Turns source code into a resolved map of files, symbols, references, and dependencies to provide structural context for coding agents.
Also known as lzehrung/codegraph, @lzehrung/codegraph
- Stars
- 9
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 13, 2026
- License
- MIT
What is codegraph MCP?
codegraph turns source code into a resolved map of files, symbols, references, and dependencies to provide structural context for coding agents.
Summary generated from the project's README
About codegraph MCP server
Providing coding agents with a structural map of a repository instead of a collection of search results is what codegraph does. It transforms a source tree into a resolved map containing files, symbols, references, and dependencies to give AI clients deep structural context. This allows an agent to understand how components connect and what a specific change might break without wasting turns listing directories or guessing search terms.
Developers can use this as a local CLI or a TypeScript library. It requires Node.js 22.16 or newer, though standalone installers are available for environments without npm. The tool works alongside text search and compilers to fill in the cross-file repository map. It provides specific commands like codegraph review for inspecting changes, codegraph deps for dependency analysis, and codegraph explore for finding implementation details and relevant tests.
What you can do with it
- 1Assess change impactAn agent can determine which tests to run or what might break after a code modification.
- 2Perform semantic refactoringYou can identify where a specific symbol is used or see the blast radius of a rename.
- 3Analyze repository healthIdentify code duplication or find files that act as hotspots due to high connection counts.
Written from the project's README. Every use case is checked against a quote from it.
How to install codegraph MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall codegraph MCP in Claude Code
$ claude mcp add codegraph -- npx -y @lzehrung/codegraphInstall codegraph MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"codegraph": {
"command": "npx",
"args": [
"-y",
"@lzehrung/codegraph"
]
}
}
}Install codegraph MCP in VS Code
.vscode/mcp.json
{
"servers": {
"codegraph": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@lzehrung/codegraph"
]
}
}
}Install codegraph MCP in VS Code CLI
$ code --add-mcp '{"name":"codegraph","type":"stdio","command":"npx","args":["-y","@lzehrung/codegraph"]}'Install codegraph MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"codegraph": {
"command": "npx",
"args": [
"-y",
"@lzehrung/codegraph"
]
}
}
}Install codegraph MCP in Codex
$ codex mcp add codegraph -- npx -y @lzehrung/codegraphInstall codegraph MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.codegraph] command = "npx" args = ["-y", "@lzehrung/codegraph"]
Install codegraph MCP in Gemini CLI
$ gemini mcp add -s user codegraph npx -- -y @lzehrung/codegraphInstall codegraph MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"codegraph": {
"command": "npx",
"args": [
"-y",
"@lzehrung/codegraph"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablelzehrung/codegraph is public and reachablegithub.com/lzehrung/codegraph ↗Pass
- Package names this repository as its source@lzehrung/codegraph names lzehrung/codegraph as sourcenpmjs.com/package/@lzehrung/codegraph ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @lzehrung/codegraphnpmjs.com/package/@lzehrung/codegraph/v/3.2.1#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/lzehrung/codegraph ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @lzehrung/codegraphPass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubcodegraph
Give your coding agent a map of the repository, not a pile of search results.
codegraph is a local CLI and TypeScript library that turns a source tree into a resolved map of files, symbols, references, and dependencies. Ask where an implementation lives, how components connect, what a change can break, or which tests are relevant, then get bounded source evidence and copyable next steps.
codegraph is not an AST, a compiler, or a linter. People can use codegraph review and codegraph deps to inspect changes and dependencies without an agent.
Without structural context, an agent burns early turns listing directories, guessing search terms, opening candidate files, and reconstructing relationships. codegraph does that discovery once so the context window can stay focused on the problem.
With Node.js 22.16 or newer, install from npm:
npm install -g @lzehrung/codegraph
codegraph doctor
codegraph install
codegraph explore "build review report" --root .
No Node.js or npm? The standalone installers download a self-contained bundle with Node.js, the CLI, and the matching native runtime:
irm https://github.com/lzehrung/codegraph/releases/latest/download/install.ps1 | iex
curl -fsSL https://github.com/lzehrung/codegraph/releases/latest/download/install.sh | sh
Use codegraph alongside text search and compilers: text search finds exact strings, compilers prove language behavior, and codegraph fills in the cross-file repository map between them. See Installation for npm, standalone, and source-checkout paths.
