mcp-integration
Central authority for Claude Code Model Context Protocol (MCP) integration. Covers MCP server installation (HTTP, SSE, stdio transports), server management (add, list, remove), installation scopes (local, project, user), plugin-provided MCP servers, enterprise MCP configuration, MCP resources and @ mentions, MCP prompts as skills, OAuth authentication, environment variable expansion, Claude Code as MCP server, output limits, and MCP security. Assists with connecting external tools, configuring MCP servers, managing authentication, and troubleshooting MCP issues. Delegates 100% to docs-management skill for official documentation.
What this skill does
# MCP Meta Skill
## ๐จ MANDATORY: Invoke docs-management First
> **STOP - Before providing ANY response about MCP (Model Context Protocol):**
>
> 1. **INVOKE** `docs-management` skill
> 2. **QUERY** for the user's specific topic
> 3. **BASE** all responses EXCLUSIVELY on official documentation loaded
>
> **Skipping this step results in outdated or incorrect information.**
### Verification Checkpoint
Before responding, verify:
- [ ] Did I invoke docs-management skill?
- [ ] Did official documentation load?
- [ ] Is my response based EXCLUSIVELY on official docs?
If ANY checkbox is unchecked, STOP and invoke docs-management first.
---
## Overview
Central authority for Claude Code Model Context Protocol (MCP) integration. This skill uses **100% delegation to docs-management** - it contains NO duplicated official documentation.
**Architecture:** Pure delegation with keyword registry. All official documentation is accessed via docs-management skill queries.
## When to Use This Skill
**Keywords:** MCP, Model Context Protocol, MCP servers, MCP tools, MCP resources, MCP prompts, HTTP transport, SSE transport, stdio transport, MCP installation, MCP scopes, local scope, project scope, user scope, .mcp.json, plugin MCP servers, enterprise MCP, managed-mcp.json, OAuth authentication, MCP resources, @ mentions, mcp__server__prompt, MCP output limits, MAX_MCP_OUTPUT_TOKENS, claude mcp serve
**Use this skill when:**
- Installing or configuring MCP servers
- Understanding MCP transport types (HTTP, SSE, stdio)
- Managing MCP server scopes (local, project, user)
- Working with plugin-provided MCP servers
- Setting up enterprise MCP configurations
- Using MCP resources with @ mentions
- Executing MCP prompts as slash commands
- Authenticating with remote MCP servers (OAuth)
- Configuring environment variable expansion in .mcp.json
- Using Claude Code as an MCP server
- Managing MCP output limits
- Troubleshooting MCP connection issues
## Keyword Registry for docs-management Queries
Use these keywords when querying docs-management skill for official documentation:
### Core Concepts
| Topic | Keywords |
| --- | --- |
| Overview | "MCP", "Model Context Protocol", "MCP overview" |
| What MCP Does | "what you can do with MCP", "MCP capabilities" |
| Popular Servers | "popular MCP servers", "MCP servers table" |
### Installation and Transport
| Topic | Keywords |
| --- | --- |
| Installation Overview | "installing MCP servers", "MCP server configuration" |
| HTTP Transport | "HTTP transport MCP", "remote HTTP server", "--transport http" |
| SSE Transport | "SSE transport MCP", "Server-Sent Events transport" |
| Stdio Transport | "stdio transport MCP", "local stdio server" |
| Windows Setup | "Windows MCP servers", "cmd /c npx" |
### Server Management
| Topic | Keywords |
| --- | --- |
| Commands | "claude mcp add", "claude mcp list", "claude mcp remove", "/mcp command" |
| JSON Configuration | "add-json MCP", "MCP JSON configuration" |
| Import from Desktop | "add-from-claude-desktop", "import MCP servers" |
### Installation Scopes
| Topic | Keywords |
| --- | --- |
| Scope Overview | "MCP installation scopes", "MCP scope levels" |
| Local Scope | "local scope MCP", "project-specific user settings" |
| Project Scope | "project scope MCP", ".mcp.json file" |
| User Scope | "user scope MCP", "cross-project MCP" |
| Scope Precedence | "MCP scope precedence", "scope hierarchy" |
### Plugin Integration
| Topic | Keywords |
| --- | --- |
| Plugin MCP Servers | "plugin-provided MCP servers", "plugin MCP configuration" |
| Plugin Features | "CLAUDE_PLUGIN_ROOT", "plugin MCP lifecycle" |
### Enterprise Configuration
| Topic | Keywords |
| --- | --- |
| Enterprise Setup | "enterprise MCP configuration", "managed-mcp.json" |
