High-performance knowledge graph MCP server for AI coding agents with semantic search.
LAIN MCP Server (io.github.spuentesp/lain)
The io.github.spuentesp/lain MCP server provides a high-performance knowledge graph interface for AI coding agents. It builds a map of project code connections—call and dependency relationships and files that tend to change together—so agents can ask questions using semantic search over that graph.
🛠️ Key Features
Knowledge graph of code relationships (what calls what, what depends on what)
Semantic search over the constructed map
Background integration for MCP-compatible AI coding assistants
Topics include petgraph, rust, and treesitter
🚀 Use Cases
Ask impact questions, e.g., “if I change this function, what else breaks?”
Use project-wide context rather than single-file guessing
Support agentic workflows with structural reasoning and code intelligence
⚡ Developer Benefits
Real answers derived from the code connectivity map
Works with any AI agent that supports MCP
⚠️ Limitations
Tooling specifics are not included in the provided data (e.g., no detailed tool list or toolCount).
A code graph for coding agents. Lain maps callers, dependencies, symbols,
and Git co-changes, then exposes them through the Model Context Protocol (MCP).
Before an agent edits a function, it can inspect what depends on it and how the
rest of the code reaches it.
Lain Command Center demo
The demo traces a symbol across the bytes and tokio repositories. Agents
query the same graph through MCP; the browser shows what Lain indexed and where
an answer came from.
Ask your agent:
text
If I change validate_token, what breaks?
Show me the call chain from entry to helper_a.
Which files usually change with auth.rs?
Is another agent already editing this code?
Lain answers with symbol names and source paths from a local index. The index
stays on disk between runs, updates when the code changes, and can cover more
than one repository. Semantic search is optional; graph queries work without
an embedding model.
Install
Using the release installer:
bash
curl -fsSL https://raw.githubusercontent.com/spuentesp/lain/main/install.sh | bash
source ~/.zshrc # or ~/.bashrc
lain --version
Rust 1.89 or newer is only needed when building from source. The
quickstart covers non-interactive installation and the
optional local embedding model.
Connect an agent
Run one setup command from the repository you want Lain to index:
bash
lain setup --agent claude-code
lain setup --agent codex
lain setup --agent cursor
lain setup --agent vscode
lain setup --agent continue
Use lain setup --agent generic for another MCP host. It writes this
project-level .mcp.json, with the absolute path of the lain binary that
ran setup as command:
Restart the agent after setup. Lain walks up from the agent's working directory
to find .git, builds .lain/graph.bin, and serves the repository over stdio.
No repos.yaml is needed for one repository.
Languages
Parsers for Rust, Python, TypeScript, JavaScript, Go, Java, C, C++, C#, Ruby,
Swift, Kotlin, Scala and PHP are built into the binary, as are the <script>
blocks of Vue and Svelte components. Every one gets definitions and a call
graph with nothing else installed.
Language servers are optional and only add precision. lain setup lists the
languages it found and asks which servers to install; pressing Enter installs
none. Non-interactive runs install none unless you name them:
bash
lain setup --lsp python,go # just these
lain setup --lsp detected # every missing one for this repository
lain setup --lsp none
First query
Ask the connected agent:
text
Use Lain to show the blast radius of validate_token.
Or call the same tool from a terminal:
bash
lain oneshot get_blast_radius validate_token
Use a symbol from your repository in place of validate_token. If the graph
isn't ready or an answer looks stale, run lain doctor.
Multiple repositories
bash
lain repos add bytes https://github.com/tokio-rs/bytes.git
lain repos add tokio https://github.com/tokio-rs/tokio.git
lain workspaces create tokio-stack --members bytes,tokio
lain server --config ./repos.yaml --transport http --port 9999
Open http://localhost:9999 for the Command Center. The server listens on
localhost only; set LAIN_BIND_ADDR=0.0.0.0 (with LAIN_API_KEYS=key1,…)
to expose it on the network. Federation adds
organization-wide search and cross-repository blast-radius queries. The
federation guide covers configuration, source types, and
failure states. After a federation schema upgrade, run lain reindex to
rebuild the on-disk graph from the sources.
Check the graph
From a source checkout:
bash
scripts/demo.sh --quick
The script creates a small repository with a known call graph, starts a real
Lain server, and compares the answers with that graph. It exits non-zero when a
check fails. A full run also records timings against this repository.
What Lain provides
Need
Tool or feature
See callers before changing a symbol
get_blast_radius, assess_change
Trace how two functions connect
get_call_chain
Find architectural entry points
find_anchors, list_entry_points
Search by name or meaning
find_symbol, search_code
Follow a symbol across repositories
get_cross_repo_blast_radius, search_org
Keep agents from editing the same code blindly
intents, presence, and advisory file claims
Static analysis can't prove every dynamic call through a message bus, dependency
injection container, or reflective router. explain_dispatch combines static
callers with convention matches, runtime traces, and Git co-change evidence; an
empty result becomes insufficient_evidence, not a claim that the edit is safe.
