ontomics

Give any coding agent instant semantic knowledge of your codebase — one tool call instead of 19, ~20x fewer tokens.

Unverified

stdio (local)

No auth

Rust

View repo 36 npm

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run

npm install -g @ontomics/ontomics

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

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

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

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

About ontomics

An MCP server that extracts domain knowledge from a codebase — concepts, naming conventions, vocabulary, and behavioral similarity between functions — and makes it queryable by coding agents in a single tool call, cutting token consumption and agentic search time dramatically. The index is built and stored locally per repo using tree-sitter parsing, TF-IDF concept scoring, local embedding models, and PageRank centrality.

Tools & capabilities (19)

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.

suggest_name

Generate an identifier name that fits the project's vocabulary.

vocabulary_health

Measure convention coverage, naming consistency, and cluster cohesion.

ontology_diff

Show new, changed, or removed domain concepts since a git ref.

export_domain_pack

Export domain knowledge as portable YAML for use in other repos.

find_similar_logic

Find functions with behaviorally similar implementations, ranked by embedding similarity.

describe_logic

Get the behavioral description, body text, and logic cluster membership for a function.

compact_context

Assemble tiered context (concepts + logic) for a symbol, optimized for LLM consumption.

describe_file

Overview of a file's entities, concepts, and relationships.

concept_map

Show which modules contain which domain concepts.

type_flows

Show dominant types and how data flows through the codebase.

trace_type

Trace how a specific type propagates across files and call sites.

When to use it

Answer 'what are the main domain concepts in this codebase?' in a single tool call instead of dozens of greps and reads
Find functions that behave similarly to a given function, surfacing implementation duplication that naming or call graphs miss
Enforce naming conventions by checking identifiers against the project's detected vocabulary and suggesting canonical names
Track how a codebase's domain vocabulary changes between git refs
Export a portable domain pack (YAML) to bootstrap conventions in other repositories

Security notes

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 FAQ

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.

Can I index a directory that isn't a git repo?

It requires a .git/ directory and refuses to index home, root, or temp directories. Pass --force to index a non-git directory.

How do I share it with my team?

Drop an .mcp.json in the repo root with the ontomics server entry (command npx, args -y @ontomics/ontomics --repo .) so teammates pick it up automatically.

#code-intelligence #semantic-search #codebase #tree-sitter #embeddings #domain-knowledge #rust #coding-agent

Alternatives to ontomics

Compare all alternatives →

Playwright MCP Server

Developer Tools

24k

Microsoft's official browser-automation MCP using Playwright's accessibility tree (no vision model).

Featured

Verified

stdio (local)

No auth

TypeScript

12 tools

Updated 21 days agoRepo

Context7 MCP Server

Developer Tools

28k

Up-to-date, version-specific library documentation injected into your coding agent.

Verified

stdio (local)

API key

TypeScript

2 tools

Updated 25 days agoRepo

codebase-memory-mcp

Developer Tools

16k

Code intelligence engine that indexes repos into a persistent knowledge graph for AI coding agents.

Unverified

stdio (local)

No auth

14 tools

Updated 11 hours agoRepo

Compare ontomics with:

vs Playwright MCP Server vs Context7 MCP Server vs codebase-memory-mcp vs Serena