symgraph
Semantic code intelligence MCP server - build knowledge graphs of codebases to enhance AI-assisted code exploration.
symgraph is a rust implementation of https://github.com/colbymchenry/codegraph. Why? Ongoing exploration of compiled binary deployment of MCP Servers.
Features
- Multi-language support: Rust, TypeScript, JavaScript, Python, Go, Java, C, C++
- Symbol extraction: functions, classes, methods, structs, interfaces, traits, enums, constants
- Relationship tracking: calls, contains, imports, exports, extends, implements
- Impact analysis: trace the effect of changes through the codebase
- Advanced code intelligence:
- Find call paths between functions
- Detect unused/dead code
- Explore class hierarchies
- Locate all interface implementations
- Analyze change impact by line range
- Incremental indexing: only re-indexes changed files using content hashing
- Dual transport: stdio (default) and HTTP server modes
Installation
macOS & Linux
|
To also configure symgraph as an MCP server for Claude Code and Claude Desktop:
|
Install a specific version:
SYMGRAPH_VERSION=2026.3.30 |
Windows (PowerShell)
irm https://raw.githubusercontent.com/grahambrooks/symgraph/main/install.ps1 -OutFile install.ps1; .\install.ps1
To also configure symgraph as an MCP server for Claude Code and Claude Desktop:
irm https://raw.githubusercontent.com/grahambrooks/symgraph/main/install.ps1 -OutFile install.ps1; .\install.ps1 -Mcp
Install a specific version:
$env:SYMGRAPH_VERSION="2026.3.30"; irm https://raw.githubusercontent.com/grahambrooks/symgraph/main/install.ps1 -OutFile install.ps1; .\install.ps1
Both scripts install to ~/.symgraph/bin/ by default. Override with SYMGRAPH_INSTALL_DIR.
Claude Desktop (MCPB Bundle)
Download and install the MCPB bundle for your platform:
| Platform | Download |
|---|---|
| macOS (Apple Silicon) | symgraph-x.x.x-darwin-arm64.mcpb |
| macOS (Intel) | symgraph-x.x.x-darwin-x64.mcpb |
| Windows | symgraph-x.x.x-windows-x64.mcpb |
| Linux | symgraph-x.x.x-linux-x64.mcpb |
- Download the
.mcpbfile for your platform from Releases - Open Claude Desktop
- Drag and drop the
.mcpbfile onto Claude Desktop, or use File > Install MCP Server - Configure the project root when prompted
From Source
Usage
Index a Codebase
# Index current directory
# Index specific directory
Start MCP Server
# Start with stdio transport (for Claude Desktop)
# Start with HTTP transport
CLI Commands
Almost every MCP tool is also a CLI subcommand (handy for testing and for
agents driven by a CLI skill instead of MCP). Run symgraph help for the full
list with arguments and options.
# Core
# Symbol relationships (query the current project's index)
# Impact, git history & coupling
Add --format json for machine-readable output (supported by every command
except blame, churn, and diff-impact), and --db <path> to point at a
specific index database. The MCP tools accept the same format: "json"
argument — both surfaces render through one shared ops layer, so CLI and
server output match.
MCP Tools
Core Tools
| Tool | Description |
|---|---|
symgraph-context |
Build focused code context for a specific task |
symgraph-search |
Quick symbol search by name |
symgraph-callers |
Find all callers of a symbol |
symgraph-callees |
Find all callees of a symbol |
symgraph-impact |
Impact + inbound coupling breakdown (contract/model/intrusive) |
symgraph-node |
Get detailed symbol information |
symgraph-definition |
Get the full source code of a symbol with context |
symgraph-file |
List all symbols defined in a specific file |
symgraph-references |
Find all references to a symbol |
symgraph-reindex |
Trigger incremental reindexing of changed files |
symgraph-status |
Get index statistics |
Advanced Tools
| Tool | Description |
|---|---|
symgraph-hierarchy |
Get class/module hierarchy (parent/child relationships) |
symgraph-path |
Find call paths between two symbols |
symgraph-unused |
Find unused/dead code with no incoming references |
symgraph-implementations |
Find all implementations of an interface/trait |
symgraph-diff-impact |
Analyze the impact of changing a specific code region |
Git-aware Tools
| Tool | Description |
|---|---|
symgraph-blame |
Git blame a symbol's definition lines |
symgraph-churn |
File change frequency over a recent window (volatility) |
Coupling Analysis Tools
These fold the resolved graph onto the strength × distance × volatility
framework. Edges come from accesses (field reads), mutates (field
writes / &mut), imports, and enum-dispatch references — so run
symgraph-reindex after code changes to populate them. Resolution is
name-based (heuristic), best for ranking hotspots. All accept format="json".
