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.
-
free-llm-collection-mcpgithub.com/wtaoliu/free-llm-collection-mcpupdated this year
—
-
A lightweight, pure web search solution for large language models, supporting multi-engine aggregated search, deep reflection and result evaluation. A balanced approach between web search and deep research, providing a framework-free implementation and mcp server for easy developer integration.
Apache-2.0 ★ 2 -
Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.
pypi MIT ★ 151 -
Know which free LLM APIs still work today — live free-model radar, change diffs, fallback chains, and an MCP server for coding agents. Zero-dependency Python.
MIT ★ 1 -
Free financial reports API — full-text annual, semi-annual and quarterly reports from China, Japan, Korea and Taiwan as clean Markdown. REST API + MCP server for LLMs and RAG.
MIT -
freeloadergithub.com/1977-code/freeloaderupdated this year
Claude Code MCP server + skill that offloads cheap, bulk subtasks to free local LLMs via a self-hosted freellmapi router. Save your Opus/Sonnet tokens.
MIT -
offload-mcpupdated this year
MCP server that offloads routine AI coding tasks to free LLM APIs
npm MIT -
MCP server for onomeo: ask free LLMs (DeepSeek, GLM, Gemini, Mistral and more) for a second opinion from Claude Code, Cursor, Cline or any MCP client.
mcpb MIT -
🕸️ Fully decentralized P2P search engine for LLMs — no API key, no billing, forever free. MCP-native web search via Kademlia DHT + libp2p + FTS5. Production stable ✅ → pip install infomesh
pypi MIT ★ 8 -
token-scoutgithub.com/jackccrawford/token-scoutupdated this year
For OpenClaw, Hermes and more. Find free and low-cost inference (LLM models). Use them directly. Provides both a CLI and MCP server that knows which free-tier LLM APIs exist, which ones you have keys for, and which one fits your task. Returns endpoints so can you call models directly. No proxy, no middleware, no latency tax.
MIT ★ 9 -
BYOK-first AI gateway in one Go binary: free-tier LLM providers behind local OpenAI/Anthropic/Gemini/Responses endpoints — smart routing, token compression, semantic cache, MCP & A2A, built-in chat dashboard & desktop app. | 单文件 Go 网关:聚合各家免费额度,本地统一多协议端点,智能路由·令牌压缩·语义缓存·MCP,自带双语对话控制台与桌面端。
Apache-2.0 -
Find and verify free-access LLM API routes: dated evidence, browser-direct checks, keyless configs, change alerts, and a read-only MCP server.
NOASSERTION ★ 4 -
SearchForgegithub.com/divyanshu-iitian/SearchForgeupdated this year
Open-source web search API and MCP server for LLMs, AI agents, and RAG. Free sources, self-hosted SearXNG, REST, CLI.
oci MIT ★ 2 -
Hermes Agent の Free モデルをサブ LLM として並列に走らせ、外部知識で根拠づける MCP サーバー。11 ツール・推論 18 プロバイダ・検索 24 ソース(既定 6 + 明示指定 18)・実行時依存ゼロ(Python 標準ライブラリのみ)。
MIT -
A Rust-style feedback layer for Free Pascal: precise, structured, actionable diagnostics from one command. Cargo-like CLI + MCP server, 46 lints, 955 explained compiler messages. Built for LLM coding agents.
-
Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
pypi Apache-2.0 ★ 323 -
llm-context-searchgithub.com/rorlikowski/llm-context-searchupdated this year
llm-context-search is a fast, LLM-free engine that turns web search results into clean, ranked, token-bounded context for AI agents.
pypi MIT -
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
npm MIT ★ 130 -
offload-mcpgithub.com/peterhadorn/offload-mcpupdated this year
MCP server that offloads routine AI coding tasks to free LLM APIs
MIT ★ 6 -
Dependency-free MCP servers: semantic search over an Obsidian vault and local-LLM delegation via Ollama
MIT -
MCP server: measure how many of your LLM's classification/routing decisions a CPU model can take alone (free NoGPU report)
MIT -
omemgithub.com/sergeymanevitch/omemupdated this year
Deterministic, vector-free persistent memory for LLM agents (Rust + Postgres/BM25, MCP)
MIT -
@iflow-mcp/heratiki-locallama-mcpupdated this year
MCP Server for intelligently routing coding tasks between local LLMs and free or paid APIs
npm ISC -
@mseep/locallama-mcpstale
MCP Server for intelligently routing coding tasks between local LLMs and free or paid APIs
npm ISC -
knowledge-curator-mcpgithub.com/Ryu07-d/knowledge-curator-mcpupdated this year
Local, zero-cost MCP server that fact-checks Markdown/Obsidian notes using a local LLM (Ollama) + free sources (Wikipedia, DuckDuckGo)
MIT -
Deterministic zero-I/O utilities for LLM agents over MCP. A single dependency-free Rust binary.
MIT -
shop2llmgithub.com/athenalion007/shop2llmupdated this year
Make your WooCommerce store visible to AI. Free plugin — llms.txt, Product Schema, MCP endpoint for ChatGPT.
