
analyze_coupling |
Module coupling metrics and instability scores |
Code Navigation (12)
| Tool | What it does |
|---|---|
symbol_search |
Find symbols by name (hybrid BM25 + semantic search) |
get_callers / get_callees |
Who calls this? What does it call? (with transitive depth) |
get_detailed_symbol |
Full symbol info: source, callers, callees, complexity |
get_symbol_info |
Quick metadata: signature, visibility, kind |
find_by_imports |
Find files importing a module (moduleName param) |
find_by_signature |
Search by param count, return type, modifiers |
find_entry_points |
Main functions, HTTP handlers, tests |
find_related_tests |
Tests that exercise a given function |
traverse_graph |
Custom graph traversal with edge/node type filters |
cross_project_search |
Search across all indexed projects |
Memory (10)
Persistent AI context across sessions — debugging insights, architectural decisions, known issues.
| Tool | What it does |
|---|---|
memory_store / memory_get / memory_search |
Store, retrieve, search memories (BM25 + semantic) |
memory_context |
Get memories relevant to a file/function |
memory_list / memory_invalidate / memory_stats |
Browse, retire, monitor |
mine_git_history / mine_git_history_for_file |
Auto-create memories from commits |
search_git_history |
Semantic search over commit history |
All tool names are prefixed with codegraph_ (e.g. codegraph_get_ai_context).
Languages
17 languages parsed via tree-sitter — all with functions, imports, call graph, complexity metrics, dependency graphs, symbol search, impact analysis, and unused code detection:
TypeScript/JS, Python, Rust, Go, C, C++, Java, Kotlin, C#, PHP, Ruby, Swift, Tcl, Verilog/SystemVerilog, COBOL, Fortran
Architecture
MCP Client (Claude, Cursor, ...) VS Code Extension
| |
MCP (stdio) LSP Protocol
| |
└───────────┐ ┌───────────┘
▼ ▼
┌───────────────────────────
Tools (10)
get_ai_contextPrimary context tool for intent-aware code analysis including source, related symbols, and architecture.get_edit_contextRetrieves source, callers, tests, memories, and git history for editing.get_curated_contextProvides cross-codebase context for natural language queries.analyze_impactPredicts the blast radius of code modifications, deletions, or renames.analyze_complexityCalculates cyclomatic complexity with a breakdown of branches, loops, and nesting.find_unused_codeDetects dead code with confidence scoring.symbol_searchFinds symbols by name using hybrid BM25 and semantic search.get_callersIdentifies functions that call a specific symbol.get_calleesIdentifies functions called by a specific symbol.memory_storeStores persistent AI context across sessions.Configuration
{"mcpServers": {"codegraph": {"command": "codegraph-mcp", "args": []}}}