MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A skill your agent uses when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client…
Install MCP Docs
$ npx skills add confluentinc/mcp-confluent --skill mcp-docs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install confluentinc/mcp-confluent mcp-docs --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/confluentinc/mcp-confluent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/mcp-docs .claude/skills/mcp-docs && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mcp-docs" agent skill from https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docs into .claude/skills/mcp-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-docs", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add confluentinc/mcp-confluent --skill mcp-docs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install confluentinc/mcp-confluent mcp-docs --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/confluentinc/mcp-confluent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/mcp-docs .agents/skills/mcp-docs && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mcp-docs" agent skill from https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docs into .agents/skills/mcp-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-docs", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add confluentinc/mcp-confluent --skill mcp-docs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install confluentinc/mcp-confluent mcp-docs --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/confluentinc/mcp-confluent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/mcp-docs .cursor/skills/mcp-docs && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mcp-docs" agent skill from https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docs into .cursor/skills/mcp-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-docs", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/confluentinc/mcp-confluent.git --path .claude/skills/mcp-docs--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add confluentinc/mcp-confluent --skill mcp-docs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install confluentinc/mcp-confluent mcp-docs --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/confluentinc/mcp-confluent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/mcp-docs .gemini/skills/mcp-docs && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mcp-docs" agent skill from https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docs into .gemini/skills/mcp-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-docs", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install confluentinc/mcp-confluent mcp-docsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add confluentinc/mcp-confluent --skill mcp-docs -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/confluentinc/mcp-confluent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/mcp-docs .github/skills/mcp-docs && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mcp-docs" agent skill from https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docs into .github/skills/mcp-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-docs", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add confluentinc/mcp-confluent --skill mcp-docs -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install confluentinc/mcp-confluent mcp-docs --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/confluentinc/mcp-confluent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/mcp-docs .opencode/skills/mcp-docs && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mcp-docs" agent skill from https://github.com/confluentinc/mcp-confluent/tree/main/.claude/skills/mcp-docs into .opencode/skills/mcp-docs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-docs", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mcp-docs- GitHub stars
- 167
- Token cost
- ~604 tokens
- SKILL.md length
- 210 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client…
- Works in 3 steps: Fetch the documentation index → Fetch the relevant page(s) → Cross-reference with our codebase
- The user asks about Model Context Protocol details (protocol spec
- SKILL.md covers Instructions and Documentation Tiers
- Reaches modelcontextprotocol.io
What it does
MCP Docs is an agent skill from confluentinc/mcp-confluent. Use when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client concepts, extensions, or SDK usage). Triggers on phrases like "MCP spec", "MCP transport", "streamable HTTP", "MCP authorization", "listtools", "initialize handshake", "MCP SDK", "@modelcontextprotocol/sdk", or "how does MCP X".
Its SKILL.md is about 600 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The licence is MIT.
When your agent uses it
- The user asks about Model Context Protocol details (protocol spec
- Tools/resources/prompts
- Sampling/elicitation/roots
- Server/client concepts
Example prompts
- “MCP spec”
- “MCP transport”
- “streamable HTTP”
- “/mcp-docs”
Requirements
- Pre-approved tools (allowed-tools): WebFetch, WebSearch, Read, Grep
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 76cffd5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
WebFetchWebSearchReadGrep
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
modelcontextprotocol.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
MCP Docs loads about 604 tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 210 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from confluentinc/mcp-confluent at commit 76cffd5, republished under its MIT licence (© confluentinc). 210 words, ~604 tokens.
Download SKILL.mdSave it as
.claude/skills/mcp-docs/SKILL.md (or your agent's skills folder).- name
- mcp-docs
- description
- Use when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client concepts, extensions, or SDK usage). Triggers on phrases like "MCP spec", "MCP transport", "streamable HTTP", "MCP authorization", "list_tools", "initialize handshake", "MCP SDK", "@modelcontextprotocol/sdk", or "how does MCP X".
- allowed-tools
- WebFetch, WebSearch, Read, Grep
MCP Protocol Documentation Lookup
Look up Model Context Protocol (MCP) documentation from modelcontextprotocol.io.
