Gaia MCP
Gaia MCP enables AI agents to discover, evaluate, and install trusted skills from the Gaia Skill Tree, providing evidence-backed recommendations and safe workspace integration.
README
Gaia MCP
Agent-native discovery, trust, installation, and progression for the Gaia Skill Tree.
Status: the
v0.1.0Trusted Discovery implementation is under review. The npm package is not published yet; use the local development instructions below until the first release passes its publication gate.
Gaia MCP lets an AI agent answer a practical question inside the user's current conversation:
Which evidence-backed skill fits this task, why should I trust it, and can you add it to this workspace safely?
It is a standalone Gaia Research instrument. It consumes canonical public data and validated local actions from Gaia Skill Tree; it does not own or mutate the Registry directly.
Repository roles
| Repository | Responsibility |
|---|---|
gaia-skill-tree |
Canonical Registry, schemas, public data, Trust Magnitude, and validated CLI actions. |
gaia-research |
Human-facing portal, research, reports, and the future Gaia MCP product page. |
gaia-mcp |
Agent-facing discovery, comparison, recommendation, installation coordination, and progression guidance. |
skill-fuse |
Creative authoring: combines installed skills into a new SKILL.md. |
gaia-operator |
Guarded browser and platform interaction runtime. |
v0.1 tool surface
gaia_search— find generic and Named Skills by task and constraints.gaia_inspect— return an evidence-backed skill dossier.gaia_status— report server compatibility, Registry freshness, counts, and source URLs.
The first three tools are implemented in read-only Registry mode for v0.1.0.
gaia_analyze_project and gaia_plan_path arrive with Bonded mode in v0.2.0.
Installation, updates, and Intake submission arrive only after the read-only surface is trustworthy. Every action will route through the canonical Gaia CLI and require explicit approval where it changes the workspace or external state.
Run the development server
Requires Node.js 22.14 or newer.
npm ci
npm run build
node dist/bin/gaia-mcp.js
The server speaks MCP over stdio, so it normally appears idle when run directly.
Connect it from an MCP client using the absolute path to
dist/bin/gaia-mcp.js.
After v0.1.0 is published and its clean-install gate passes, the canonical
Claude Code installation will be version-pinned:
claude mcp add gaia -- npx -y @gaia-research/mcp@0.1.0
Do not use that npm command until the package appears in the Gaia MCP releases.
The public projection endpoints can be overridden for testing with
GAIA_REGISTRY_URL and GAIA_NAMED_SKILLS_URL.
Verify
npm run check # typecheck, unit/protocol tests, build
npm run test:live # current gaiaskilltree.com data contract
npm pack --dry-run # publishable artifact contents
Design documents
Cross-repository tracking
gaia-mcpv0.1 implementation and release- Founder npm bootstrap and trusted-publisher handoff
- Gaia Skill Tree extraction and Roadmap v5 RFC
- Gaia Research website integration and consumer test
Non-goals
Gaia MCP is not:
- a conversational wrapper around every
gaiacommand; - a second Registry implementation;
- the engine that creatively fuses
SKILL.mdfiles; - a direct Registry or Skill Tree mutation path;
- a background update daemon;
- part of the Gaia Research website runtime.
License
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.