omni-tools-mcp
An MCP server that exposes 83 utility tools (string, JSON, CSV, list, time, number, XML) to AI agents, auto-generated from the omni-tools source.
README
omni-tools-mcp
An MCP server that exposes omni-tools' tool logic to AI agents — 83 tools across string, JSON, CSV, list, time, number, and XML categories.
There is no hand-written tool code here. omni-tools keeps each tool's pure logic in a service.ts separate from its React UI, so this project auto-generates its entire tool registry from the omni-tools source using ts-morph:
- entry functions are discovered from each tool's own
index.tsximports of./service - parameter types are compiled to zod schemas (primitives, literal-union enums, arrays, options objects)
- tool names/descriptions come from
meta.tsi18n keys resolved againstpublic/locales/en/*.json - browser/wasm-bound tools (ffmpeg, canvas, pdf renderers) are skipped with reasons — see
src/generated/report.jsonafter a build
Point it at a newer omni-tools checkout and re-run npm run generate to pick up new upstream tools with zero code changes.
Usage
stdio (Claude Desktop, Claude Code, most MCP clients)
{
"mcpServers": {
"omni-tools": {
"command": "node",
"args": ["/path/to/omni-tools-mcp/dist/index.js"]
}
}
}
Streamable HTTP
PORT=3000 node dist/http.js
# MCP endpoint: http://localhost:3000/mcp health: /health
Building
git clone https://github.com/iib0011/omni-tools # sibling checkout (or set OMNI_TOOLS_ROOT)
git clone <this repo> omni-tools-mcp && cd omni-tools-mcp
npm install
npm run build # generate registry from omni-tools source + bundle
node scripts/smoke-test.mjs
The build bundles the extracted services into dist/ — the runtime needs no omni-tools checkout and no node_modules.
What's included / excluded
| Included (83) | Excluded (~26) |
|---|---|
| string (28), csv (11), list (11), time (11), json (9), number (6), xml (2), misc | audio/video (ffmpeg.wasm), image/pdf converters (canvas, pdf.js workers), File-based tools |
Excluded tools depend on browser/wasm APIs that don't exist in Node. They could be added later by shelling out to native ffmpeg/ghostscript — contributions welcome.
License
MIT — same as omni-tools, whose extracted service code is bundled into dist/. All tool logic copyright the omni-tools contributors.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.