Skip to content
Back to search

codanna

Local code intelligence MCP server and CLI for AI coding agents

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/bartolli/codanna with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/bartolli/codanna'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/bartolli--codanna/badge.svg)](/listings/bartolli--codanna)

HTML

<a href="/listings/bartolli--codanna"><img src="/api/listings/bartolli--codanna/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

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](https://docs.codanna.sh/installation) 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 was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 21 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  3. "name": "codanna",
  4. "owner": {
  5. "name": "Angel Bartolli"
  6. },
  7. "plugins": [
  8. {
  9. "name": "codanna-toolset",
  10. "source": "./agents/plugins/claude/codanna-toolset",
  11. "description": "Codanna toolset for Claude Code: x-ray (semantic search + relationship traversal with 3D neighbourhood, radial tree and edge-bundle views) and graph (the whole index as a module disc with hubs at the centre, timeline and heatmap). Needs the codanna CLI.",
  12. "version": "0.18.0",
  13. "author": {
  14. "name": "Angel Bartolli"
  15. },
  16. "category": "development",
  17. "strict": false
  18. }
  19. ],
  20. "description": "Claude Code plugins for codanna, the code-intelligence CLI and MCP server: x-ray and graph views over a codanna index."
  21. }
README.md · README · 226 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <h1 align="center">Codanna</h1>
  3. [![Claude](https://img.shields.io/badge/Claude-✓%20Compatible-grey?logo=claude&logoColor=fff&labelColor=D97757)](#)
  4. [![Google Gemini](https://img.shields.io/badge/Gemini-✓%20Compatible-grey?logo=googlegemini&logoColor=fff&labelColor=8E75B2)](#)
  5. [![OpenAI Codex](https://img.shields.io/badge/Codex-✓%20Compatible-grey?logo=openai&logoColor=fff&labelColor=10A37F)](#)
  6. [![Rust](https://img.shields.io/badge/Rust-CE412B?logo=rust&logoColor=white)](#)
  7. [![Crates.io Total Downloads](https://img.shields.io/crates/d/codanna?logo=rust&labelColor=CE412B&color=grey)](#)
  8. <p align="center">
  9. <a href="https://docs.codanna.sh/" target="_blank">Documentation</a>
  10. ·
  11. <a href="https://github.com/bartolli/codanna/issues">Report Bug</a>
  12. ·
  13. <a href="https://github.com/bartolli/codanna/discussions">Discussions</a>
  14. </p>
  15. <h2></h2>
  16. **Local code intelligence MCP server and CLI for AI coding agents.**
  17. *X-ray vision for your agent.*
  18. </div>
  19. <p align="center">
  20. <img src="https://raw.githubusercontent.com/bartolli/codanna/main/assets/readme/disc-tour.webp" alt="The codanna index as an interactive disc: module wedges, call webs, symbol search, commit timeline" width="100%">
  21. </p>
  22. 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.
  23. 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.
  24. ## Two operational modes
  25. Codanna's MCP toolset is reachable two ways. Same tools, same surface — pick the mode that fits the workflow.
  26. **Persistent MCP server** — for session-long agent workflows.
  27. ```bash
  28. codanna serve # stdio
  29. codanna serve --http # HTTP
  30. codanna serve --https # HTTPS
  31. ```
  32. **One-shot CLI** — for slash-commands, bash hooks, scripts, CI. No daemon required.
  33. ```bash
  34. codanna mcp find_symbol name:"my_function"
  35. codanna mcp analyze_impact symbol_name:"my_function"
  36. codanna mcp semantic_search_with_context query:"recursively extract function calls"
  37. ```
  38. `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.
  39. 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.
  40. ## What one call returns
  41. 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:
  42. ```text
  43. $ codanna mcp semantic_search_with_context query:"recursively extract function calls" limit:1
  44. Found 1 results for query: 'recursively extract function calls'
  45. 1. extract_calls_recursive - Method at src/parsing/cpp/parser.rs:1002-1047 [symbol_id:1477]
  46. Similarity Score: 0.833
  47. Documentation:
  48. Recursively extract function calls with context tracking
  49. Signature: fn extract_calls_recursive<'a>(
  50. node: Node,
  51. code: &'a str,
  52. current_function: Option<&'a str>,
  53. calls: &mut Vec<(&'a str, &'a str, Range)>,
  54. )
  55. extract_calls_recursive calls 3 function(s):
  56. -> Method extract_calls_recursive at src/parsing/cpp/parser.rs:1002 [symbol_id:1477] (called at src/parsing/cpp/parser.rs:1045)
  57. -> Method function_name_at_def at src/parsing/cpp/parser.rs:377 [symbol_id:1451] (called at src/parsing/cpp/parser.rs:1008)
  58. -> Method new at src/types/mod.rs:112 [symbol_id:7388] (called at src/parsing/cpp/parser.rs:1028)
  59. 2 function(s) call extract_calls_recursive:
  60. <- Method extract_calls_recursive at src/parsing/cpp/parser.rs:1045 [symbol_id:1477]
