测试

Official Firecrawl MCP Server - Adds powerful web scraping to Cursor, Claude and any other LLM clients.

Structured business info (address, hours, services, payment methods, languages, insurance) for any named business — combines OpenStreetMap + KVK Handelsregister + LLM-extracted website data.

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

mneme is an open-source, vault-native memory layer for Claude Code and any MCP client. Your Markdown files are the source of truth. The index, embeddings, and knowledge graph are all derived and rebuildable. No LLM or network on the capture path. Redaction runs before every derived store. MIT licensed.

An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.

63-layer continuous-time Symplectic Neural ODE computing topological invariants of real market signals. 256-dim feature space with non-Abelian gauge field geometry. 27 data products (property intelligence, DAG manifold computation, federal contracts, distressed real estate) with autonomous Stripe purchase. 500K out-of-pocket validated embeddings. Free tier available.

An MCP server that provides a tool for sending transactional emails via Mailtrap

ead-only MCP server for searching and browsing essays on payments, fintech, and protocol thinking by Ben Milne. 3 tools: list_posts, get_post, search_posts. Streamable HTTP transport, no auth required.

A Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Turn a written schedule into a live calendar link people subscribe to in Apple, Google, Outlook. Calfeed's create_calendar tool takes plain text (shifts, practices, classes, a season, an itinerary) and publishes a hosted calendar that updates for every subscriber. Mint an access token at calfeed.ai/profile.

# govql-mcp-server An MCP (Model Context Protocol) server for [GovQL](https://govql.us) — gives AI clients like Claude Desktop, Claude Code, and Cursor direct access to the US Congressional GraphQL API at [api.govql.us/graphql](https://api.govql.us/graphql) without bespoke HTTP wiring. For the design rationale (why FastMCP-Python, the passthrough+curated philosophy, roadmap through v0.4), see [design.md](https://github.com/govql/govql/blob/main/mcp-server/docs/design.md). ## What you can do with it Ask an agent questions like: - *"How did Vermont's two senators vote on the most recent nomination?"* - *"Which legislators in the 118th Congress switched parties during their service?"* - *"Compare Senator Sanders' voting record to Senator Murkowski's on cloture votes in the most recent Congress."* The agent picks the right tool, writes the GraphQL query against the live schema, and parses the response — no manual API wrangling. ## Install The server runs as a per-client subprocess over stdio. Pick your client: ### Claude Desktop Edit `claude_desktop_config.json` (Settings → Developer → Edit Config): ```json { "mcpServers": { "govql": { "command": "uvx", "args": ["govql-mcp-server"] } } } ``` Restart Claude Desktop. The `govql` tools appear in the tools panel. ### Claude Code Add to `.mcp.json` in your project (or `~/.mcp.json` for global): ```json { "mcpServers": { "govql": { "command": "uvx", "args": ["govql-mcp-server"] } } } ``` ### Cursor Settings → MCP → Add Server. Use the same `command` / `args` as above. ### Other clients Any MCP-compatible client that supports stdio servers will work. The command is `uvx govql-mcp-server` with no required arguments. ## Tools | Tool | Purpose | |---|---| | `execute_graphql` | Run any GraphQL query against the GovQL endpoint. Returns the result plus an `last_ingest` timestamp so the agent can reason about data freshness. | | `list_types` | Returns the names and kinds of every type in the GovQL schema. Optional `kind` filter (`"OBJECT"`, `"INPUT_OBJECT"`, `"ENUM"`, etc.) to narrow further. Start here when you don't know what's queryable. | | `describe_type` | Returns one type's full details — fields, arg signatures, input fields, enum values. Call after `list_types` to learn the shape of a specific type before writing a query. | ## Configuration All env vars are optional — the package is zero-config for end users. | Env var | Default | Purpose | |---|---|---| | `GOVQL_ENDPOINT` | `https://api.govql.us/graphql` | Endpoint to query. Override to point at a local dev stack. | | `GOVQL_TIMEOUT_MS` | `30000` | Per-request HTTP timeout. | | `LOG_LEVEL` | `INFO` | Logging level. Logs go to stderr only (stdout is reserved for the MCP transport). | ## Limits (enforced by the upstream API) - Max query depth: 10 - Max query complexity: ~10 billion points (`first: N` multiplies child cost by N — keep page sizes reasonable on deeply nested queries) - Rate limit: 100 requests / 60 s per source IP A depth or complexity violation surfaces as a GraphQL `errors` entry in the tool response so the agent can adjust and retry. ## Data freshness Every `execute_graphql` response includes a `last_ingest` ISO timestamp. Vote data refreshes hourly; legislator data refreshes daily. ## Status Version 0.1.0 ships three foundational tools: a GraphQL passthrough (`execute_graphql`) and two narrow schema-discovery tools (`list_types`, `describe_type`). Curated higher-level tools (`find_legislator`, `get_voting_record`, `compare_voters`, etc.) are planned for subsequent releases — see [design.md](https://github.com/govql/govql/blob/main/mcp-server/docs/design.md) for the roadmap. ## Links - [GovQL project site](https://govql.us) - [GraphQL API](https://api.govql.us/graphql) - [Source / issues](https://github.com/govql/govql)

