MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
exa-mcpgithub.com/2aronS/exa-mcpupdated this year
MCP server for web search and crawling using Exa API
MIT ★ 6 -
Exa MCPno update data
Enable AI assistants to perform web searches using Exa's powerful search API.
smithery -
Use Exa with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Exa MCP for web search and web crawling!
MIT ★ 5,234 -
exa-mcp-rotategithub.com/AdvaitR7/exa-mcp-rotateupdated this year
Exa MCP server with multi-key round-robin API key rotation for OpenCode and other MCP clients.
MIT ★ 1 -
A Model Context Protocol server with Exa for web search, academic paper search, and Twitter/X.com search. Provides real-time web searches with configurable tool selection, allowing users to enable or disable specific search capabilities. Supports customiz
npm mit -
Exa MCP Serverno update data
Enable AI assistants to perform real-time web searches using Exa's powerful search API. Get structured search results, cache recent searches, and handle rate limits gracefully for a seamless experience. Empower your AI with fresh content and optimized search capabilities.
smithery -
Exa MCP Serverno update data
Enable AI assistants to perform web searches using Exa's powerful search API. Get real-time web information in a safe and controlled way, while caching recent searches for future reference. Enhance your AI's capabilities with structured search results and customizable parameters.
smithery -
SearchHub normalizes Serper, Tavily, Exa, AnySearch, and other search APIs behind one HTTP, CLI, and MCP interface. It manages provider keys, quotas, rate limits, circuit breakers, logs, and failover so an AI agent does not lose web search when one key or provider fails.
npm MIT ★ 3 -
web-retrieval-mcpgithub.com/velvetsp/web-retrieval-mcpupdated this year
MCP server for AI agents: high-fidelity web search (Exa) + tiered web fetch (Exa → optional local browser → Firecrawl) with an SSRF guard. A drop-in replacement for built-in WebSearch/WebFetch.
pypi MIT -
MCP server for AI agents: high-fidelity web search (Exa) + tiered web fetch (Exa→browser→Firecrawl) with SSRF guard. Drop-in replacement for built-in WebSearch/WebFetch in Claude Code, Codex, Grok, Cursor and all other agents.
MIT ★ 9 -
Local web-search proxy and cache for AI agents. Exa-compatible HTTP API + MCP, under 30MB RSS.
NOASSERTION ★ 6 -
Agent-native multi-provider web search for AI agents (Claude Code, Hermes, DeepSeek Harness, OpenCode, Codex). Model grounding (Responses, ARK) + semantic search (Exa, Parallel) + keyless defaults via MCP, CLI, and DSH plugin.
pypi MIT ★ 16 -
Round-robin web search over the free tiers of multiple search APIs (Tavily, Firecrawl, Parallel, Exa, …) as an MCP server — with a dashboard for keys, engine order/toggles and live quota status.
npm MIT ★ 2 -
Unified multi-provider search & content-extraction MCP server & aggregates Exa/Serper/Tavily/Firecrawl/Jina with RRF fusion
MIT -
mcp-server-metasearchgithub.com/busigui2023/mcp-server-metasearchupdated this year
A local MCP server aggregating 15 web search & extraction tools across 5 providers (Jina, Tavily, Exa, Firecrawl, Bocha)
MIT -
The web toolkit for AI coding agents — scrape, search, map, crawl, index, extract, diff, serve. Single static binary, MIT. Self-hosted Firecrawl/Exa/Tavily alternative.
MIT -
Balanced web search plugin/MCP server for DeepSeek Harness: Keenable / Exa / Tavily / Firecrawl / AnySearch / TinyFish round-robin with automatic failover. / 均衡搜索插件:六家搜索 API 轮流调用,自动故障切换。
MIT ★ 5 -
Self-hosted search API gateway: aggregate Serper / Tavily / Exa / AnySearch behind one unified API with automatic key rotation, provider failover, circuit breaking and per-key quotas. 自托管统一搜索网关。
npm MIT -
Web search MCP server for AI agents. Google Search grounding via Gemini: answers with cited sources and evidence passages. Self-hosted alternative to Tavily, Exa and Perplexity Sonar. Bring your own Gemini API key. stdio, Streamable HTTP, Docker image on GHCR.
MIT -
webshiftgithub.com/x-hannibal/webshiftupdated this year
Shift noisy web pages into clean, context-ready text for LLMs — Rust library & MCP server
MIT ★ 8 -
Self-hosted search gateway for AI agents. Unified search, news and page extraction with provider fallback. REST API, MCP server and TypeScript library.
npm MIT -
Search, scrape, crawl, and answer with sources, from your own machine. A CLI and MCP server with one optional key: Jev.
Apache-2.0 ★ 3 -
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
npm NOASSERTION ★ 5,544 -
A standalone MCP server for the Web Research Hub — exposes web search, URL fetching, safe calculation, and report export as standardized tools over Streamable HTTP. Callable by Claude Desktop, Claude.ai, or any MCP-compatible agent.
-
Super search is all you need: one query fans out across 9 providers (web, Wikipedia, 7 preprint servers) with a receipt per provider. MCP server + diagnostics webapp; Brave Goggles lenses, paper cards, authorized breaker chain.
MIT ★ 2