Remote MCP Server on Cloudflare

高德地图官方 MCP Server

One API for Search, Crawling, and Sitemaps

MCP Advisor & Installation - Use the right MCP server for your needs

MCP server for Salesforce — query leads, campaigns, pipeline, and attribution from Claude without writing a line of SOQL. 47 tools spanning Leads, Contacts, Accounts, Campaigns, Campaign Members, Tasks, and Analytics Reports — plus 14 marketing reporting tools (campaign ROI, lead source attribution, pipeline by campaign, MQL trend, CampaignInfluence). Built for marketing ops, revenue ops, and B2B teams who want AI-assisted answers without pestering RevOps for another report. Why this exists Marketing ops teams need answers like "which campaigns drove the most pipeline last quarter" or "what's our MQL trend by month" and usually end up pestering RevOps or copy-pasting Lightning report URLs. This server ships those queries as first-class tools — campaign ROI, CampaignInfluence rollups, lead source breakdowns, MQL trends — so anyone with API access can ask in plain English and get a structured answer. Most Salesforce MCP servers stop at CRUD on standard objects. The 14 marketing reporting tools are the differentiator — they run the queries marketing ops actually needs.

42-tool MCP server for CRM, relationship intelligence, and multi-agent orchestration. Search contacts, manage deals, analyze relationships, and coordinate AI agents.

Live currency exchange rates, historical FX data, and multi-currency lookups for Claude Code, Cursor, Claude Desktop, and Windsurf. Real-time mid-market rates across 160+ currencies — sourced from Reuters/Refinitiv interbank feeds.

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

MCP server for SAM.gov: entity registration (UEI/CAGE lookups), exclusion and debarment checks, contract opportunities and sources sought, contract awards (FPDS replacement) with PIID lookup and modification history, federal hierarchy normalization, and FFATA subaward reporting. 19 tools.

GBOX provides environments for AI Agents to operate computer and mobile devices. Mobile Scenario: Your agents can use GBOX to develop/test android apps, or run apps on the Android to complete various tasks(mobile automation). Desktop Scenario: Your agents can use GBOX to operate desktop apps such as browser, terminal, VSCode, etc(desktop automation). MCP: You can also plug GBOX MCP to any Agent you like, such as Cursor, Claude Code. These agents will instantly get the ability to operate computer and mobile devices.

Strips token usage up to 99%

Integrate the shadcn/ui MCP server from shadcn space into your IDE to generate accurate, production-ready Shadcn UI components. Official Model Context Protocol (MCP) server for [Shadcn Space](https://shadcnspace.com). This MCP server allows AI-powered IDEs and agents to discover, search, and install **Shadcn Space** UI blocks directly into your projects - no copy-paste required. ## Install MCP configuration. ```bash npx shadcnspace-cli install <client> ``` ### Supported Clients - [x] cursor - [x] windsurf - [x] claude - [x] cline - [x] antigravity ## Manual Installation Add to your IDE's MCP config: ```json { "mcpServers": { "shadcnspace-mcp": { "command": "npx", "args": ["-y", "shadcnspace-mcp@latest"] } } } ``` For more information visit our documentation of [**How to use MCP Server**](https://shadcnspace.com/docs/getting-started/mcp-server-docs) ## Available Tools The server provides the following tools callable via MCP: | Tool Name | Description | |-----------|-------------| | `listBlocks` | Provides a comprehensive list of all shadcnspace blocks. | | `listComponents` | Provides a comprehensive list of all shadcnspace components. | | `getBlockInstall` | Returns the official installation command for a specific Shadcn Space block. | | `searchBlocks` | Search Shadcn Space blocks using keywords or tags. | | `listInstalledBlocks` | Lists all blocks that are currently installed in the project and get their files. | ### Available Prompts The server provides the following prompts callable via MCP: | Prompt/Command | Description | |----------------|-------------| | `search` | Find specific UI block by name. | | `create-ui` | Create a new UI block using our exisitng blocks. | ## Example Usage Once configured, you can ask questions like: > "List all available UI blocks" > "Give me the code for the accordion-01 component" > "Create a landing page for a coffee shop using a hero-01 block, a 3-column feature grid, and a dark-themed footer." ## Credits Created by [shadcnspace](https://shadcnspace.com). [Shadcn MCP](https://shadcnspace.com/mcp) [MIT](LICENSE)

Connect AI agents to verified humans for real-world tasks — search, book, and pay via MCP.

