Ontomics

v0.3.1Coding Agentsstable

🦀 🏠 🍎 🐧 - Semantic code index that extracts domain concepts, naming conventions, and

agentic-codingai-codingclaude-codecodexcoding-agents
Share:
33
Stars
0
Downloads
0
Weekly
0/5

What is Ontomics?

Ontomics is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🦀 🏠 🍎 🐧 - semantic code index that extracts domain concepts, naming conventions, and

🦀 🏠 🍎 🐧 - Semantic code index that extracts domain concepts, naming conventions, and

This server falls under the Coding Agents and Developer Tools categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP protocol support

Use Cases

Extract domain concepts and naming conventions from code through semantic analysis.
Help AI coding agents understand codebase structure and domain knowledge at a glance.
Index code repositories for intelligent codebase navigation and context injection.
EtienneChollet

Maintainer

LicenseMIT License
Languagerust
Versionv0.3.1
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y @ontomics/ontomics

Manual Installation

npx -y @ontomics/ontomics

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Ontomics

Ontomics is a semantic code indexer written in Rust that analyses your repository and builds a rich domain knowledge graph — extracting concepts, naming conventions, vocabulary health, logic similarity clusters, and type flows — and exposes all of this through an MCP server so AI coding agents can understand your codebase's domain language at a glance. It supports Python, TypeScript, JavaScript, and Rust out of the box, stores its index in a local .ontomics/index.db SQLite file, and is distributed as a prebuilt binary available via npm, Homebrew, or a shell installer. Teams can check a .mcp.json into their repo so every developer's coding agent automatically gets shared ontomics context.

Prerequisites

  • A git repository (ontomics requires a .git/ directory and will refuse to index home or root directories)
  • Node.js 18+ (to use the npm/npx distribution) OR Homebrew on macOS OR the shell installer for direct binary installation
  • An MCP client such as Claude Code, Cursor, or any agent supporting the Model Context Protocol
  • One of the supported languages in your codebase: Python, TypeScript, JavaScript, or Rust
1

Install the ontomics binary

Choose the installation method that suits your environment. npm/npx is the easiest cross-platform option; Homebrew is recommended on macOS for a persistent global install.

# Via npm (global install)
npm install -g @ontomics/ontomics

# Via Homebrew (macOS)
brew install EtienneChollet/tap/ontomics

# Via shell installer (macOS/Linux)
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/EtienneChollet/ontomics/releases/latest/download/ontomics-installer.sh | sh
2

Register ontomics with your MCP client

Add ontomics as an MCP server in your client. For Claude Code, use the mcp add command. For other clients, add the JSON configuration block manually.

# Claude Code
claude mcp add -s user ontomics -- ontomics

# Codex
codex mcp add ontomics -- ontomics
3

Navigate to your repository and run the initial index

From your project root (which must contain a .git directory), trigger ontomics to build the index. The index is stored in .ontomics/index.db.

cd /path/to/your/project
ontomics
4

Share the configuration with your team (optional)

Add a .mcp.json file to the repository root so all team members' MCP clients automatically pick up ontomics with the correct settings pointing to the repo.

{
  "mcpServers": {
    "ontomics": {
      "command": "npx",
      "args": ["-y", "@ontomics/ontomics", "--repo", "."]
    }
  }
}
5

Access the briefing resource in your AI client

The ontomics://briefing MCP resource provides a ready-made conventions summary and vocabulary warnings that you can inject into your AI agent's context before starting a coding session.

Ontomics Examples

Client configuration (Claude Desktop / stdio)

Add this to claude_desktop_config.json to run ontomics as a local MCP server using npx.

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

Prompts to try

Once connected, ask your AI assistant to use ontomics to understand your codebase.

- "Read the ontomics://briefing resource and summarise the naming conventions in this repo."
- "What are the core domain concepts extracted from this codebase?"
- "Find functions with logic similar to the parseUserInput function."
- "Show me the vocabulary health report — are there any inconsistently named symbols?"
- "Give me an overview of the src/services directory based on the ontomics index."

Troubleshooting Ontomics

ontomics refuses to index with an error about the directory

ontomics requires a .git directory and will refuse to run in home (~), root (/), or temp directories. Run it from within an actual git repository. If you have a legitimate need to index a non-standard location, pass the --force flag.

No symbols or concepts appear after indexing

Confirm your codebase contains files in a supported language (Python .py, TypeScript .ts, JavaScript .js, or Rust .rs). ontomics auto-detects languages from file extensions; other languages are not yet indexed.

The npx command is not found or fails to run

Ensure Node.js 18+ is installed and npx is in your PATH. Alternatively, install the binary directly via Homebrew or the shell installer and use the 'ontomics' command directly instead of npx.

Frequently Asked Questions about Ontomics

What is Ontomics?

Ontomics is a Model Context Protocol (MCP) server that 🦀 🏠 🍎 🐧 - semantic code index that extracts domain concepts, naming conventions, and It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Ontomics?

Install via npm with the command: npx -y @ontomics/ontomics. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Ontomics?

Ontomics works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Ontomics free to use?

Yes, Ontomics is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Ontomics?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides