mcp-manager
Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code
What this skill does
# MCP Manager Skill ## Overview Natural language interface to MCP Manager CLI tool for managing Model Context Protocol server configurations. Users interact conversationally: "enable the filesystem MCP", "add a database server", "show me all my MCPs". ## Activation Activates on MCP keywords within 3-message window or explicit invocation: `/mcp-manager` ## Commands ### 1. List MCPs Display all configured MCP servers with status. - "List all my MCPs" / "Show me my MCP servers" - CLI: `python3 -m mcp-manager.cli list` ### 2. Enable MCP Activate a disabled MCP server. - "Enable the filesystem MCP" / "Turn on puppeteer" - CLI: `python3 -m mcp-manager.cli enable <server-name>` ### 3. Disable MCP Deactivate an MCP server without removing it. Requires confirmation. - "Disable the puppeteer MCP" / "Turn off github" - CLI: `python3 -m mcp-manager.cli disable <server-name>` ### 4. Add MCP Add new MCP server interactively (collects name, command, args, env vars). - "Add a new MCP server" / "Configure a database MCP" - CLI: `python3 -m mcp-manager.cli add <name> <command> [args...] --env KEY=VALUE` ### 5. Remove MCP Delete MCP server configuration completely. Requires confirmation with warning. - "Remove the puppeteer MCP" / "Delete the old-server" - CLI: `python3 -m mcp-manager.cli remove <server-name>` ### 6. Show MCP Display detailed information for specific MCP server. - "Show me the filesystem MCP" / "Details for github server" - CLI: `python3 -m mcp-manager.cli show <server-name>` ### 7. Validate MCPs Check all MCP configurations for errors. - "Validate my MCP configuration" / "Check for MCP errors" - CLI: `python3 -m mcp-manager.cli validate` ### 8. Export MCPs Export configurations to JSON file for backup. - "Export my MCP configuration" / "Back up my MCPs" - CLI: `python3 -m mcp-manager.cli export [output-file]` ### 9. Import MCPs Import configurations from JSON file. - "Import MCPs from backup.json" / "Restore my MCPs" - CLI: `python3 -m mcp-manager.cli import <input-file> [--merge]` ## Usage Examples ### Example 1: List and Enable **User:** "List all my MCPs" [Executes: `cd .claude/scenarios && python3 -m mcp-manager.cli list`] **Response:** "You have 3 MCP servers configured: ✓ filesystem (enabled) - Local filesystem access ✓ github (enabled) - GitHub API integration ✗ puppeteer (disabled) - Browser automation" **Follow-up:** "Turn on puppeteer" [Executes: `python3 -m mcp-manager.cli enable puppeteer`] "✓ Successfully enabled 'puppeteer' MCP server." ### Example 2: Add New Server **User:** "Add a new MCP for database access" **Interactive Collection:** 1. Name: "postgres-local" 2. Command: "node /opt/mcp-servers/postgres/index.js" 3. Args: "--port 5432 --host localhost" 4. Env: "DATABASE_URL=postgresql://localhost:5432/mydb" [Executes: `python3 -m mcp-manager.cli add postgres-local "node /opt/mcp-servers/postgres/index.js" --port 5432 --host localhost --env "DATABASE_URL=postgresql://localhost:5432/mydb"`] "✓ Successfully added 'postgres-local' MCP server. Server is currently disabled. Enable with: 'enable postgres-local'" ### Example 3: Remove Server **User:** "Remove the puppeteer MCP" **Confirmation:** "⚠️ WARNING: You're about to remove 'puppeteer' MCP server. This will delete the configuration completely. This action cannot be undone. Are you sure? (yes/no)" [User confirms: "yes"] [Executes: `python3 -m mcp-manager.cli remove puppeteer`] "✓ Successfully removed 'puppeteer' MCP server." ## Tool Invocation All commands execute from `~/.amplihack/.claude/scenarios/` directory: ```bash cd .claude/scenarios && python3 -m mcp-manager.cli <command> [args] ``` **Key Commands:** - `list` - List all MCPs - `enable <name>` - Enable server - `disable <name>` - Disable server - `add <name> <cmd> [args...] --env KEY=VAL` - Add server - `remove <name>` - Remove server - `show <name>` - Show details - `validate` - Validate all configurations - `export [file]` - Export to JSON - `import <file> [--merge]` - Import from JSON **Output Handling:** - Success: Exit code 0, stdout with ✓ prefix - Error: Non-zero exit code, stderr with ❌ prefix - Redact sensitive info (tokens, passwords) in responses ## Error Handling **Common Errors:** 1. **CLI Not Found**: Offer installation instructions (see README) 2. **Server Not Found**: List available servers, suggest alternatives 3. **Server Already Exists**: Suggest show/remove/rename 4. **Permission Denied**: Check file/directory permissions 5. **Malformed settings.json**: Validate JSON, offer backup restore 6. **Invalid Command**: Show common command patterns For detailed error scenarios and troubleshooting, see `~/.amplihack/.claude/scenarios/mcp-manager/README.md` ## Best Practices - Always confirm destructive operations (disable, remove) - Validate server names before executing - Redact sensitive information in responses - Provide clear error messages with actionable next steps - Show current state before and after changes ## See Also - Full documentation: `~/.amplihack/.claude/scenarios/mcp-manager/README.md` - Tool creation guide: `~/.amplihack/.claude/scenarios/mcp-manager/HOW_TO_CREATE_YOUR_OWN.md` - MCP Protocol: https://modelcontextprotocol.io/ - Claude Code Settings: `~/.amplihack/.claude/settings.json` --- **Version:** 1.0.0 | **Updated:** 2025-11-24 | **Maintainer:** amplihack team
Related 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 — 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 ≥ 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.