Execute SQL against MySQL or PostgreSQL databases via categorized MCP tools. Use when the user asks to query, describe, explain, create, alter, insert, update, delete, truncate, or drop tables. Provides read tools (select, describe, explain, explain-analyze), write tools (insert, update, alter, create-table), and destructive tools (delete, truncate, drop-table) with built-in injection protection and elicitation on destructive operations.
Add or update an MCP server definition in this registry (servers/*.json) from an upstream repo URL, npm/PyPI package, Docker image, or hosted MCP endpoint. Use when asked to "add a server", "add <product> MCP", "create a definition for <url>", or to add another transport variant (npx/uvx/docker/http) of an existing server.
Add a new MCP server to pi (local stdio scripts or remote HTTP servers with OAuth/API keys like Slack, Linear, Grafana, Redash, Snowflake). Covers mcp.json, the pi mcp CLI, OAuth sign-in, exposure settings, cookie-gate auth-hook prefixes, and verification. Use when the user asks to add/configure/register a new MCP server in pi.
Configure and manage MCP (Model Context Protocol) servers in Claude Code CLI. Use this skill when adding, removing, listing, or troubleshooting MCP servers, or when questions arise about MCP configuration, transport types, scopes, or authentication. Essential for connecting Claude Code to external tools, databases, and APIs.
417mo agoReviewMountCreate a free account to mount
Use when generating an MCP server from an OpenAPI spec with Speakeasy. Triggers on "generate MCP server", "MCP server", "Model Context Protocol", "AI assistant tools", "Claude tools", "speakeasy MCP", "mcp-typescript
2k5mo agoReviewMountCreate a free account to mount
Expose a Buildpad app's own data and actions as an MCP server, so Claude, Copilot, Kiro or Antigravity can call them as tools. Adds one Next.js route (`/api/mcp`, Streamable HTTP, stateless) built on the official MCP TypeScript SDK, where every tool forwards the caller's own access token to the data API, so the caller's permissions apply and no elevated key is used. Covers tool design, input validation, the response shape, client configuration, and testing with the MCP Inspector. Use when the user says add an MCP server, expose my app to AI agents, make tools for an agent, or build an MCP endpoint in the app. Not for connecting an agent to the Buildpad Platform's own MCP.
Use when adding, changing, or troubleshooting an MCP server in the Pi coding agent (`pi mcp add`, `~/.pi/agent/mcp.json`, `.pi/mcp.json`, `/mcp`); covers scope, stdio vs HTTP, credentials, OAuth sign-in, and tool exposure.
Use Zhipu CodePlan MCP vision server for screenshot/UI understanding: OCR, error screenshot diagnosis, and UI→artifact conversion. Use when you need to analyze images, extract text, or turn UI into code/spec. Triggers: OCR, screenshot, 识图, 提取文字, diagnose error screenshot, ui_to_artifact.
Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2) defining MCP tools from GraphQL operations, (3) using introspection tools (introspect, search, validate, execute, explorer), (4) configuring authentication, CORS, health checks, or telemetry, (5) writing Rhai scripts for request lifecycle hooks, (6) defining MCP prompts, (7) troubleshooting MCP server connectivity or tool execution issues, (8) building MCP Apps for interactive UI experiences, (9) deploying Apollo MCP Server to production.
1239mo agoReviewMountCreate a free account to mount
Connect an AI assistant to the Didit identity platform through the Didit MCP server (Model Context Protocol). Use when the user wants to install or configure the Didit MCP server in Claude Code, Claude Desktop or claude.ai, Cursor, VS Code, Windsurf, Zed or any MCP client; sign in with a Didit console account (OAuth 2.1); run the server headless over stdio with a user access token or self-host it; or have an agent act in the Didit Business Console as the signed-in user: build workflows, create and review verification sessions, run standalone checks, manage users, transactions and rules, lists, cases, webhooks, reports and billing. Covers scopes, roles, confirmations and file inputs.
2920d agoReviewMountCreate a free account to mount
Migrates an MCP server with interactive widgets from the OpenAI Apps SDK (window.openai, text/html+skybridge) to the MCP Apps standard (@modelcontextprotocol/ext-apps), covering server-side and client-side changes.
808mo agoReviewMountCreate a free account to mount
Setup tips & tricks: Claude Managed Agents as an MCPserver
Things that aren't obvious from the docs and tend to cost debugging time.
---
## Mental model
### Claude Desktop
19k40d agoReviewMountCreate a free account to mount
Build a curated, tested MCP server (agent tools) with toolsmelt. Use when the user wants an MCP server or agent tools from an API, an OpenAPI/Swagger file, a backend, or a website that has no public API (via a recorded browsing session / HAR file).
1811d agoReviewMountCreate a free account to mount
Connect an MCP client (Claude, Cursor, ChatGPT, any MCP host) to the QuantumProxies.io MCP server: remote Streamable HTTP endpoint with OAuth 2.1 or API key, local npm package quantumproxies-mcp, tool presets, and the list of the 28 tools. Use when the user wants QuantumProxies.io tools inside an AI assistant instead of raw HTTP calls.
Generate a complete Go MCP server project with proper structure, dependencies, and implementation using the official github.com/modelcontextprotocol/go-sdk.
41k7d agoReviewMountCreate a free account to mount
Free MCP server providing 154 tools for AI agents to automate X/Twitter. Scrapes profiles, followers, tweets. Posts, follows, likes, retweets, downloads videos, analyzes sentiment, monitors brands, manages DMs, runs workflows, and more. Uses local Puppeteer -- no API keys or payments required. Compatible with Claude Desktop, Cursor, Windsurf, VS Code. Use when setting up or using AI agent Twitter automation via MCP.
6398mo agoReviewMountCreate a free account to mount
Pentest an MCP server for authentication bypass, confused-deputy SSRF, and tool-argument injection - black-box from its URL, deeper with repo or host access. Use to assess an MCP server's exposure.
15333d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
voletivarshithDeletes or force-pushesSkill