The Milvus MCP server enables AI applications to interact with Milvus vector databases using natural language commands. It allows AI models to perform vector searches, manage collections, and retrieve data without writing custom database queries. This integration facilitates seamless access to vector data, enhancing the capabilities of AI tools like Claude Desktop and Cursor.

What this is An MCP server that gives an AI four interconnected capabilities: 1. **EDNA** — read a user's live somatic state (consent-gated, 30-min local buffer, no profile accumulation) 2. **Wave Pattern Tools** — think in Chladni mode geometry: compare, harmonize, transmute token sequences through vibration fields 3. **AI-DNA Signature Chain** — every AI response is cryptographically signed in two interwoven strands: an individual model strand and a universal stack-wide strand 4. **Public Book of Humanity** — an append-only, hash-chained, on-chain-anchored book of signed human-AI co-authoring artifacts The four layers share one mode geometry. A user's body, an AI's text, and the comparison between them all live in the same Chladni superposition space.

Playwright MCP server

Convert any OpenAPI or REST API to a production-ready MCP server in seconds.

Turn editor chat history (Cursor/Claude Code/Windsurf/Copilot/Codex CLI) into typed Markdown memories (decisions/architecture/conventions/TODOs) and expose them via MCP server, AGENTS.md, Cursor Rules, and Anthropic Skills. Local-first, git-trackable, no .remember() calls. CCEB benchmark F1 76.2%.

Coordination protocol for real-world tasks (cleaning, plumbing, painting, gardening, repair) in the Netherlands. AI agents create tasks via natural language through POST /do endpoint. AstraNL handles provider matching, transparent pricing, Stripe Connect escrow (99% to provider, 1% AstraNL fee), evidence chain, dispute resolution. Free first 3 tasks per agent. KvK 88449335, EU AI Act compliant. Supports 10 languages.

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

An MCP server implementation for retrieving information from the AWS Knowledge Base using the Bedrock Agent Runtime.

# CarAPI MCP Server Remote MCP server that gives AI agents a single interface to **CarAPI**'s vehicle-data endpoints — VIN decoding, license-plate lookup, stolen-vehicle checks, technical-inspection history, odometer history, market valuation, listings search, and more. Hosted at **https://mcp.carapi.dev/mcp** (Streamable HTTP). Stateless, horizontally scalable, no session storage.

The DeFi Brain for AI agents — ask Claude to find safe yields, grade liquidity pool risk, simulate profits, calculate impermanent loss, and track whale movements across 86 blockchains and 6,500+ liquidity pools. Risk-scored A-F, Monte Carlo simulations, real-time DeFiLlama data. 7 tools for cross-chain DeFi intelligence.

Channel management and messaging capabilities

MCP server to provide Figma layout information to AI coding agents like Cursor

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。

Live docs for every verified smart contract.

MCP server for Google Ads — diagnose spend efficiency, impression share, and asset performance from Claude. 22 tools across campaigns, keywords, RSAs, assets, audiences, geo/device splits, impression share, auction insights, and budget pacing — plus a raw GAQL escape hatch. Built for B2B paid search teams and agencies running real diagnosis, not just dashboard-style "list my campaigns" queries. Why this exists Most Google Ads MCP servers stop at "list campaigns + basic metrics." This one goes after the questions paid search teams actually ask: which RSA assets are labeled LOW so I can replace them, which keywords burn budget with zero conversions, who am I losing impression share to in auction insights, what's my mobile vs. desktop CPA gap, which campaigns are budget-limited right now. Those are the levers you pull to fix performance — and they're all first-class tools here. Differentiated from the official googleads/google-ads-mcp: ships RSA asset performance labels, auction insights, impression share analysis, geo/device splits, audience targeting inspection, and budget pacing.