mcpField
O
OpenClaw Agent Instruction Registry

OpenClaw Agent Instruction Registry

Local
openclaw-sandy-eight.vercel.appAI & Agents1Updated 32w ago
RepositoryVisit website

About OpenClaw Agent Instruction Registry

OpenClaw Agent Instruction Registry is an MCP server that gives compatible AI agents access to AgentBase, an open registry of instruction files. It supports searching by keyword, domain, or type and retrieving files by ID.

Key features

  1. 01Search instructions by keyword, domain, or type
  2. 02Retrieve a file by ID
  3. 03List registry categories and domains
  4. 04Browse featured instruction files

Use cases

  1. 01Load domain-specific instructions at runtime
  2. 02Retrieve skills for Claude Code workflows
  3. 03Share prompts and workflows across a team
  4. 04Fetch safety filters for AI deployments

MCP support

The MCP server wraps AgentBase HTTP endpoints and exposes search, retrieval, category listing, and featured-file lookup as structured tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "izworskic-openclaw-registry": {
      "command": "npx",
      "args": [
        "-y",
        "agentbase-mcp"
      ]
    }
  }
}
Run commandnpx -y agentbase-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagentbase-mcp1.0.1

Tools

4

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
qstringNoKeyword search across title, tags, and slug. Optional.
categoryenumNoFilter by category. One of: system-prompts, skills, workflows, tool-definitions, domain-packs, safety-filters, orchestrationsystem-prompts | skills | workflows | tool-definitions | domain-packs | safety-filters | orchestration
min_qualitynumberNoMinimum quality score (0-100). Recommended: 80 for production use.
featured_onlybooleanNoIf true, return only featured (quality >= 90) files.

Details

From the project README

AgentBase MCP Server

Listed on awesome-mcp-servers Glama Score

MCP server for the AgentBase agent instruction registry. Gives any MCP-compatible AI agent direct access to search and retrieve instruction files.

Listed in punkpeye/awesome-mcp-servers — 83k+ stars.

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

ToolDescription
search_registrySearch instruction files by keyword, domain, or type
get_fileRetrieve a specific instruction file by ID
list_categoriesList all available categories and domains
get_featuredGet 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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.