Table of contents
- Changelog
- What you can do
- Try it
- A useful first five minutes
- Visualize a graph
- What the output looks like
- Why codegraph
- Why not just grep or an LSP?
- Agent setup
- Language support
- Using as a library
- How it works
- Limits and tradeoffs
- Documentation
- Development
What you can do
| Job | Question | Start here | What comes back |
|---|---|---|---|
| Review | What could this change break? | codegraph review |
Changed symbols, risks, and candidate tests |
| Review | Which tests should I run? | codegraph affected --base HEAD --head WORKTREE --quiet |
Test paths from changed files and reverse dependencies |
| Review | Where should I start reading for a topic? | codegraph explore "<terms>" --root . |
Top search hits with their source, dependents, and candidate tests |
| Refactor | Where is this symbol used? | codegraph refs src/file.ts:10:5 |
Semantic references and coverage |
| Refactor | What depends on this file? | codegraph rdeps src/file.ts --json |
Reverse dependencies |
| Refactor | What evidence supports a change? | codegraph refactor-plan <symbol-target> |
Read-only evidence; no code changes |
| Refactor | Where would a rename apply? | codegraph rename-preview <symbol-target> <new-name> |
Read-only edits and conflicts; no code changes |
| Quality | Which files have the most connections? | codegraph hotspots ./src --limit 20 |
Fan-in and fan-out ranking |
| Quality | Where is code duplicated? | codegraph duplicates ./src --min-confidence medium |
Ranked duplicate groups |
| Docs | Which public symbols exist? | codegraph apisurface |
Exported API symbols |
| Docs | Which exports have no indexed docstring? | codegraph apisurface --undocumented |
Locations; partial coverage names unchecked files |
| Docs | Are Markdown links broken? | codegraph links --root . |
Broken local links with ranges; external URLs skipped |
CLI output is readable by default. Use --json for structured fields and omission counts.
Try it
See Installation for npm, standalone, and source-checkout steps.
A useful first five minutes
Do not begin by generating every possible report. Start with the question you actually have.
Understand an unfamiliar repo
# Map the repository before selecting a target
codegraph orient --root . --budget small
# Search a concrete term (the query is lexical: use the words that appear in code)
codegraph search "build review report" --json
# explore: search, then bundle the top hits with source, dependents, and candidate tests
codegraph explore "build review report" --root .
# Follow a returned target
codegraph explain src/review.ts
codegraph deps src/review.ts --json
codegraph refs src/review.ts:215:23
Review local changes
# Compact reviewer handoff for staged and unstaged tracked changes
codegraph review
# Broader blast-radius map when the summary needs expansion
codegraph impact --base HEAD --head WORKTREE
# Deterministic affected-test paths for focused validation
codegraph affected --base HEAD --head WORKTREE --quiet
Use --head STAGED to compare HEAD with the index, or use refs such as --base origin/main --head HEAD for a branch review.
Inspect repository health
codegraph inspect ./src --limit 20
codegraph cycles --sort priority
codegraph unresolved
codegraph apisurface
codegraph duplicates ./src --min-confidence medium --limit 20
codegraph drift ./src --base origin/main --head HEAD --graph-edges summary --public-api removals
# Validate local Markdown links offline (exit 1 on broken links)
codegraph links --root .
Export the model
codegraph graph --root . ./src --json --output codegraph.json
codegraph graph --root . ./src --mermaid --output graph.mmd
codegraph graph --root . ./src --dot --output graph.dot
codegraph graph --root . ./src --sqlite codegraph.sqlite
Visualize a graph
The packaged viewer is a human-facing graph UI; agents should use graph JSON, SQLite, MCP, or --json instead. Its command is codegraph viewer [--root <root>] [--graph <root-confined-json>] [--host <host>] [--port <0-65535>] [--open] [--print-url]; the root defaults to the current directory.

codegraph viewer --root . --open
codegraph viewer --root . --graph codegraph-out/graph.json --open
codegraph viewer --root . --port 4173 --print-url
The default host is 127.0.0.1 and the default port is 4173. Without --graph, each UI load or reload builds a current graph projection through the automatically validated .codegraph/cache/index-v1 index; init, index, and an exported JSON file are not prerequisites. An explicit --graph serves that root-confined snapshot through the same /graph.json route, while --print-url only prints the deterministic URL and exits.
The UI loads Sigma, Graphology, and ForceAtlas2 from bundled src/viewer/vendor/ assets, so the viewer stays offline and self-contained once codegraph is installed.
What the output looks like
Because ranking and counts change with the working tree, this abbreviated explore excerpt shows the stable response structure rather than snapshot-specific totals:
Anchors
- buildReviewReport [symbol] src/review.ts
- src/cli/help.ts:1 [chunk] src/cli/help.ts
- ReviewPreset [symbol] src/review.ts
Relevant source
- buildReviewReport is defined in src/review.ts.
- References, dependencies, and dependents are summarized here.
Blast radius
- src/review.ts: src/index.ts, src/cli/review.ts, src/mcp/server.ts, ...
Candidate tests
- tests/agent-explain.test.ts
- tests/agent-explore.test.ts
- tests/agent-packet.test.ts
Follow-ups
- codegraph file src/review.ts
- codegraph refs src/review.ts:215:23
Limits
- anchors, packets, paths, blast radius, reverse dependencies, and candidate tests
Recommended next: codegraph file src/review.ts
Real output includes counts, copyable follow-ups, and the limits that applied; --json adds the omission counts.
A worktree review is optimized for a different job:
Review Summary
==============
Status: ok
Files changed: 5
Symbols changed: 22
Candidate tests: 1 (high: 1, medium: 0, low: 0)
Risk: high (80)
Signals: exported-symbols-changed, many-symbols-changed
Structured output carries the underlying changed files, symbols, graph edges, reasons, diagnostics, snippets, and candidate-test confidence.
Why codegraph
Spend context on the problem, not repository discovery
explore runs one search and bundles bounded context around the top hits: source, dependency paths, dependents, candidate tests, and next commands. It is a reading starting point, only as good as the search terms. MCP omits source by default.
Ground the next action
Results include source paths, symbol ranges, stable handles, rank reasons, graph relationships, confidence, and omission counts. An agent can inspect why something ranked, jump to the definition or references, and continue from an exact target instead of treating a fuzzy match as an answer.
Trust the answer, or know why not
Definitions, references, and call edges come from scopes, imports, packages, and receivers proven from source, not from name matching alone. When codegraph cannot prove a target, it returns not_found or reports referenceCoverage as partial with a reason instead of guessing. An agent can act on a complete result and fall back to text search or a compiler for the rest; complete covers every candidate known to the index, not unknown dynamic loading. See the refs coverage contract and the language parity matrix for per-language support and tested limits.
Reuse one map from discovery through review
Search, navigation, dependency analysis, impact, and review reuse the same graph and semantic index. A target found during discovery can flow directly into explain, refs, deps, impact analysis, and candidate-test selection.
Work across the repository an agent actually has
One repository model can include source code, SQL, workspace packages, documentation links, stylesheets, templates, and single-file components. Capability claims stay language-specific, so graph support is not presented as full compiler or language-server parity.
Keep the evidence local and reusable
codegraph runs locally as a CLI, library, or MCP server. Humans get readable output; agents and programs can keep structured JSON, stable handles, warm sessions, SQLite data, or graph exports without parsing display text.
Why not just grep or an LSP?
codegraph complements both.
- Use text search for exact strings, logs, config keys, and prose.
- Use a compiler or language server when you need compiler-grade type analysis, overload resolution, dynamic dispatch, or editor refactors.
- Use codegraph when the question crosses files, languages, dependency edges, a git diff, or an agent context boundary.
The distinction is evidence shape, not a claim that one tool replaces the others.
Agent setup
Run codegraph install on an interactive terminal to detect supported clients, preview the changes, and confirm once. Use --all when you want the full current catalog without detection:
codegraph install
codegraph install --target codex,claude --dry-run
codegraph install --target codex,claude --yes
codegraph install --all --dry-run
codegraph install --all --yes
codegraph install --print-config codex
Supported target ids are codex, claude, cursor, gemini, opencode, omp, kilo, and agents. Interactive writes default to no; noninteractive writes require --yes.
For a skill without MCP configuration:
codegraph skill install --agent codex
codegraph skill install --agent claude
codegraph skill install --agent cursor
See Agent workflows for exploration strategy, warm sessions, streaming, review loops, and tool wrappers. Default stdio MCP clients share one compatible project owner's index, workers and watcher. Use codegraph server status --root . --json and codegraph server stop --root . to inspect or stop it; use an explicit workspace when launching from a directory of repositories. See MCP for server and client configuration.
