005-mcp-integration

005-mcp-integration is an agent for coding agents from paulbreuler/limps. It costs 0 tokens per session (410 once invoked), scanned A, original, MIT.

A development task for adding MCP tools that expose commands from the limps skill system. MCP is a way for an AI agent to call external tools.

In plain words
What is it for?
Use it to implement skill-listing and skill-loading tools, validate skill names, and register those tools with an MCP server.
Why use it?
It lets the agent discover available skills and read their instructions through MCP, without needing to know how to run the underlying command-line program.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/paulbreuler/limps/005-mcp-integration
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 005-mcp-integration

README.md
[![agentmods](https://agentmods.dev/badge/agents/paulbreuler/limps/005-mcp-integration.svg)](https://agentmods.dev/agents/paulbreuler/limps/005-mcp-integration)
Your own site
<a href="https://agentmods.dev/agents/paulbreuler/limps/005-mcp-integration"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/005-mcp-integration.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00410
Opus 5 $0.00000 $0.00205
Sonnet 5 $0.00000 $0.00082
Haiku 4.5 $0.00000 $0.00041

Measured 3d ago against content hash e976fefa5020, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

005-mcp-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plans/0046-limps-skills/agents/005-mcp-integration.md · 60 lines

What it actually says

Agent 005: MCP Integration

Objective

Create MCP tools that wrap skill CLI commands (CLI-first pattern).

Tasks

  1. load_skill tool (src/tools/skill.ts)

    • Wraps limps skill read <name>
    • Returns full SKILL.md content for AI consumption
    • Used when AI needs guidance on limps usage
  2. list_skills tool

    • Wraps limps skill list --json
    • Returns skill metadata array
    • For AI to discover available skills
  3. Tool registration

    • Add to MCP server tool list
    • Include descriptions for AI discovery

Tool Definitions

export const loadSkillTool: MCPTool = {
  name: 'load_skill',
  description: 'Load a limps skill for guidance. Use when you need help with limps planning tools.',
  inputSchema: {
    type: 'object',
    properties: {
      skillName: { type: 'string', description: 'Skill name (e.g., limps-planning)' }
    },
    required: ['skillName']
  },
  handler: async ({ skillName }) => {
    if (!/^[a-zA-Z0-9_-]+$/.test(skillName)) throw new Error('Invalid skill name');
    const { stdout } = await execFile('limps', ['skill', 'read', skillName]);
    return { content: [{ type: 'text', text: stdout }] };
  }
};

Acceptance Criteria

  • load_skill MCP tool returns SKILL.md content
  • list_skills MCP tool returns metadata array
  • Tools call CLI (don't reimplement logic)
  • Error handling for missing skills
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 60 lines · 0 tokens per session scan A e976fefa5020

Subscribe to this mod's changes

005-mcp-integration is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 410 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories