mister-clean
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mister-cleanprovide the closeout report template and validation steps"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mister Clean
Mister Clean is an agent skill for closing repository work all the way: paying completion debt, reconciling planning and Git state, validating the result, and leaving a successor-ready codebase. Its premise is simple: the repository is the next team's prompt, so a clean inheritance creates intelligent momentum while an unfinished one compounds debt across every later session.
Invocation is standing authorization for the procedures documented in the skill. Ordinary in-scope cleanup is performed, not queued; hard safety and ownership boundaries remain hard boundaries.
Use the skill
Install this repository as a skill in an agent harness, then invoke:
$mister-cleanThe entrypoint is SKILL.md. It routes to focused references only when the current repository makes them relevant.
Use the MCP server
Run the local stdio server:
npx -y @bradheitmann/mister-cleanOr connect a Streamable HTTP client to:
https://mister-clean.bradheitmann.ai/mcpThe MCP server is intentionally read-only. It exposes the canonical skill, references, templates, examples, and closeout prompt; the invoking agent does the authorized work locally where repository policy and ownership can be verified.
Validate a closeout
The authoritative local validators remain inside the repository:
python3 scripts/validate_closeout.py report path/to/closeout-report.json
python3 scripts/validate_closeout.py manifest path/to/action-manifest.jsonRun the full project check before proposing a release:
pnpm install
pnpm check
PYTHONDONTWRITEBYTECODE=1 python3 evals/run_all.py
python3 scripts/check_public_safety.py .Public-safety boundary
The public distribution contains generalized doctrine and synthetic examples. Private case studies, local paths, credentials, project names, and operational evidence do not belong in this repository or its Git history.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Read-only discovery for exact-commit Agent Skill validation, x402 payment, and signed receipts.
Search your team's shared AI-skill library, get install commands, and save skills from your agent.
Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bradheitmann/mister-clean'
If you have feedback or need assistance with the MCP directory API, please join our Discord server