graphlens-mcp 0.1.0

Semantic code graph MCP server for coding agents

graphlens-mcp

A free, MIT-licensed MCP server that gives coding agents (Claude Code, Cursor, and compatible clients) a semantic code graph of your project — symbols, cross-file calls, references, imports and cross-language boundaries.

Instead of reading files top-to-bottom or grepping for names, the agent navigates the structure: who calls this function, what does it depend on, what breaks if I change its signature. It is a thin runtime layer over the graphlens analysis engine: graphlens provides the mechanisms (parsing, stable node identity, resolvers); graphlens-mcp owns the storage, freshness and the agent-facing surface.

📖 Documentation: https://neko1313.github.io/graphlens-mcp/

Status: early. The core navigation works; see Known limitations.

Why

A filesystem/grep MCP makes the agent read whole files and match text — slow, noisy, and blind to which of three modules actually calls OrderService.create. Bare tree-sitter gives single-file syntax but cannot resolve links between files. graphlens-mcp answers the cross-file questions — call graphs and impact analysis — and keeps the graph fresh as you edit, then teaches the agent to use it via a bundled navigation skill.

Install

Requires Python ≥ 3.13 (a constraint inherited from graphlens).

uv tool install graphlens-mcp      # or: pipx install graphlens-mcp

Python language analysis works out of the box (the ty type engine ships as a dependency). Other languages parse immediately and unlock full cross-file semantics once their toolchain is present (Node for TypeScript, the Go toolchain, etc.); without it that language is reported as degraded rather than blocking init.

Quickstart (two commands)

uv tool install graphlens-mcp        # 1. install
cd your-project && graphlens-mcp init  # 2. index + configure your agent

init detects the project's languages, indexes the code into a local graph, writes the MCP server entry into your agent's config and installs the navigation skill. You do not run serve yourself — your agent launches it from the config. Restart the agent and ask it something like "what breaks if I change the signature of create_order?".

Commands

Command	What it does
graphlens-mcp init	Detect languages → toolchain doctor → full index → configure agents → install skill
graphlens-mcp serve	Start the MCP server over stdio. Launched by the agent, not by you
graphlens-mcp status	Show detected languages, toolchain status, and graph size/freshness
graphlens-mcp reindex	Force a full rebuild (e.g. after installing a new toolchain)
graphlens-mcp remove	Deregister from agents and (with --purge-db) delete the local graph

Useful init flags: --root <dir>, --agent claude_code --agent cursor (repeatable), --no-agent, --no-skills, --db <path>.

The graph lives at <project>/.graphlens/graph.db (SQLite). It is a regenerable cache — safe to delete; reindex rebuilds it. Add .graphlens/ to your VCS ignore (the bundled init flow assumes it is not committed).

Supported languages

Language	Engine	Out-of-box
Python	ty (bundled)	Full semantics immediately
TypeScript	Node bridge	degraded without Node; full semantics with Node installed
Go	Go toolchain	degraded without toolchain
Rust	SCIP / rust-analyzer	degraded without toolchain
PHP	PHP parser	degraded without toolchain

graphlens-mcp status reports the actual resolver status per language. When a toolchain is missing, that language is reported as degraded (parsed structure, calls/types not fully resolved) with an install hint — it never blocks init.

Agent tools

Each response carries a graph-quality status (ok | degraded) so the agent never mistakes a partial answer for a complete one.

Tool	Purpose
search_symbols	Full-text search over symbol names — start here
get_node_info	Source snippet + signature + location for a node
get_file_structure	Symbol outline of a file
get_callees	What a function calls (outgoing, up to max_depth)
get_callers	Who calls a function — primary impact-analysis tool
get_neighbors	Nodes within N hops in any direction
find_references	Non-call usages (type annotations, assignments)
get_cross_language_calls	Connections across service boundaries (HTTP/gRPC/queues)

Freshness model

A single mechanism keeps the graph current: a filesystem watcher (serve starts it by default; disable with --no-watch). When a file changes on disk the server re-indexes the connected set — the changed file plus the files that import it and the files it imports — with one full analyze, so cross-file edges are rebuilt correctly rather than left partial. Deleting a file prunes its symbols and refreshes its importers. There is no polling and no structure-only "skeleton" phase: every (re)index produces the full graph the resolver can give. As a backstop, a tool that touches a file the watcher hasn't processed yet triggers the same connected re-index on access.

Files created, deleted or edited while the server was down are invisible to an event-based watcher, so serve runs a one-shot reconcile at startup: it scans the project, indexes new files, prunes vanished ones, and refreshes any that changed — then hands off to the watcher.

Known limitations

• Whole-project re-link: the watcher re-links the connected set of a change, not the entire project. A rename that ripples through many indirection layers — or creating a file that an unchanged file already imports — may need a full reindex for an exact graph.
• Cross-language edges on incremental edits: synthesized COMMUNICATES_WITH edges are rebuilt on a full reindex; they can erode across incremental edits (the boundary-based query still resolves connections). Run reindex for an exact cross-language view.

Uninstall

graphlens-mcp remove deregisters the server from your agents; add --purge-db to also delete the local .graphlens/ cache.

Development

uv sync --all-groups   # install lint + test tooling
task check             # ruff + format-check + ty + bandit + pytest (the CI gate)
task docs:serve        # preview the docs site locally (needs Node + pnpm)

See ARCHITECTURE.md for the design and invariants, or the documentation site for the full guide.

License

MIT — see LICENSE.