AgentBase MCP Server
Open registry of agent instruction files — system prompts, skills, workflows, and domain packs. Exposes the OpenClaw registry via 4 MCP tools: search by keyword/category, fetch full instruction files, list categories, and get top-rated files. CC0 licensed, free to use.
README
agentbase-mcp
MCP server for the AgentBase agent instruction registry. Gives any MCP-compatible AI agent direct access to search and retrieve instruction files.
What It Does
AgentBase is an open registry of agent instruction files — system prompts, skills, workflows, domain packs, safety filters, and orchestration patterns. This MCP server wraps the registry's HTTP endpoints and exposes them as structured tools.
Tools:
search_registry— search by keyword, category, quality scoreget_instruction— fetch a full instruction file (or just the deployable text)list_categories— see all categories with file countsget_featured— get all quality 90+ featured files
Install
npm install -g agentbase-mcp
Or use npx (no install):
npx agentbase-mcp
Configure
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"agentbase": {
"command": "npx",
"args": ["agentbase-mcp"]
}
}
}
Claude Code
claude mcp add agentbase npx agentbase-mcp
Continue (VS Code)
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "stdio",
"command": "npx",
"args": ["agentbase-mcp"]
}
}
]
}
}
Any MCP Host
{
"command": "npx",
"args": ["agentbase-mcp"]
}
Usage Examples
Once connected, you can ask your AI agent:
- "Search AgentBase for safety filter instructions"
- "Find a customer support system prompt"
- "What categories of instruction files are available?"
- "Get the structured web research skill and show me just the instruction text"
- "Find featured orchestration patterns"
Direct API (no MCP)
The registry also has HTTP endpoints:
GET https://agentbase-registry.vercel.app/registry/index.json
GET https://agentbase-registry.vercel.app/registry/[slug].md
GET https://agentbase-registry.vercel.app/api/search?q=research&min_quality=85
GET https://agentbase-registry.vercel.app/llms.txt
Registry
- Website: https://agentbase-registry.vercel.app
- GitHub: https://github.com/AgentBase1/registry
- Submit a file: https://agentbase-registry.vercel.app/submit/
License
MIT — do whatever you want with the server code. Individual instruction files in the registry have their own licenses (most are CC0).
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.