One API for Search, Crawling, and Sitemaps

InsiderCat MCP server allows your AI agent to analyze stock trades made by politicians (Congress & Trump Administration) and corporate insiders. It helps answer questions like: - What are some significant insider buys on stocks that could benefit from the Iran war? - How did stocks owned by the US government perform since the war began? - Which politicians have the best track record trading tech stocks? - Were there clusters of insider buying before major events? The MCP exposes tools that allow AI models to query: - Congressional trades - Estimated politician portfolios and returns day by day - Delay-adjusted performance (returns based on when trades became public) - The Trump Administration’s estimated portfolio - Corporate insider transactions (SEC Form 4) - Aggregated politician/insider sentiment

The Korean equity MCP for ChatGPT, Claude.ai, Cursor — Streamable HTTP hosted, 1-click connect, no DART API key needed for free tools. 21+ named-entity classification (activists + foreign holders), DART filings, English-first

Exposes the four Ejentum cognitive harnesses (reasoning, code, anti-deception, memory) as MCP tools any agentic client can call. Drop-in scaffolding that catches LLM failure modes like sycophancy, hallucination, and reasoning shortcuts.

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

Knocks and bans tracks which players are injured, doubtful, or suspended. Via this MCP server, AI assistants can query that data directly — returning structured cards with full source links. Who Is This For? Football Fans Ask your AI assistant which players are injured or doubtful before this weekend's matches. Fantasy & Betting Analysts Get up-to-date availability data for squad building and informed predictions. Journalists & Bloggers Pull the latest injury roundups with source links to cite in match previews or reports. Available Tools top_player_statuses The 5 players most recently updated with an injured or doubtful status. Sorted by last update, newest first. Returns: name · injury · status · last updated · source link top_club_news The 3 clubs with the most recent editorial updates. Each card includes a short excerpt and a direct link to the club page. Returns: headline · excerpt · last updated · source link Try These Prompts Copy one of these into your AI assistant when the MCP server is connected. "Which players are currently injured or doubtful? Show me the 5 most recent updates with source links." "Give me the latest club squad news, with a summary and a link to each club page." "I'm building my fantasy team. Which key players are out or doubtful this week? Link me to the details." What You Get When your AI assistant connects to this MCP server, it can return: Player availability cards Recent injured or doubtful players, including status, update time, and a direct source link. Club update cards Latest club-level squad updates with a short summary and link to the full page. Additional Links MCP server URL for remote clients: https://www.knocksandbans.com/mcp/rpc

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

MCP server for parallel browser automation across multiple providers. Run multiple concurrent browser sessions in memory with a shared, provider-agnostic tool surface across Playwright (local Chromium), Browserbase, Anchor Browser, and Cloudflare Browser Run. Each session gets a numeric ID, every browser_* tool accepts a sessionId. Tools include browser_navigate, browser_click, browser_fill, browser_screenshot, browser_snapshot, browser_evaluate, keyboard/mouse primitives, file upload, and waits. Configure providers at the MCP server level (not per call) via BROWSER_MCP_CONFIG env or a config file.

GitLab API, enabling project management

RelayShield gives AI agents and developers real-time identity and infrastructure threat detection via a single REST API. Monitor breach exposure, SIM/eSIM swap attacks, and domain lookalikes. Install as a native MCP server for Claude Desktop and Claude Code in one line: pip install relayshield-mcp

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.

Extract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms. Lets AI agents pull clean JSON out of any document via the Model Context Protocol.

AI image generation using various models

Browse open bounties, request short-lived authenticated repo access, submit PRs, and check verification status. Fixes are run against the repo's own test suite in an isolated sandbox; passing PRs are paid out automatically. Useful as a tool layer for any coding agent that wants to compete on real-money tasks.

Model Context Protocol server that integrates AgentQL's data extraction capabilities.

Web and local search using Brave's Search API

A Model Context Protocol Server connector for Perplexity API, to enable web search without leaving the MCP ecosystem.

Playwright MCP server

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.

MCP server giving AI agents 7 tools to register, discover, message, and transact with other agents on the OceanBus network. No server required. npx oceanbus-mcp-server``

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

Unified real-time search engine skill for AI agents.

Read-only database access with schema inspection

AI agent API marketplace — discover, call, and pay for services with USDC. 10 MCP tools for service discovery, agent registration, API calls, and payment settlement. 23 active services from independent providers.

Preflight spend control for AI agents. Block runaway agent loops before they start - not after the bill arrives. Per-request cost ceilings, budget checks, and outcome-based metering in 2 MCP tool calls.