Mcp documentation
Reference and learning guide for the Model Context Protocol (MCP). Use when implementing clients/servers or debugging connection issues. For server listings, see mcp-server-registry.From its SKILL.md
npx -y skills add tuliosousapro/SaaS-blueprint --skill mcp-documentationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 4 stars4 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
1.6 KB, 303 tokens by cl100k_base, as published. Nobody here has run it
MCP Documentation Skill
When to Use
- When needing to understand the underlying architecture of MCP.
- When implementing a custom MCP client or server.
- To research specific protocol features (Resources, Prompts, Tools).
Reference
Instructions
1. Conceptual Understanding
- Clients: Applications like Claude Desktop or IDEs that connect to servers.
- Servers: Lightweight programs that expose tools, resources, and prompts.
- Transports: The communication layer (usually Stdio or SSE).
2. Implementation Guide
- SDKs: Use the official SDKs for TypeScript or Python.
- Core Components:
Tools: Executable functions (e.g.,calculate_roi).Resources: Data sources (e.g.,database://logs).Prompts: Pre-defined templates for LLM interaction.
3. Debugging
- Use the MCP Inspector to test servers interactively.
- Check transport logs for message parsing errors.
Quality Gates
- Compliance with the latest Specification.
- Use of official SDKs for standardized implementations.
- Documentation of custom tools/resources for agent discoverability.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most docs writing skills give in 303 tokens
Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06
- Use third-person for skill descriptionsin 54 of 1951, across 35 files
- Start descriptions with Use whenin 43 of 1951, across 29 files
- Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
- Use active voicein 40 of 1951, across 36 files
- Map file responsibilities before defining tasksin 36 of 1951, across 29 files
- Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
- Ask one question at a timein 35 of 1951
- Offer execution options after saving the planin 33 of 1951, across 24 files
- Include complete code in every stepin 33 of 1951, across 27 files
- Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
- Announce the skill usage at the startin 30 of 1951
- Verify agent compliance after adding the skillin 29 of 1951, across 17 files
Said here and by no other author read
- Use official TypeScript or Python SDKs
- Consult official MCP documentation for architecture
- Document custom tools and resources
- Ensure compliance with the latest specification
- Use MCP Inspector to test servers
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.