| Tool | Description |
|---|---|
symgraph-module-graph |
Dependency adjacency, fan-in/fan-out, and cycles (SCCs) at a file/dir/module boundary |
symgraph-coupling-score |
Rank module-pair coupling by strength × distance × volatility (churn) |
symgraph-god-struct |
Rank structs/classes by pub-field × inbound-refs × churn (architectural debt) |
symgraph-dispatch-sites |
Find every file that matches/switches on an enum's members (control coupling) |
Example Use Cases
Find dead code for cleanup:
Use symgraph-unused to find all unused functions and classes
Understand function call chains:
Use symgraph-path with from="main" and to="database_query" to see how data flows
Assess change impact:
Use symgraph-diff-impact with file_path="src/auth.rs" start_line=45 end_line=60
to see what would be affected by changes in that region
Explore OOP hierarchies:
Use symgraph-hierarchy with symbol="BaseHandler" to see all parent/child relationships
Find all trait implementations:
Use symgraph-implementations with symbol="Iterator" to find all structs implementing Iterator
Project Setup
Add symgraph to your project in two steps: index your code, then configure your AI tool.
Step 1: Index Your Project
This creates a .symgraph/ directory containing the SQLite knowledge graph. Add .symgraph/ to your .gitignore.
Re-run symgraph index after significant code changes, or use the symgraph-reindex MCP tool to incrementally update from within your AI tool.
Step 2: Configure Your AI Tool
Claude Code
Register symgraph as an MCP server for your project:
Or add .mcp.json to your project root:
Optional: Add the /explore-code skill for guided code exploration:
Then use it in Claude Code:
/explore-code how does the authentication middleware work?
/explore-code what would break if I changed the User struct?
Claude Desktop
Via MCPB bundle (easiest):
- Download the
.mcpbfile for your platform from Releases - Drag and drop onto Claude Desktop, or use File > Install MCP Server
- Set the project root when prompted
Via manual config — add to claude_desktop_config.json:
GitHub Copilot
Per-repository — add .copilot/mcp.json to your project:
VS Code user settings — add to settings.json:
See GitHub Copilot MCP documentation for more details.
OpenAI Codex
Or add to ~/.codex/config.toml:
[]
= "symgraph"
= ["serve"]
See OpenAI Codex MCP documentation for more details.
HTTP Mode (Any MCP Client)
For shared or remote setups, run symgraph as an HTTP server:
Then point your MCP client at http://localhost:8080/mcp.
Environment Variables
| Variable | Description | Default |
|---|---|---|
SYMGRAPH_ROOT |
Project root directory | Current directory |
SYMGRAPH_DB |
Explicit index database path (highest priority) | — |
SYMGRAPH_STORAGE |
Index location strategy: git / cache / local |
auto |
SYMGRAPH_IN_MEMORY |
1 ⇒ ephemeral in-memory index (no disk writes) |
off |
SYMGRAPH_AUTH_TOKEN |
Bearer token for HTTP /mcp |
— |
Index Storage
The index is persistent and shared between the CLI and the MCP server, so you
symgraph index once and both use it. The location is resolved by this chain
(use symgraph where to see what's chosen):
--db <path>/SYMGRAPH_DB— explicit override.--in-memory/SYMGRAPH_IN_MEMORY=1— ephemeral (good for long-running MCP sessions, CI, and read-only checkouts; rebuilt on start).SYMGRAPH_STORAGEstrategy, or the auto default:- reuse an existing
.symgraph/if present (back-compat), else git→<git-common-dir>/symgraph/index.db— co-located with the repo, never tracked, no.gitignoreentry needed (the default in a git repo; handles worktrees/submodules), elsecache→ an OS cache dir keyed by the repo path (for non-git dirs).
- reuse an existing
symgraph prune removes cached indexes whose source repo no longer exists.
local storage writes a self-.gitignore so even in-tree indexes don't dirty
git status.
Architecture
symgraph/
├── src/
│ ├── main.rs # CLI entry point
│ ├── lib.rs # Core indexing logic
│ ├── types.rs # Type definitions (Node, Edge, etc.)
│ ├── db/ # SQLite database operations
│ ├── extraction/ # Tree-sitter code extraction
│ ├── graph/ # Graph traversal algorithms
│ ├── context/ # Context building for AI tasks
│ └── mcp/ # MCP protocol handlers
└── .symgraph/
└── index.db # SQLite database (per-project)
Core Concepts
- Node: A code symbol (function, class, method, etc.)
- Edge: A relationship between nodes (calls, contains, imports, etc.)
- Knowledge Graph: The complete set of nodes and edges for a codebase
Development
Prerequisites
- Rust 1.70+
- SQLite (bundled via rusqlite)
Building
Project Structure
| Module | Description |
|---|---|
types |
Core type definitions (NodeKind, EdgeKind, Language, etc.) |
db |
SQLite database schema and operations |
extraction |
Tree-sitter based code parsing and symbol extraction |
graph |
Graph algorithms (callers, callees, impact analysis) |
context |
Context builder for AI task assistance |
mcp |
MCP protocol server implementation |
License
MIT