  61. <- Method find_calls at src/parsing/cpp/parser.rs:885 [symbol_id:1467]
  62. Changing extract_calls_recursive would impact 1 symbol(s) (max depth: 2):
  63. methods (1):
  64. - find_calls [symbol_id:1467]
  65. Guidance: Found one match with full context. Review the relationships to understand how this fits into the codebase.
  66. ```
  67. Every result carries `file:line` coordinates the agent can open directly, `symbol_id`s it can reuse to disambiguate name collisions, and a guidance hint it can chain on. Add `--json` for the structured envelope.
  68. ## Local-first
  69. 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.
  70. <h3 align="left"></h3>
  71. ## Quick Start
  72. ### Install (macOS, Linux, WSL)
  73. ```bash
  74. curl -fsSL --proto '=https' --tlsv1.2 https://install.codanna.sh | sh
  75. ```
  76. ### Or via Homebrew
  77. ```bash
  78. brew install codanna
  79. ```
  80. ### Or via Nix
  81. ```bash
  82. nix run github:bartolli/codanna
  83. ```
  84. ### Windows (PowerShell)
  85. ```powershell
  86. irm https://raw.githubusercontent.com/bartolli/codanna/main/scripts/install.ps1 | iex
  87. ```
  88. See [Installation Guide](https://docs.codanna.sh/installation) for Cargo and other options.
  89. ### Initialize and index
  90. ```bash
  91. codanna init
  92. codanna index src
  93. ```
  94. ### Search code
  95. ```bash
  96. codanna mcp semantic_search_with_context query:"where do we handle errors" limit:3
  97. ```
  98. ### Search documentation (RAG)
  99. ```bash
  100. codanna documents add-collection docs ./docs
  101. codanna documents index
  102. codanna mcp search_documents query:"authentication flow"
  103. ```
  104. ## What It Does
  105. Your AI assistant gains structured knowledge of your code:
  106. - **"Where's this function called?"** - Instant call graph, not grep results
  107. - **"Find authentication logic"** - Semantic search matches intent, not just keywords
  108. - **"What breaks if I change this?"** - Full dependency analysis across files
  109. The difference: Codanna understands code structure. It knows `parseConfig` is a function that calls `validateSchema`, not just a string match.
  110. ## Features
  111. | Feature | Description |
  112. |---------|-------------|
  113. | **[Semantic Search](https://docs.codanna.sh/features/semantic-search)** | Natural language queries against code and documentation. Finds functions by what they do, not just their names. |
  114. | **[Relationship Tracking](https://docs.codanna.sh/features/relationships)** | Call graphs, implementations, and dependencies. Trace how code connects across files. |
  115. | **[Document Search](https://docs.codanna.sh/features/document-search)** | Index markdown and text files for RAG workflows. Query project docs alongside code. |
  116. | **[MCP Protocol](https://docs.codanna.sh/reference/mcp-quick)** | Native integration with Claude, Gemini, Codex, and other AI assistants. |
  117. | **[Profiles](https://docs.codanna.sh/features/collaboration)** | Package hooks, commands, and agents for different project types. |
  118. **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](https://docs.codanna.sh/reference/benchmarks).
  119. **Languages:** Rust, Python, JavaScript, TypeScript, Java, Kotlin, Go, PHP, C, C++, C#, Clojure, Lua, Swift, GDScript.
  120. ## Claude Code plugin
  121. 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](https://github.com/luke321/vault-graph) by Lukas Proprentner (MIT).
  122. ```
  123. /plugin marketplace add bartolli/codanna
  124. /plugin install codanna-toolset@codanna
  125. ```
  126. <p align="center">
  127. <img src="https://raw.githubusercontent.com/bartolli/codanna/main/assets/readme/xray-tree.webp" alt="The x-ray collapsible tree: module structure with symbol detail panels and call-graph navigation" width="100%">
  128. </p>
  129. ## Integration
  130. Add codanna to any MCP-compatible client. Project-scoped `.mcp.json` (Claude Code, Cursor, Windsurf):
  131. ```json
  132. {
  133. "mcpServers": {
  134. "codanna": {
  135. "command": "codanna",
  136. "args": ["--config", ".codanna/settings.toml", "serve", "--watch"]
  137. }
  138. }
  139. }
  140. ```
  141. `--watch` keeps the index hot as files change. Transports: stdio, HTTP, HTTPS. See [Integration Guides](https://docs.codanna.sh/reference/mcp-quick) for Claude Desktop, Gemini, Codex, and network setups.
  142. ## Requirements
  143. - ~150MB for embedding model (downloaded on first use)
  144. - **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
  145. - **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)
  146. - **Build from source:** Rust 1.85+ and `pkg-config`
  147. - Windows support is experimental
  148. ## Contributing
  149. Contributions welcome. See [CONTRIBUTING.md](CONTRIBUTING.md).
  150. ## License
  151. Apache License 2.0 - See [LICENSE](LICENSE).
  152. Attribution required. See [NOTICE](NOTICE).
  153. ---
  154. Built with Rust.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.