百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

Web and local search using Brave's Search API

Web content fetching and conversion for efficient LLM usage

A Serper MCP Server

MCP server for the Savvly Longevity Benefit Fund: product info, Savvly-vs-alternative comparisons, eligibility checks, an audience-tagged Q&A library, and retirement / lump-sum / monthly projections (with inline MCP Apps chart widgets).

clariBI is an AI-powered business intelligence platform built for small and mid-sized SaaS, ecommerce, and operations teams. Instead of writing SQL or building dashboards manually, users ask questions in plain English ("what's our CAC by channel last quarter?") and the AI engine pulls the data from Stripe, HubSpot, Google Analytics, ad platforms, Jira, and 30+ other sources via the open Model Context Protocol. Dashboards generate themselves on source connect.

虎嗅嗅官方AI助手，可查询AI行业早报、投融资事件、产品动态、硬件与原生关键信号。

A stdio MCP server that connects MCP-compatible Agents to MySQL for database discovery, table inspection, safe SELECT queries, controlled INSERT/UPDATE operations, EXPLAIN plans, and table status metadata. Part of MCP Java SDK, a Java toolkit for building custom MCP Servers.

Zhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.

Recruiting-ops MCP for asking Lever questions and finding bottleneck owners inside Claude, Cursor, or another AI workspace.

AgentDrive is a cross-agent artifact workspace with provenance and portable storage across Claude Code, Codex, Cursor, and LangGraph. 20 MCP tools: file CRUD, semantic recall over workspace artifacts, run logging, cross-agent attribution, comments, and shares. Connect to the hosted server at https://mcp.agentdrive.sh/mcp with an Authorization: Bearer key, or run locally via npx @adrive/mcp-server. Free tier (1 GB + 10k embeddings) at https://app.agentdrive.sh — no credit card.

Create a QR code for Ukrainian domestic payments at a point of sale or online and accept cashless payments to IBAN

AI image generation using various models

RollingGo-Flight-MCP is a native MCP plugin for global air ticketing services. Powered by the world’s 3rd largest travel B2B firm. Totally free with no call quota limits. Fully compatible with AI Agents including Claude, Cursor, Codex and mainstream MCP clients. It aggregates 500 airlines, covering flight routes across 200 countries and regions.

Minimal project management for teams and AI agents. Manage tasks, projects, and workspaces from Claude, Cursor, Windsurf, and any MCP-compatible AI assistant.

Validate a business idea against 6 live demand signals: Demand, Pain, Competition, Money, Funding, Urgency. Drawn from a 55k+ idea corpus across 200+ sources (a16z, YC, Product Hunt, Forbes, App Store), hundreds scored each week and refreshed daily, with named competitors, metrics, and real user complaints cited to source URLs. Validate your own idea too. Works in Claude Code, Cursor, and Codex.