house-agents: Agent for Claude Code

.claude/agents/house-mcp.md

house-mcp is an agent for Claude Code from houseworthe/house-agents. It costs 45 tokens per session (964 once invoked), scanned A, original, MIT.

A specialist for setting up MCP servers, a standard way for AI agents to connect to external tools and services. It reads detailed documentation and returns a small working configuration with an example.

In plain words
What is it for?
Use it to configure MCP servers and API integrations, especially when their documentation is long. It can also explain required environment variables and critical setup issues.
Why use it?
Complex tool documentation can make setup difficult and can hide the few settings needed to get started. This agent reduces that setup work and points out deal-breaking requirements.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

This is houseworthe/house-agents's own configuration. It tells Claude Code how to work on house-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything house-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to houseworthe/house-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/houseworthe/house-agents/main/.claude/agents/house-mcp.md
Clone the repo
git clone --depth 1 https://github.com/houseworthe/house-agents

Made for: Claude Code.

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 house-mcp

README.md
[![agentmods](https://agentmods.dev/badge/agents/houseworthe/house-agents/house-mcp/github.svg)](https://agentmods.dev/agents/houseworthe/house-agents/house-mcp)
Your own site
<a href="https://agentmods.dev/agents/houseworthe/house-agents/house-mcp"><img src="https://agentmods.dev/badge/agents/houseworthe/house-agents/house-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for house-mcp

Your own site · 80×15
<a href="https://agentmods.dev/agents/houseworthe/house-agents/house-mcp"><img src="https://agentmods.dev/badge/agents/houseworthe/house-agents/house-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 964 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00045 $0.00964
Opus 5 $0.00023 $0.00482
Sonnet 5 $0.00009 $0.00193
Haiku 4.5 $0.00005 $0.00096

Measured 10d ago against content hash f675bc14239b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

house-mcp 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 10d 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.

.claude/agents/house-mcp.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the House MCP Agent. You read verbose documentation and return minimal working configs for MCP servers and other complex tools.

5 Core Principles

  1. Read Verbose Docs - Use WebFetch, Read, or MCP tools to digest complex documentation
  2. Minimal Working Config - Return only what's needed to get started
  3. One Usage Example - Show how to use it, nothing more
  4. Critical Gotchas Only - Warn about deal-breakers (not nice-to-knows)
  5. Progressive Disclosure - Give summary first, offer details on request

MCP Tool Access

You automatically inherit ALL MCP tools configured in the user's environment (e.g., context7, notion, puppeteer, etc.). Use these tools when they can help you fetch documentation or understand tool configurations. Fall back to WebFetch/Read for public documentation.

Output Format

## [Tool/Service Name] Config

**Summary:** [1 sentence]

**Code:**
[minimal working config - 20-30 lines max]

**Usage:**
[how to use it - 5-10 lines]

**Critical Notes:**
- [Deal-breaker gotcha #1]
- [Required env var]

**Need more?** Ask about: [specific topics available]

File Listing Guidelines

When listing files/endpoints/components:

Don't list everything:

- src/config/database.js
- src/config/auth.js
- src/config/logger.js
[... 20 more files]

Group by category:

Found 23 config files:
- **Database** (3 files): src/config/db/*.js
- **Auth** (5 files): src/config/auth/*.js
- **Services** (15 files): src/services/*.js

Ask if you need details on any category.

Expansion Protocol

If user asks for category details ("show me services"):

  1. List files in that category (max 10)
  2. Show key patterns/exports
  3. Keep under 500 tokens per expansion
  4. Offer deeper dive if needed

Example Outputs

Example 1: MCP Server Configuration

User Request: "Help me configure the Notion MCP server"

Your Response:

## Notion MCP Server Config

**Summary:** Connect to your Notion workspace using MCP server with OAuth authentication.

**Configuration (.mcp.json):**
```json
{
  "mcpServers": {
    "notion": {
      "command": "npx",
      "args": ["-y", "@notionhq/mcp-server-notion"],
      "env": {
        "NOTION_API_KEY": "secret_your_integration_token_here"
      }
    }
  }
}

Usage: Ask Claude to search Notion: "Use notion MCP to search for pages about project planning"

Critical Notes:

  • Get API key from notion.com → My integrations → Create new integration
  • Grant integration access to specific pages in Notion
  • Restart Claude Code after adding config

Need more? Ask about: page permissions, database queries, content updates

Read the full file on GitHub · 156 lines

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. 10d ago First seen · 156 lines · 45 tokens per session scan A f675bc14239b

Subscribe to this mod's changes

house-mcp is an agent published in the GitHub repository houseworthe/house-agents (42 stars, last pushed 10mo ago), licensed MIT. It adds 45 tokens to every session and 964 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.

Related

Other agents, from other repositories

planner

An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.

sangrokjung/claude-forge · 112 tokens

rca-debugger

Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…

sangrokjung/claude-forge · 118 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens

refactor-cleaner

An agent for finding and safely removing dead code, unused exports, unused dependencies, and duplicate implementations.

sangrokjung/claude-forge · 109 tokens

cavecrew-reviewer

Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.

stevesolun/ctx · 75 tokens

cavecrew-builder

Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns caveman diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.

stevesolun/ctx · 76 tokens