Codanna MCP server
Commit Oct 11, 2026Indexes a local repository so AI coding agents can search code semantically and trace call graphs, dependencies, and impact.
Also known as bartolli/codanna
- Stars
- 760
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 11, 2026
- License
- Apache-2.0
What is Codanna MCP?
Codanna indexes a local repository so AI coding agents can search code semantically and trace call graphs, dependencies, and impact.
Summary generated from the project's README
About Codanna MCP server
Developers using AI coding agents can provide their assistants with deep structural knowledge of local repositories through codanna. This tool indexes codebases to enable semantic search, call graph tracing, and dependency analysis. It works by running as a persistent MCP server via stdio, HTTP, or HTTPS, or as a one-shot CLI for scripts and CI environments. It is compatible with clients like Claude Code, Cursor, Windsurf, Gemini, and Codex.
By indexing files locally, the server allows agents to perform complex tasks such as impact analysis and document RAG without sending source code to a remote API. The system supports 15 languages, including Rust, Python, TypeScript, and Go. While it runs locally by default, users can opt-in to remote OpenAI-compatible embeddings by configuring environment variables. The tool provides specific insights like symbol identities, signatures, and the blast radius of code changes, effectively collapsing the traditional grep-and-read loop into a single structured response.
What you can do with it
- 1Analyze code change impactAsk an agent to determine which symbols will be affected if a specific function is modified.
- 2Trace function relationshipsIdentify exactly which functions call a specific method and where those calls occur.
- 3Query project documentationSearch through markdown and text files to find information about authentication flows or other project details.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablebartolli/codanna is public and reachablegithub.com/bartolli/codanna ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-11github.com/bartolli/codanna ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- 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 GitHubLocal code intelligence MCP server and CLI for AI coding agents.
X-ray vision for your agent.
Codanna is a local code intelligence and semantic code search MCP server for AI coding agents. One MCP call returns symbol context, call graph, and impact analysis, pre-correlated — the grep-and-read loop your agent runs today, collapsed into a single response it can act on.
It indexes your repository on disk and serves symbol search, semantic search, call graphs, dependency tracking, document RAG, and impact analysis to Claude Code, Cursor, Windsurf, Codex, Gemini, and any MCP-compatible client — as a persistent MCP server for session-long work, or a one-shot CLI for instant answers when LSP is too slow. Written in Rust. 15 languages. No source code leaves your machine.
Two operational modes
Codanna's MCP toolset is reachable two ways. Same tools, same surface — pick the mode that fits the workflow.
Persistent MCP server — for session-long agent workflows.
codanna serve # stdio
codanna serve --http # HTTP
codanna serve --https # HTTPS
One-shot CLI — for slash-commands, bash hooks, scripts, CI. No daemon required.
codanna mcp find_symbol name:"my_function"
codanna mcp analyze_impact symbol_name:"my_function"
codanna mcp semantic_search_with_context query:"recursively extract function calls"
codanna mcp semantic_search_with_context is the headline command: it returns N semantic matches, and for each match the symbol identity, signature, docstring, callees, callers, and recursive impact analysis — five MCP tools fused into one query.
The one-shot CLI is also what makes codanna skill-friendly: an Agent Skill can wrap codanna mcp commands directly in Claude Code, Cursor, Windsurf, Codex, Gemini, or any harness that runs shell commands — no MCP plumbing required.
What one call returns
The headline command, run against codanna's own source tree. One call, and the agent has the symbol, its documentation, signature, callees with exact call sites, callers, and blast radius:
$ codanna mcp semantic_search_with_context query:"recursively extract function calls" limit:1
Found 1 results for query: 'recursively extract function calls'
1. extract_calls_recursive - Method at src/parsing/cpp/parser.rs:1002-1047 [symbol_id:1477]
Similarity Score: 0.833
Documentation:
Recursively extract function calls with context tracking
Signature: fn extract_calls_recursive<'a>(
node: Node,
code: &'a str,
current_function: Option<&'a str>,
calls: &mut Vec<(&'a str, &'a str, Range)>,
)
extract_calls_recursive calls 3 function(s):
-> Method extract_calls_recursive at src/parsing/cpp/parser.rs:1002 [symbol_id:1477] (called at src/parsing/cpp/parser.rs:1045)
-> Method function_name_at_def at src/parsing/cpp/parser.rs:377 [symbol_id:1451] (called at src/parsing/cpp/parser.rs:1008)
-> Method new at src/types/mod.rs:112 [symbol_id:7388] (called at src/parsing/cpp/parser.rs:1028)
2 function(s) call extract_calls_recursive:
<- Method extract_calls_recursive at src/parsing/cpp/parser.rs:1045 [symbol_id:1477]
<- Method find_calls at src/parsing/cpp/parser.rs:885 [symbol_id:1467]
Changing extract_calls_recursive would impact 1 symbol(s) (max depth: 2):
methods (1):
- find_calls [symbol_id:1467]
Guidance: Found one match with full context. Review the relationships to understand how this fits into the codebase.
Every result carries file:line coordinates the agent can open directly, symbol_ids it can reuse to disambiguate name collisions, and a guidance hint it can chain on. Add --json for the structured envelope.
Local-first
Codanna runs on your machine. The repository index lives on disk under .codanna/. The embedding model downloads once on first use, then runs locally. No source code, symbols, or queries are sent to a remote API by default. Remote OpenAI-compatible embeddings are opt-in: remote_url under [semantic_search] in settings.toml, or CODANNA_EMBED_* environment variables; the API key is environment-only.
Quick Start
Install (macOS, Linux, WSL)
curl -fsSL --proto '=https' --tlsv1.2 https://install.codanna.sh | sh
Or via Homebrew
brew install codanna
Or via Nix
nix run github:bartolli/codanna
Windows (PowerShell)
irm https://raw.githubusercontent.com/bartolli/codanna/main/scripts/install.ps1 | iex
See Installation Guide for Cargo and other options.
Initialize and index
codanna init
codanna index src
Search code
codanna mcp semantic_search_with_context query:"where do we handle errors" limit:3
Search documentation (RAG)
codanna documents add-collection docs ./docs
codanna documents index
codanna mcp search_documents query:"authentication flow"
What It Does
Your AI assistant gains structured knowledge of your code:
- "Where's this function called?" - Instant call graph, not grep results
- "Find authentication logic" - Semantic search matches intent, not just keywords
- "What breaks if I change this?" - Full dependency analysis across files
The difference: Codanna understands code structure. It knows parseConfig is a function that calls validateSchema, not just a string match.
Features
| Feature | Description |
|---|---|
| Semantic Search | Natural language queries against code and documentation. Finds functions by what they do, not just their names. |
| Relationship Tracking | Call graphs, implementations, and dependencies. Trace how code connects across files. |
| Document Search | Index markdown and text files for RAG workflows. Query project docs alongside code. |
| MCP Protocol | Native integration with Claude, Gemini, Codex, and other AI assistants. |
| Profiles | Package hooks, commands, and agents for different project types. |
Performance: parser throughput 76,000-249,000 symbols/second depending on language; warm-server lookups under 10 ms (0.3 ms exact, ~3 ms semantic). Parsing is the fast layer; embedding generation during indexing takes longer and scales with your cores. Measured numbers, machine spec, and reproduction commands: Benchmarks.
Languages: Rust, Python, JavaScript, TypeScript, Java, Kotlin, Go, PHP, C, C++, C#, Clojure, Lua, Swift, GDScript.
Claude Code plugin
Two skills over the index, driven by the agent: it picks the view that fits the question. x-ray covers scoped questions — a symbol's blast radius as a call DAG, module structure as a collapsible tree or radial poster, cross-module calls as an edge-bundle page. graph covers codebase shape: the module disc with hubs at the centre, a commit timeline, and a heatmap. Symbol search, detail panels with highlighted signatures, call-graph navigation. The disc renderer is adapted from vault-graph by Lukas Proprentner (MIT).
/plugin marketplace add bartolli/codanna
/plugin install codanna-toolset@codanna
Integration
Add codanna to any MCP-compatible client. Project-scoped .mcp.json (Claude Code, Cursor, Windsurf):
{
"mcpServers": {
"codanna": {
"command": "codanna",
"args": ["--config", ".codanna/settings.toml", "serve", "--watch"]
}
}
}
--watch keeps the index hot as files change. Transports: stdio, HTTP, HTTPS. See Integration Guides for Claude Desktop, Gemini, Codex, and network setups.
Requirements
- ~150MB for embedding model (downloaded on first use)
- macOS: Apple Silicon. ONNX Runtime 1.28 has no Intel macOS build, so 0.17.1 and later do not target Intel Macs; 0.17.0 is the last release that does
- Linux: glibc 2.38+ and libstdc++ from GCC 13+ for
cargo install(the prebuilt ONNX Runtime binaries); the release binaries are built on Ubuntu 24.04 (glibc 2.39) - Build from source: Rust 1.85+ and
pkg-config - Windows support is experimental
Contributing
Contributions welcome. See CONTRIBUTING.md.
License
Apache License 2.0 - See LICENSE.
Attribution required. See NOTICE.
Built with Rust.
Codanna MCP questions
Does Codanna send my source code to a remote API?
No. Codanna indexes the repository on disk under .codanna/ and runs the embedding model locally; remote embeddings are opt-in via settings.
Which programming languages does Codanna support?
Codanna parses 15 languages including Rust, Python, JavaScript, TypeScript, Java, Go, C, C++, C#, Swift, PHP, Kotlin, Clojure, Lua, and GDScript.
Can I use Codanna without running a persistent server?
Yes. The one-shot CLI runs the same MCP tools as single commands for scripts, hooks, or CI.
What does semantic_search_with_context return?
It returns semantic matches with symbol identity, signature, docstring, callees, callers, and recursive impact analysis in one response.
Which transports does the Codanna MCP server support?
It supports stdio, HTTP, and HTTPS.