MCP Directory

How to add ontomics to Claude Desktop

Give any coding agent instant semantic knowledge of your codebase — one tool call instead of 19, ~20x fewer tokens. Paste the config into ~/Library/Application Support/Claude/claude_desktop_config.json and restart Claude Desktop.

Last updated June 14, 2026 · 36★ · stdio · no auth

Claude Desktop config for ontomics

npm install -g @ontomics/ontomics
{
  "mcpServers": {
    "ontomics": {
      "command": "npx",
      "args": [
        "-y",
        "@ontomics/ontomics",
        "--repo",
        "."
      ]
    }
  }
}

Setup steps

  1. 1Open Claude Desktop → Settings → Developer → Edit Config (this opens ~/Library/Application Support/Claude/claude_desktop_config.json).
  2. 2Paste the ontomics config below under the top-level "mcpServers" key.
  3. 3Fill in any placeholder secrets (API keys, paths) in the snippet.
  4. 4Save the file, then fully quit and reopen Claude Desktop.
  5. 5Open a chat and confirm ontomics's tools appear under the 🔌 tools menu.

Before you start

  • A git repository (.git/ directory); non-git directories require --force
  • The ontomics binary, installed via npm (@ontomics/ontomics), Homebrew (EtienneChollet/tap/ontomics), the shell installer, or built from source with cargo
  • Supported source languages: Python, TypeScript, JavaScript, or Rust
  • macOS or Linux

What ontomics can do in Claude Desktop

query_concept

Find all variants, related concepts, and occurrences of a term.

locate_concept

Find the key signatures, classes, and files for a concept.

describe_symbol

Get the signature, docstring, and relationships for a function or class.

trace_concept

Trace how a concept flows through the codebase via call chains.

list_concepts

List the top domain concepts by frequency.

list_conventions

List all detected naming patterns (prefixes, suffixes, conversions).

list_entities

List code entities (classes, functions) filtered by concept, role, or kind.

check_naming

Check an identifier against project conventions; suggests the canonical form.

Security

Runs entirely locally — no API keys and no network calls for indexing (embedding models are downloaded once on first run and cached). Requires a git repository; ontomics refuses to index home, root, or temp directories unless --force is passed.

ontomics + Claude Desktop FAQ

Where is the Claude Desktop config file?

Claude Desktop reads MCP servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Paste the ontomics config there under the "mcpServers" key and restart the client.

Is ontomics safe to use with Claude Desktop?

Runs entirely locally — no API keys and no network calls for indexing (embedding models are downloaded once on first run and cached). Requires a git repository; ontomics refuses to index home, root, or temp directories unless --force is passed.

Does it require any API keys or send my code to a service?

No. The entire pipeline runs locally. The two embedding models (BGE-small and CodeRankEmbed) are downloaded once on first run and cached; indexing makes no API calls.

Which languages are supported?

Python, TypeScript, JavaScript, and Rust, auto-detected from file extensions.

Where is the index stored?

At <repo>/.ontomics/index.db. Subsequent startups load from cache and watch for file changes. Configuration lives in .ontomics/config.toml.

View repo Full ontomics page