MCP Configuration Management
Comprehensive MCP server configuration templates, .mcp.json management, API key handling, and server installation helpers. Use when configuring MCP servers, managing .mcp.json files, setting up API keys, installing MCP servers, validating MCP configs, or when user mentions MCP setup, server configuration, MCP environment, API key storage, or MCP installation.
What this skill does
# MCP Configuration Management
This skill provides comprehensive tooling for managing MCP (Model Context Protocol) server configurations, including templates, validation scripts, API key management, and installation helpers.
## What This Skill Provides
### 1. Helper Scripts (13 scripts - v2.1 added 7)
**Registry Management (v2.1+):**
- `scripts/registry-init.sh` - Initialize universal MCP registry at ~/.claude/mcp-registry/
- `scripts/registry-add.sh` - Add server to universal registry
- `scripts/registry-list.sh` - List all servers in registry
- `scripts/registry-sync.sh` - Sync registry to target format(s)
- `scripts/transform-claude.sh` - Transform registry → .mcp.json (Claude Code format)
- `scripts/transform-vscode.sh` - Transform registry → .vscode/mcp.json (VS Code format)
**Configuration Management:**
- `scripts/init-mcp-config.sh` - Initialize .mcp.json with proper structure
- `scripts/add-mcp-server.sh` - Add new MCP server to existing config
- `scripts/validate-mcp-config.sh` - Validate .mcp.json structure and server definitions
- `scripts/manage-api-keys.sh` - Securely manage API keys in project .env files (v2.1: .env-only mode)
- `scripts/install-mcp-server.sh` - Install and configure MCP server packages
### 2. Configuration Templates (8 templates - v2.1 added 2)
**Server Type Templates:**
- `templates/basic-mcp-config.json` - Basic .mcp.json structure
- `templates/stdio-server.json` - stdio MCP server configuration
- `templates/http-server.json` - HTTP MCP server configuration
- `templates/python-fastmcp.json` - Python FastMCP server setup
- `templates/typescript-server.json` - TypeScript MCP server setup
- `templates/multi-server-config.json` - Multiple MCP servers configuration
**Registry Templates (v2.1+):**
- `templates/.env.example` - Complete .env template with all known MCP API keys
- Global: `~/.claude/mcp-registry/marketplace.json` - VS Code marketplace servers reference
### 3. Usage Examples (5 examples)
**Documentation:**
- `examples/basic-setup.md` - Basic MCP configuration setup
- `examples/api-key-management.md` - Secure API key handling patterns
- `examples/multiple-servers.md` - Managing multiple MCP servers
- `examples/troubleshooting.md` - Common issues and solutions
- `examples/production-config.md` - Production-ready MCP configurations
## Instructions
### RECOMMENDED: Universal Registry Workflow (v2.1+)
**Best Practice**: Use the universal registry for managing MCP servers across multiple formats (Claude Code, VS Code, Gemini, Qwen, Codex).
#### Step 1: Initialize Registry (One-time)
```bash
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-init.sh
```
Creates:
- `~/.claude/mcp-registry/servers.json` - Universal server definitions
- `~/.claude/mcp-registry/marketplace.json` - VS Code marketplace reference
- `~/.claude/mcp-registry/backups/` - Automatic backups
- `~/.claude/mcp-registry/README.md` - Documentation
#### Step 2: Add Servers to Registry
```bash
# stdio server example (most common)
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-add.sh context7 \
--transport stdio \
--command npx \
--args "-y,@upstash/context7-mcp" \
--env "CONTEXT7_API_KEY=\${CONTEXT7_API_KEY}" \
--description "Up-to-date library documentation"
# http-remote server example
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-add.sh supabase \
--transport http-remote \
--url "https://mcp.supabase.com/mcp" \
--description "Supabase database access"
# http-remote-auth server example (VS Code only)
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-add.sh github \
--transport http-remote-auth \
--url "https://api.githubcopilot.com/mcp/" \
--header "Authorization: Bearer \${GITHUB_TOKEN}" \
--description "GitHub Copilot MCP API"
```
#### Step 3: Sync Registry to Project
```bash
# Sync to Claude Code format (.mcp.json)
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-sync.sh claude
# Sync to VS Code format (.vscode/mcp.json)
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-sync.sh vscode
# Sync to both formats
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-sync.sh both
```
#### Step 4: Configure API Keys
```bash
# Add API keys to project .env
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/manage-api-keys.sh \
--action add \
--key-name CONTEXT7_API_KEY
# Use templates/.env.example as reference
```
#### Step 5: List and Search Registry
```bash
# List all servers
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/registry-list.sh
# Or use jq directly
jq -r '.servers | to_entries[] | "\(.key) - \(.value.transport) - \(.value.description)"' \
~/.claude/mcp-registry/servers.json
```
### Initial MCP Configuration Setup (Direct Mode - Backward Compatible)
When user wants to set up MCP configuration:
1. **Check for existing configuration:**
- Look for `.mcp.json` in project root or `~/.claude/` directory
- Check if server is already configured
2. **Initialize configuration:**
```bash
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/init-mcp-config.sh [path]
```
3. **Use appropriate template:**
- Read template from `templates/` directory
- Customize based on server type (stdio, HTTP, Python, TypeScript)
- Replace placeholder values with actual configuration
### Adding MCP Servers
To add a new MCP server to existing configuration:
1. **Execute add-mcp-server script:**
```bash
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/add-mcp-server.sh \
--name "server-name" \
--type "stdio|http" \
--command "python" \
--args "-m server_module" \
--config-path ".mcp.json"
```
2. **Server types supported:**
- **stdio**: Local process communication (most common)
- **http**: Remote HTTP API servers
- **sse**: Server-sent events (streaming)
3. **Common stdio configurations:**
- Python FastMCP: `python -m fastmcp server_name`
- TypeScript: `node dist/index.js`
- Shell scripts: `bash ./server.sh`
### API Key Management
For servers requiring API keys or secrets:
1. **Create/update .env file:**
```bash
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/manage-api-keys.sh \
--action add \
--key-name "OPENAI_API_KEY" \
--env-file ".env"
```
2. **Reference in MCP config:**
- Use `${API_KEY}` syntax in .mcp.json
- Keys are loaded from .env at runtime
- Script ensures .env is in .gitignore
3. **Security best practices:**
- Never commit API keys to version control
- Use .env files for local development
- Use environment variables in production
- Rotate keys regularly
### Validating Configuration
Before using MCP configuration:
1. **Run validation script:**
```bash
bash ~/.claude/plugins/marketplaces/dev-lifecycle-marketplace/plugins/foundation/skills/mcp-configuration/scripts/validate-mcp-config.sh .mcp.json
```
2. **Validation checks:**
- Valid JSON syntax
- Required fields present (mcpServers object)
- Server type is valid (stdio, http, sse)
- Command paths exist for stdio servers
- URLs are valid for HTTP servers
- Environment variables are defined
- No duplicate server names
3. **Auto-fix common issues:**
- Script can suggRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.