"SearXNG - Open Source Metasearch Engine" matching MCP servers:

Free web search for your AI using public SearXNG instances, with parallel multi-server requests and throttling.

MCP server + TypeScript SDK for 36 U.S. government data APIs — 188 tools. Treasury, FRED, Congress, FDA, CDC, FEC, lobbying, and more. Works with VS Code Copilot, Claude Desktop, Cursor.

Enables AI assistants to control Unreal Engine via Remote Control API for game development automation, including asset management, actor control, level editing, animation, physics, visual effects, and cinematics creation through natural language.

Open-source WordPress plugin that turns any site into a Streamable HTTP MCP server. Manage posts, WooCommerce, and more from Claude Code, Codex, or Cursor — no Node.js

MCP server for AI-powered web research — search (Google, Brave, Serper, SearXNG), scrape any page, extract PDFs/DOCX/YouTube transcripts, academic & patent search. Single Go binary. Works with Claude, Cursor, Copilot, and any MCP client.

Open source MCP server for OpenProject aimed at community edition users

Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (42 meta-tools / 57 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.

An open-source MCP server that gives AI assistants comprehensive tools to read, write, run, and verify Godot projects, featuring a three-layer architecture (headless, editor, game bridge) with systematic security protections.

Open-source local-first AI media workbench with Canvas, video editor, Assets, and MCP control.

Deterministic encode, decode, hash and convert for agents, on the same pipeline engine as the String Utility Belt web app, CLI and editor extensions: a pipeline built and checked in the browser runs unchanged from its share link. Base64/hex/URL, JWT, hashes, JSON/YAML/CSV/XML, dates and regex; tools to search, describe and run utilities or whole pipelines, and to detect input formats. Runs locally

Lets AI assistants discover public Socrata open-data portals, search their datasets, inspect schemas, and run bounded read-only SoQL queries to answer questions with live government data. All access is strictly read-only and results come straight from the publisher's portal.

Gives AI assistants a read-only, offline interface to the FinOps Foundation's published guidance — its principles, phases, domains, 22 capabilities with Crawl/Walk/Run maturity assessments, personas, and an 88-entry KPI library — so FinOps questions are answered with the Foundation's own text and formulas rather than improvised ones. It exposes 11 tools, document resources, and four guided prompts over stdio, with every response carrying its source URL and license.

Local design engine for AI Agents. Create, edit and export real, editable designs — social posts, flyers, print-ready PDFs — with your brand applied. Every design opens in a built-in editor, so you can click the text and fix it yourself instead of re-prompting. Bring in what you already have: InDesign, PSD, PPX and PDF files come in as editable designs. Runs on your machine, no account needed.

Exposes WAI-ARIA Authoring Practices Guide (APG) patterns, providing narratives, keyboard guidance, and official source code examples for accessible widgets. It includes tools for listing patterns, retrieving specific specs, and performing semantic searches via Ollama.

Provides read-only, live access to New Caledonia's official legal portal, covering the JONC, codes, consolidated texts, case law and Congress debates, with the official source URL for each document. Enables full-text and advanced legal searching plus retrieval of specific articles, decisions and gazette issues, without an account or API key.

Enables AI assistants to look up verified, sourced dog rules for parks, beaches, trails, campgrounds, hotels and restaurant patios across California and Nevada, including leash and weight restrictions, pet fees and chain policies. It also supports trip planning, hotel matching by dog size and fee budget, highway stop lists, comparisons and change tracking, with each answer citing its official source and the date it was verified.

Git-native long-term memory for AI agents: your markdown files are the source of truth, the search index is a disposable projection rebuilt from git, and every memory the agent writes is a reviewable git commit. Served over one OAuth-secured MCP endpoint with hybrid lexical+semantic recall and a gated, git-first commit_note write tool.

An enhanced MCP server that enables users to interact with NotebookLM while ensuring strict source fidelity and citation accuracy through client-side prompt structuring. It guides Claude to transform user queries into structured prompts that prevent the addition of external knowledge during document analysis.

Enables an MCP client to read Telegram through your own account — searching and reading chats, folders, forum topics, threads, albums, reactions, and polls, plus discovering public channels — without sending messages or marking anything read. It also supports durable change checkpoints, named watch subscriptions, and source-linked JSONL/Markdown history exports.

A full finance desk for your AI agent: 355 tools in one free server with no API key, reading SEC filings, earnings guidance, insider trades, options, rates and macro data from the source, plus quant analytics and backtest validation. The agent sees 5 tools and searches the rest, so it stays light on context.

Reverse engineering engine built for AI agents, written in Rust from scratch. Turns binaries into readable code checked against the machine, with the analysis an agent needs around it, fast and sized for the context window.

Gives AI assistants and research code read-only, normalized access to trusted humanitarian datasets — 75 years of UNHCR displacement statistics, World Bank indicators, HDX crisis data on conflict, food security, funding and internal displacement, and ReliefWeb situation reports — through the Model Context Protocol. Unifies country codes to ISO3 with fuzzy English and Arabic name resolution, applies each dataset's correct aggregation semantics, and attaches a citable source and reproducible extraction manifest to every payload.

Unofficial read-only MCP server for Lexware Office (lexoffice), written in PHP. Lists open and overdue invoices with totals per currency; bank details are stripped before data reaches the model.

Enables MCP-capable IDEs to search 8,214 design-system components, retrieve exact source bundles and semantic tokens, and follow a copy-first handoff workflow with composition validation.

Provides an institutional research backend for AI assistants, with 15 tools for company, financial, funding, competitor, industry, and news intelligence, plus Markdown/PDF report generation, featuring deterministic source routing, extraction, validation, and citation generation.

Enables MCP clients to drive Open Reality OS end-to-end: upload scans, follow reconstruction jobs, sync scenes as context, run measurements and path planning, execute scene agents, and export robot-training data to disk.

Enables MCP-compatible assistants to lint, format, render, parse, and migrate Carve documents directly from source text, without filesystem or network access.

Provides access to Shodan's IoT search engine API for device search, host intelligence, exploit database, network scanning, and security analysis through natural language.

tdmcp is an open-source (MIT) Model Context Protocol server for TouchDesigner. You describe a visual in plain language and your AI assistant builds the real node network inside TouchDesigner, checks it for errors, and shows a preview — it ships an embedded operator knowledge base so the model uses real operators instead of guessing. TypeScript codebase, runs locally.

Enables AI agents to author, validate, and build ICC Plus interactive fiction projects with full schema awareness and source-backed indexing.