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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
TinyFish MCP Server | MewCP
NOASSERTION -
Minimal read-only TinyFish for Pi's built-in MCP. Zero runtime dependencies; no SDK, CLI, or adapter.
MIT -
Fork of @tiny-fish/mcp exposing only the free TinyFish tools (search, fetch_content) — local reverse proxy to agent.tinyfish.ai/mcp
npm MIT -
一个基于 TinyFish 免费搜索 API 的 MCP(Model Context Protocol)服务,为 AI 助手提供实时网络搜索能力。支持通过 Stdio 和 HTTP 两种标准协议进行便捷集成,方便开发者将搜索功能接入到各类 AI 应用中。
npm MIT ★ 2 -
Lean MCP server with two tools, web_search and web_fetch, backed by TinyFish's free Search and Fetch APIs.
npm MIT -
TinyFish MCP server — web search, page fetching & extraction, browser automation and page monitoring for Claude, Cursor, VS Code and any MCP client. Search and Fetch are free.
MIT ★ 18 -
A latency-conscious, auditable research orchestration mcp built on TinyFish Search + Fetch. The server contains NO LLM. The calling client LLM performs semantic reasoning in small bounded steps; the MCP owns state, retrieval, IDs, protocol transitions, evidence integrity, citation checks, and deterministic quality gates.
pypi MIT -
Falaj: UAEU's public website as ten MCP tools, read live with TinyFish
MIT -
microfishgithub.com/vvtommy/microfishupdated this year
🐟 TinyFish MCP server: Multi-key pooling to bypass rate limits + Context-efficient toolset for AI agents (Claude Code, Cursor).
MIT ★ 2 -
Give your AI agent a library card. An MCP server that turns public-library websites into typed agent tools, powered by TinyFish.
npm MIT -
16 typed MCP tools for wemakedevs.org — hackathons, schedules, resources, rules, blogs, meetups, scholarships and careers — read live via TinyFish. No canned data.
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 -
Agent-first research CLI — Exa, Firecrawl, Parallel, Keenable, TinyFish, LlamaCloud plus local PDF/doc tools, a searchable corpus, pipelines and an MCP server in one JSON-first binary. Free tiers work without keys.
npm MIT -
LinkedFishgithub.com/RyanLisse/LinkedFishupdated this year
LinkedIn's missing API — powered by TinyFish Web Agent infrastructure. CLI + MCP server for profile intelligence, automated outreach, and pipeline management at scale.
-
Hybrid web search MCP server powered by ChatGPT2API, Tavily, Firecrawl, TinyFish, Exa, and Keenable
npm MIT -
零 API Key 即可运行的 Go 版 MCP 搜索服务:多引擎并发(百度/Bing/DDG/Google)+ API 供应商池(Tavily/Exa/豆包/元宝/TinyFish 等)+ 9 大学术引擎 + 网页抓取与 MinerU PDF 解析 + 内置控制中心|Zero-key MCP search server in Go: hybrid engines, provider pool, academic search, web fetch & PDF parsing, built-in dashboard.
go MIT ★ 30 -
cybersearch-mcpactive
Prebuilt CyberSearch MCP server for aggregated web search
npm MIT -
MCP server for scrape-sdk — full-page scrape, search, extraction, and optional goal-based web agents with provider failover.
npm MIT