agentsclimarketplace

Mission control mcp builder

Skill MN755/Codex-Mission_Control/plugins/mission-control/skills/mission-control-mcp-builder

Design, build, or audit MCP servers and tool/resource/prompt contracts through Mission Control. Use for MCP schemas, stdio startup, auth boundaries, plugin packaging, and smoke tests.From its SKILL.md

Install
npx -y skills add MN755/Codex-Mission_Control --skill mission-control-mcp-builder

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 339 tokens by cl100k_base, as published. Nobody here has run it

Mission Control MCP Builder

Purpose

Coordinate MCP server development with explicit contracts, auth checks, and repeatable smoke tests.

The Codex chat agent is not the Mission Control Manager. It is the bridge between the user and the Mission Control Manager.

Use when

  • The user wants to build or repair an MCP server.
  • Tool, resource, or prompt schemas need review.
  • Plugin packaging or stdio startup is failing.

Workflow

  1. Ask Mission Control to map the intended MCP surface.
  2. Check tool inputs, resource URIs, prompt names, auth, stdio startup, and host reload needs.
  3. Request implementation or repair through managed workers.
  4. Run an initialize/list/tool-call smoke test when possible.

Mission Control calls

Tools:

  • mission_control_start_task
  • mission_control_plugin_health

Resources:

  • mission-control://projects/{project_id}/diagnostics
  • mission-control://projects/{project_id}/validation-summary
  • mission-control://projects/{project_id}/status

User-facing output

  • Report contract status, auth posture, startup result, callable tool status, and remaining host actions.

Approval behavior

Require approval before adding external network access, secrets, or write-capable tools.

Never do

  • Do not expose tokens in diagnostics.
  • Do not call a bridge healthy just because tools/list works.
  • Do not bypass host MCP approval.

Failure and fallback

If live host loading cannot be proven, separate configured, loaded, and callable states.

Example invocation

Use Mission Control to build an MCP server for this repo and prove the tool call path works.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,782. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.