Language support
Shared source-language indexing and navigation: JavaScript, TypeScript, Python, PHP, Go, Java, C#, Ruby, Rust, Kotlin, Swift, Zig, C, and C++.
SQL: statement chunking, object symbols, common DDL/DML and CTE facts, SQL-to-SQL edges, and object-level navigation. codegraph does not claim column-definition resolution.
Terraform: module-directory symbols, dependency edges to local module sources, and navigation for var, local, module, data source, and resource references, including module outputs and call arguments.
Graph-first formats: HTML, Astro, Handlebars, Markdown, MDX, reStructuredText, AsciiDoc, CSS, SCSS, and Less have narrower graph or chunking support.
Single-file components: Vue and Svelte script blocks participate in dependency graphs and chunking; semantic navigation is narrower.
See Language parity for the capability matrix and Scenario catalog for the fixtures behind those claims.
Using as a library
Install @lzehrung/codegraph-core when you need the library without the CLI, MCP server, installer, or viewer.
import { buildProjectIndex, getHotspots } from "@lzehrung/codegraph-core";
const index = await buildProjectIndex(process.cwd());
console.log(getHotspots(index.graph, { limit: 10 }));
See the Library API reference for navigation, review, agent sessions, and artifacts.
How it works
codegraph follows a single analysis pipeline:
- Discover supported files under the selected project and include roots.
- Parse source languages with Tree-sitter and extract imports, exports, definitions, bindings, and scopes.
- Resolve module specifiers to project files or explicit external nodes.
- Build forward and reverse dependency indexes plus a semantic symbol index.
- Reuse those indexes for navigation, exploration, impact, review, and exports.
Disk caching avoids repository-wide source reads on exact warm text-search hits. How it works covers caching, native failure reporting, and performance choices.
Limits and tradeoffs
The honest boundaries matter:
- codegraph is not a compiler or type checker. Reflection, generated code, macros, overload behavior, and dynamic dispatch can be missed. When a result would need expression type inference, overload ranking beyond arity, or build-system membership, codegraph reports
not_foundorpartialcoverage rather than a guessed target. - Precise navigation depends on successful native parsing and language queries. A missing native addon is an error; run
codegraph doctorto diagnose it. Files over the native size limit are skipped with asourceTooLargereport, and failed native queries are reported asqueryFailurewithout regex recovery. Document and stylesheet graph-only extraction remains supported. - Call-compatibility findings are conservative review leads, not compiler diagnostics.
- Duplicate matches and candidate tests are ranked leads that still require human or agent judgment.
- The checked
explorebenchmark is a bounded evidence-retrieval benchmark, not a universal performance claim. - The fixture test matrix and language parity docs show what codegraph has actually been tested against by language and operation; absence there means untested, not guaranteed.
Mitigations are explicit too:
- The repository keeps real-language fixtures and native parity suites for definitions, references, dependencies, chunking, and MCP.
- A generated fixture test matrix shows real
tests/languages/*.test.tsstatus and test counts per language, with no hand-authored goldens involved. - Structured output keeps freshness, confidence, and omission counts visible instead of pretending unsupported cases were resolved.
Run codegraph doctor to confirm the active runtime. Use --report on graph, index, search, inspect, or review commands when backend and cache behavior need to be auditable.
Development
npm install
npm run build
npm run check
Use the narrowest relevant test while iterating. npm run check is the pre-commit baseline for formatting, lint, build, and tests; native workspace changes also require npm run build:native and npm run test:native.
codegraph is MIT licensed.
codegraph MCP questions
How do I add codegraph MCP to Claude Code?
Run claude mcp add codegraph -- npx -y @lzehrung/codegraph in your terminal. Add --scope user to make it available in every project.
How do I add codegraph MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What is codegraph not?
It is not an AST, a compiler, or a linter.
Can I use codegraph without Node.js or npm?
Yes, standalone installers are available that download a self-contained bundle including Node.js, the CLI, and the matching native runtime.
Does codegraph change my code?
No, tools like refactor-plan and rename-preview provide read-only evidence and edits without making actual code changes.