The AgentBase MCP Server gives AI agents programmatic access to search and retrieve agent instruction files from the AgentBase open registry. Here's what you can do:
Search the registry (
search_registry): Find instruction files — system prompts, skills, workflows, domain packs, safety filters, and orchestration patterns — by keyword, category, minimum quality score, or featured status.Retrieve a specific instruction file (
get_instruction): Fetch a file by its slug, including YAML frontmatter, purpose, usage notes, and deployable instruction text, with an option to return only the raw deployable instruction.List all categories (
list_categories): Browse all available categories with descriptions and file counts.Get featured files (
get_featured): Retrieve curated, top-rated (quality score 90+), verified, and production-tested instruction files.
This enables AI agents to dynamically load domain-specific instructions at runtime, share and reuse prompts across teams, and implement tested safety filters and workflows — all from a centralized registry.
AgentBase MCP Server
MCP server for the AgentBase agent instruction registry. Gives any MCP-compatible AI agent direct access to search and retrieve instruction files.
Listed in
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 MCP tools.
Tools
Tool | Description |
| Search instruction files by keyword, domain, or type |
| Retrieve a specific instruction file by ID |
| List all available categories and domains |
| Get featured/top-rated instruction files |
Install
{
"mcpServers": {
"agentbase": {
"command": "npx",
"args": ["-y", "@agentbase1/mcp-server"]
}
}
}Use Cases
AI agents that need to load domain-specific instructions at runtime
Claude Code workflows that pull skills from a shared registry
Teams sharing system prompts and workflows across agents
Safety filter retrieval for production AI deployments
Registry
Browse the full registry at agentbase-registry.vercel.app.
CC0 licensed. All instruction files are free to use without restriction.
Built By
Chris Izworski — Solutions Consultant at Prepared, former Michigan 911 Executive Director, and AI implementer. Bay City, Michigan.
Website: chrisizworski.com
GitHub: github.com/izworskic
Wikidata: Q138283432
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.