| Allowlists/Denylists | "allowedMcpServers", "deniedMcpServers", "MCP restrictions" |
| Enterprise Paths | "enterprise MCP paths", "managed MCP locations" |
### Resources and Prompts
| Topic | Keywords |
| --- | --- |
| MCP Resources | "MCP resources", "@ mentions MCP", "reference MCP resources" |
| MCP Prompts | "MCP prompts", "mcp__servername__promptname", "MCP skills" |
### Authentication
| Topic | Keywords |
| --- | --- |
| OAuth Setup | "MCP OAuth", "authenticate remote MCP", "/mcp authentication" |
| Token Management | "MCP token refresh", "clear MCP authentication" |
### Advanced Configuration
| Topic | Keywords |
| --- | --- |
| Environment Variables | "environment variable expansion", ".mcp.json variables", "${VAR}" |
| Output Limits | "MCP output limits", "MAX_MCP_OUTPUT_TOKENS", "output warning" |
| Claude as Server | "claude mcp serve", "Claude Code as MCP server" |
### Tool Search & Auto Mode (v2.1.7+)
| Topic | Keywords |
| --- | --- |
| Auto Mode Default | "MCP tool search auto mode", "ENABLE_TOOL_SEARCH", "auto mode default" |
| Auto Threshold Syntax | "auto:N syntax", "MCP threshold percentage", "context threshold" |
| Enable/Disable | "/mcp enable", "/mcp disable", "tool search toggle" |
**Behavior Change (v2.1.7):** MCP tool search auto mode is now enabled by default with a 10% context threshold. Use `auto:N` syntax to configure custom thresholds (0-100%).
**Behavior Change (v2.1.6):** @-mention syntax for MCP servers was removed. Use `/mcp enable <server>` instead.
### Security
| Topic | Keywords |
| --- | --- |
| MCP Security | "MCP security", "MCP prompt injection", "trust MCP servers" |
## Quick Decision Tree
**What do you want to do?**
1. **Add a remote MCP server** -> Query docs-management: "installing MCP servers", "HTTP transport MCP"
2. **Add a local MCP server** -> Query docs-management: "stdio transport MCP", "local stdio server"
3. **Understand scopes** -> Query docs-management: "MCP installation scopes", "scope precedence"
4. **Share MCP with team** -> Query docs-management: "project scope MCP", ".mcp.json file"
5. **Use MCP across projects** -> Query docs-management: "user scope MCP", "cross-project MCP"
6. **Configure plugin MCP** -> Query docs-management: "plugin-provided MCP servers"
7. **Set up enterprise MCP** -> Query docs-management: "enterprise MCP configuration", "managed-mcp.json"
8. **Authenticate with OAuth** -> Query docs-management: "MCP OAuth", "/mcp authentication"
9. **Reference MCP resources** -> Query docs-management: "MCP resources", "@ mentions MCP"
10. **Use MCP prompts** -> Query docs-management: "MCP prompts", "MCP skills"
11. **Expose Claude as MCP server** -> Query docs-management: "claude mcp serve"
12. **Troubleshoot MCP issues** -> Query docs-management: "MCP troubleshooting" + specific issue
## Topic Coverage
### Transport Types and Installation
- HTTP transport (recommended for remote servers)
- SSE transport (deprecated, use HTTP)
- Stdio transport (local processes)
- Windows-specific setup (cmd /c wrapper)
- Double dash (--) parameter explanation
- MCP_TIMEOUT environment variable
### Server Management Commands
- `claude mcp add` (with transport flags)
- `claude mcp list` (show all servers)
- `claude mcp get` (server details)
- `claude mcp remove` (delete server)
- `/mcp` command (in-session status)
- `claude mcp add-json` (JSON configuration)
- `claude mcp add-from-claude-desktop` (import)
- `claude mcp reset-project-choices` (approval reset)
### Scope Configuration
- Local scope (default, private to user/project)
- Project scope (.mcp.json, version controlled)
- User scope (cross-project, private)
- Scope precedence (local > project > user)
- --scope flag usage
### Environment Variable Expansion
- ${VAR} syntax
- ${VAR:-default} syntax with defaults
- Supported expansion locations (command, args, env, url, headers)
- Missing variable handling
### Plugin MCP Server Integration
- Plugin .mcp.json configuration
- Inline mcpServers in plugin.json
- CLAUDE_PLUGIN_ROOT variable
- Automatic lifecycle management
- Multiple transport type support
### Enterprise MCP Management
- managed-mcp.json file locations (macOS, Windows, Linux)
- allowedMcpSeRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts โ single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score โฅ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.