Instructions
You are looking up MCP protocol documentation to answer a question or guide implementation.
Step 1: Fetch the documentation index
Fetch the machine-readable index at https://modelcontextprotocol.io/llms.txt. This lists all ~90
documentation pages with titles and URLs. Use it to identify which page(s) are relevant to the
question.
Step 2: Fetch the relevant page(s)
Append .md to page URLs for cleaner markdown content. For example:
https://modelcontextprotocol.io/docs/learn/architecture.mdhttps://modelcontextprotocol.io/specification/2025-11-25/server/tools.md
Fetch only the pages needed to answer the question — typically 1-3 pages.
Step 3: Cross-reference with our codebase
When relevant, use Read and Grep to cross-reference the documentation with our implementation in
src/ to provide concrete, project-specific guidance.
Documentation Tiers
Use these categories to prioritize which pages to fetch:
Specification (
/specification/2025-11-25/...) — Protocol-level details: transports, lifecycle, tools, resources, prompts, pagination, logging. Prioritize for questions about MCP server implementation, protocol behavior, or message formats.Develop guides (
/docs/develop/...) — Building servers/clients, connecting local/remote servers. Prioritize for integration, setup, or "how do I build..." questions.Learn (
/docs/learn/...) — Architecture, core concepts, server/client roles. Prioritize for conceptual or "how does MCP work" questions.SDK (
/docs/sdk.md) — SDK reference. Relevant when working with@modelcontextprotocol/sdkAPIs.Extensions (
/extensions/...) — Auth, application support, client compatibility matrix. Relevant for auth and transport questions.
© confluentinc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/mcp-docs of confluentinc/mcp-confluent.
Open the folder on GitHubat commit 76cffd5
Compare with similar skills
MCP Docs next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| MCP Docs this skillconfluentinc/mcp-confluent | 167 | — | ~604 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | 1 repos | ~823 | Automated safety check: Pass | Apache-2.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
More from confluentinc/mcp-confluent
Related
Works with
Categories
Questions about MCP Docs
What does MCP Docs do?
A skill your agent uses when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client…. MCP Docs is an agent skill from confluentinc/mcp-confluent. Use when the user asks about Model Context Protocol details (protocol spec, transports, authorization, tools/resources/prompts, sampling/elicitation/roots, server/client concepts, extensions, or SDK usage).
When should I use MCP Docs?
MCP Docs fits situations like: the user asks about Model Context Protocol details (protocol spec; tools/resources/prompts; sampling/elicitation/roots; server/client concepts.
How do I install MCP Docs in Claude Code?
Run `npx skills add confluentinc/mcp-confluent --skill mcp-docs -a claude-code`. Or copy the skill folder (.claude/skills/mcp-docs in confluentinc/mcp-confluent) into .claude/skills/mcp-docs in your project. Claude Code loads it when a task matches its description.
How do I install MCP Docs in Codex?
Run `npx skills add confluentinc/mcp-confluent --skill mcp-docs -a codex`. Or copy the skill folder (.claude/skills/mcp-docs in confluentinc/mcp-confluent) into .agents/skills/mcp-docs in your project. Codex loads it when a task matches its description.
Can I use MCP Docs in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add confluentinc/mcp-confluent --skill mcp-docs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-docs, .gemini/skills/mcp-docs, .github/skills/mcp-docs and .opencode/skills/mcp-docs in your project.
What does MCP Docs need to run?
SKILL.md names no scripts, command-line tools or credentials: MCP Docs is instructions for the agent only. Its frontmatter pre-approves these tools: WebFetch, WebSearch, Read, Grep.
Does MCP Docs access the network?
SKILL.md names 1 domain. In commands or code: modelcontextprotocol.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is MCP Docs safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does MCP Docs use?
MCP Docs is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does MCP Docs use?
About 604 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to MCP Docs?
Skills that share tags, products or a category with MCP Docs: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MCP Docs?
confluentinc (a GitHub organization) maintains it in confluentinc/mcp-confluent, which has 167 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.
Source: confluentinc/mcp-confluent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.