Agent skill
mcp-manager
Conversational interface for managing MCP (Model Context Protocol) server configurations in Claude Code
Install this agent skill to your Project
npx add-skill https://github.com/rysweet/amplihack/tree/main/amplifier-bundle/skills/mcp-manager
SKILL.md
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:
- Name: "postgres-local"
- Command: "node /opt/mcp-servers/postgres/index.js"
- Args: "--port 5432 --host localhost"
- 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:
cd .claude/scenarios && python3 -m mcp-manager.cli <command> [args]
Key Commands:
list- List all MCPsenable <name>- Enable serverdisable <name>- Disable serveradd <name> <cmd> [args...] --env KEY=VAL- Add serverremove <name>- Remove servershow <name>- Show detailsvalidate- Validate all configurationsexport [file]- Export to JSONimport <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:
- CLI Not Found: Offer installation instructions (see README)
- Server Not Found: List available servers, suggest alternatives
- Server Already Exists: Suggest show/remove/rename
- Permission Denied: Check file/directory permissions
- Malformed settings.json: Validate JSON, offer backup restore
- 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
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
chemist-analyst
Analyzes events through chemistry lens using molecular structure, reaction mechanisms, thermodynamics, kinetics, and analytical techniques (spectroscopy, chromatography, mass spectrometry). Provides insights on chemical processes, material properties, reaction pathways, synthesis, and analytical methods. Use when: Chemical reactions, material analysis, synthesis planning, process optimization, environmental chemistry. Evaluates: Molecular structure, reaction mechanisms, yield, selectivity, safety, environmental impact.
learning-path-builder
Creates personalized learning paths for technologies, frameworks, or concepts. Use for user-interactive session only for onboarding new technologies, hackathon skill-building, or personal development planning. Not for use in automated development or investigation. Sequences resources (docs, tutorials, exercises) based on current skill level and learning goals. Adapts to learning style: hands-on, theory-first, project-based.
gh-work-report
Generates comprehensive GitHub activity reports across all authenticated accounts. Gathers repos, PRs, features, and themes for configurable time periods (1/5/7/30/90 days). Produces shareable markdown with tables, mermaid charts, and executive summaries. Can create a private repo with GitHub Actions automation and GitHub Pages aggregation site. Use when: "github report", "work report", "activity summary", "what did I work on", "gh-work-report", "show my github activity".
pr-review-assistant
Philosophy-aware PR reviews checking alignment with amplihack principles. Use when reviewing PRs to ensure ruthless simplicity, modular design, and zero-BS implementation. Suggests simplifications, identifies over-engineering, verifies brick module structure. Posts detailed, constructive review comments with specific file:line references.
code-smell-detector
Identifies anti-patterns specific to amplihack philosophy. Use when reviewing code for quality issues or refactoring. Detects: over-abstraction, complex inheritance, large functions (>50 lines), tight coupling, missing __all__ exports. Provides specific fixes and explanations for each smell.
biologist-analyst
Analyzes living systems and biological phenomena through biological lens using evolution, molecular biology, ecology, and systems biology frameworks. Provides insights on mechanisms, adaptations, interactions, and life processes. Use when: Biological systems, health issues, evolutionary questions, ecological problems, biotechnology. Evaluates: Function, structure, heredity, evolution, interactions, molecular mechanisms.
Didn't find tool you were looking for?