MCP Servers

RFP.ai's remote MCP server (streamable-http at rfp.ai/api/mcp) lets Claude Desktop and Cursor draft cited RFP and security-questionnaire answers from your knowledge base, with human review. It exposes 18 scope-gated tools — knowledge-base search, project and Q&A management, approvals and file ingestion — plus 3 prompts. Bearer-token auth is read-only by default, with write scopes granted per token, and every agent write is recorded to an owner-only audit log. EU-hosted. Registry: ai.rfp/rfp-ai.

Provides web search capabilities by integrating with self-hosted or external SearXNG instance. Features - Web Search: Perform powerful aggregated searches across multiple engines. - Discovery: Programmatically retrieve available categories and engines. - Stateless HTTP: Compatible with any standard JSON-RPC client. - Flexible Configuration: Supports environment variables and command-line arguments.

The Oxylabs MCP server provides a bridge between AI models and the web. It enables them to scrape any URL, render JavaScript-heavy pages, extract and format content for AI use, bypass anti-scraping measures, and access geo-restricted web data from 195+ countries. This implementation leverages the Model Context Protocol (MCP) to create a secure, standardized way for AI assistants to interact with web content.

SVGMaker MCP Server is a powerful, AI-driven tool for generating and editing SVG graphics via natural language. It supports seamless LLM integrations (Claude, Cursor, VS Code, and more), real-time updates, secure file handling, and TypeScript support—making it ideal for developers, designers, and automation workflows.

The Harness MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with Harness APIs, enabling advanced automation and interaction capabilities for developers and tools.

Seamlessly integrate real-time data fetched using Scrapeless services, such as Google SERP results into your LLM applications with Scrapeless MCP Server. Backed by the Scrapeless powerful Scraping Browser: a cloud browser developed based on Chromium, with strong customizability, anti-detection capabilities, and scalability. - Browser: precisely manage the entire browser session - Crawl: single page crawling or full-depth recursive crawling to simplify large-scale extraction workflows - Universal API: use advanced anti-bots to bypass website blocks and deal with JavaScript-intensive websites.

Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. In this repository, we provide an installer as well as an MCP Server for Upstash Developer API's.

Enables AI assistants to manage Vercel deployments, projects, and environment variables via natural language commands using Vercel's REST API.

This is a simple MCP server that sends emails using Resend's API. Why? Now you can let Cursor or Claude Desktop compose emails for you and send it right away without having to copy and paste the email content.

An MCP server (stdio transport) that wraps Hugging Face's LocalPythonExecutor (from the smolagents framework). It is a custom Python runtime that provides basic isolation/security when running Python code generated by LLMs locally. It does not require Docker or VM. This package allows to expose the Python executor via MCP (Model Context Protocol) as a tool for LLM apps like Claude Desktop, Cursor or any other MCP compatible client. In case of Claude Desktop this tool is an easy way to add a missing Code Interpreter (available as a plugin in ChatGPT for quite a while already).

Enables AI assistants to interact with Convex deployments, allowing operations such as querying deployment status, managing tables and data, executing functions, and handling environment variables.

Enables AI assistants to interact with CircleCI workflows, retrieve build failure logs, and analyze pipeline statuses using natural language commands.

Enables AI assistants to interact with Apache APISIX via natural language, supporting operations like managing routes, services, plugins, and security configurations through the Admin API.

Provides secure management of environment variables with AES-256 encryption, supporting multi-environment setups and integration with various languages and frameworks.

An MCP server that connects to the Teamwork API, providing a simplified interface for interacting with Teamwork projects and tasks.

Enables AI assistants to interact with Paddle Billing's API, facilitating tasks like managing products, prices, customers, transactions, subscriptions, and generating financial reports.

Enables AI assistants to initiate and manage real-time voice calls using Twilio for telephony and OpenAI for audio processing, facilitating two-way conversational interactions.

Enables AI assistants to retrieve real-time production context—logs, metrics, traces—from Last9, facilitating faster debugging and code fixes.