mcp

Admin tools for inspecting and restarting connected MCP servers — status, resources, prompts. Does NOT expose tools provided by MCP servers; those appear as mcp__server__tool and are fetched via tool_search.

6 stars

Best use case

mcp is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Admin tools for inspecting and restarting connected MCP servers — status, resources, prompts. Does NOT expose tools provided by MCP servers; those appear as mcp__server__tool and are fetched via tool_search.

Teams using mcp should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/mcp/SKILL.md --create-dirs "https://raw.githubusercontent.com/lmorchard/decafclaw/main/src/decafclaw/skills/mcp/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/mcp/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How mcp Compares

Feature / AgentmcpStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Admin tools for inspecting and restarting connected MCP servers — status, resources, prompts. Does NOT expose tools provided by MCP servers; those appear as mcp__server__tool and are fetched via tool_search.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# MCP admin

**This skill is NOT for calling tools that MCP servers provide.** Tools exposed by MCP servers are named `mcp__server__tool` and live in the regular tool catalog. If a tool like `mcp__github__create_issue` isn't immediately available, use `tool_search` to fetch it from the deferred catalog — do NOT activate this skill.

This skill is only for *administering* the MCP layer itself — inspecting server status, listing or reading resources, listing or fetching prompts, or restarting servers.

## Tools

- `mcp_status(action?)` — show connected servers and their tools/resources/prompts, or `action="restart"` to reconnect a server.
- `mcp_list_resources()` — list resources (static) and resource templates (parameterized) from all connected servers.
- `mcp_read_resource(server, uri)` — fetch a specific resource by URI.
- `mcp_list_prompts()` — list prompts from connected servers, including argument schemas.
- `mcp_get_prompt(server, name, arguments?)` — retrieve a specific prompt, optionally with JSON arguments.

## When to use

- A user asks about MCP server status, missing servers, or server errors.
- You need to fetch resource content from an MCP server.
- You need a prompt templated from an MCP server.
- A restart is needed after a config change.

If you're just using a tool exposed by an MCP server (e.g. `mcp__github__create_issue`), you do **not** need this skill — those tools are regular tools in the catalog.

Related Skills

vault

6
from lmorchard/decafclaw

Unified knowledge base — shared Obsidian-compatible vault for curated pages, journal entries, and user notes

tabstack

6
from lmorchard/decafclaw

Your primary tool for any web, PDF, or research task. More powerful than web_fetch — prefer this for all research, web reading, and data extraction. Triggers on: 'tell me about,' 'what is,' 'look up,' 'find out,' 'research,' 'summarize this article,' 'read this PDF,' 'check this site,' 'what does this page say,' 'extract data from,' 'find the price on,' 'compare X vs Y,' 'is it true that,' or any URL/link. Handles JavaScript-heavy websites, PDFs, structured data extraction, content transformation, multi-source research with citations, and multi-step browser automation.

project

6
from lmorchard/decafclaw

Structured project workflow: brainstorm, spec, plan, execute multi-step tasks

postmortem

6
from lmorchard/decafclaw

Structured blameless analysis of what went wrong in this conversation — identifies root causes and proposes minimal, specific fixes

newsletter

6
from lmorchard/decafclaw

Compose and deliver a narrative newsletter summarizing autonomous agent activity in the window.

ingest

6
from lmorchard/decafclaw

Fetch a URL, workspace file, or attachment and integrate its content into the vault — one primary page plus cross-linked updates to related pages

health

6
from lmorchard/decafclaw

Show agent diagnostic status — process, MCP, heartbeat, tools, embeddings

garden

6
from lmorchard/decafclaw

Vault gardening sweep — merge, link, split, and tidy agent pages

dream

6
from lmorchard/decafclaw

Review recent journal entries and conversations, distill insights into vault pages

claude_code

6
from lmorchard/decafclaw

Delegate coding tasks to Claude Code as a subagent. Use when asked to fix bugs, add features, refactor code, write tests, review code, or do any work that requires reading and editing files in a codebase. Triggers on: 'fix this bug', 'add a feature', 'refactor', 'write a test', 'review this code', 'update the config', 'clean up', or any request involving code changes in a repository.

background

6
from lmorchard/decafclaw

Start, monitor, and stop long-running background processes (servers, watchers, builds). Returns immediately with a job ID you can poll for output.

writing-clearly

6
from lmorchard/decafclaw

Edit prose for clarity and concision using Strunk's *The Elements of Style* (1918). Use whenever you have a draft — documentation, commit messages, blog posts, replies — that should be tightened before it goes out.