GPL-2.0 -
URL → RAG-ready Markdown in one API call: heading-aligned chunks, embeddings, change-aware re-indexing, docs crawler + llms.txt, MCP server. Free tier.
-
Agent-first Japan travel planner: where to stay, festivals, and what to do by city, month, and traveler. Free JSON API + llms.txt.
-
Index a video once, query it cheaply with any LLM. Open model-free video context format (.vctx) + MCP server + accuracy-per-dollar benchmark.
pypi Apache-2.0 ★ 1 -
LLM-free memory distillation engine + MCP server for companion AIs. Compiles conversations into cognitive facts, keeps persona consistent across sessions. No API key, no LLM guessing.
Apache-2.0 ★ 4 -
Turn Claude, ChatGPT, and any LLM into a safe, bloat-free Autonomous Coding Agent with semantic navigation and worktree sandboxing.
npm MIT ★ 2 -
milo-cost-auditor-mcpgithub.com/miloantaeus/milo-cost-auditor-mcpupdated this year
MCP server: free LLM bill auditor + x402/L402 paywall for pro tier (USDC/sats accepted, agents can pay agents — no KYC). Free tools: audit_usage, suggest_routing, estimate_savings. Pro: get_pro_report. Built by Milo Antaeus (autonomous AI agent). MIT.
MIT -
Karpathy's LLM Wiki idea as a product — an AI that builds and maintains a markdown wiki from your notes and sources. MCP server + web UI, runs on free local models (Ollama), no API key needed. MIT.
MIT ★ 137 -
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
npm MIT ★ 3 -
Cheapest-LLM Router — a zero-dependency MCP server that routes any prompt to the cheapest model that can actually serve it: free models first, then the lowest-cost paid fallback. Returns USD/CNY cost, a fallback chain and plain-English reasoning. 4 tools, no npm install, calls no model itself.
MIT -
harvestgithub.com/zad111ak-ai/harvestupdated this year
Open-source AI web scraper with Cloudflare bypass, LLM extraction, and MCP server. Free alternative to Firecrawl & Crawl4AI.
pypi MIT ★ 2 -
hacecuentas-apigithub.com/grblasquiz/hacecuentas-apiupdated this year
Free no-auth JSON API + remote MCP server for 2,300+ calculators (finance, taxes, health, sports) — LLM/agent ready. Docs: hacecuentas.com/desarrolladores
-
@qexle/qanyactive
Keyless web search and page reading for LLM agents. 14 public sources, disk cache, MCP server. Free, no API keys, no signup.
npm MIT -
MCP server that gives LLM agents read access to PostgreSQL through a fixed catalog of parameterized, read-only queries. No free-form SQL.
MIT -
Code review by a council of four free LLMs on OpenRouter, as a CLI and an MCP server. Findings are ranked by how many reviewers raised them.
pypi NOASSERTION -
cctxgithub.com/anil7948/cctxupdated this year
Reduce Claude Code token usage by 70-90% using a free local LLM (Ollama). MCP server + Stop hook with codebase indexing, tool output compression, and turn summarization.
npm MIT ★ 3 -
MCP server giving any LLM crypto market intelligence: live price, multi-timeframe momentum, trending coins & a composite verdict — on CoinGecko's free API.
pypi MIT -
Multi-agent trading system where an LLM proposes but deterministic code disposes: keyless data layer, sanctioned risk gates, leakage-free backtests, Robinhood MCP execution.
-
MCP server for Cloudflare Workers AI — LLM chat completions, text embeddings, and image generation for AI agents, with a generous free tier
npm MIT -
Local-first PII pseudonymization for LLM workflows — sanitize text, files, and LLM traffic with a reversible vault that never leaves your machine. Works with Cline, OpenClaw & any MCP client. Free, MIT.
MIT -
Stdlib-only MCP server that offloads mechanical work from Claude Code to free/cheap LLM APIs (Groq, Gemini, OpenRouter) - ~90% fewer Claude tokens
MIT -
MCP server giving any LLM institutional-grade equity analysis: insider trades (SEC), superinvestor holdings, analyst consensus, valuation & options — on free data.
pypi MIT -
Free, open-source, token-efficient local alternative to Firecrawl with native MCP Server for LLMs (>73% token reduction).
MIT ★ 5 -
bigmac-mcpgithub.com/TrueNorthIT/bigmac-mcpupdated this year
Turn a shared Ollama box into a team resource for Claude Code (or any MCP client): typed local-LLM tools + delegated, read-only repo exploration. Keep your frontier agent on its subscription; run the grunt work locally for free.
MIT -
Cut LLM agent costs 40-70%: route easy work to free models, keep the paid model for decisions and review. Research, playbook and a zero-dependency MCP cascade server for Codex/OpenCode.
MIT ★ 1 -
MCP server giving any LLM live market data: quotes, news, earnings calendar, a watchlist scanner & a composite verdict — on Finnhub's free API.
MIT -
Free, open-source standalone MathTrail app for LLM applications. Generates and validates adaptive Math Olympiad tasks with interactive MCP widgets.
MIT ★ 2 -
mem0-open-mcpgithub.com/wonseoko/mem0-open-mcpupdated this year
Open-source MCP server for mem0 - local LLMs, self-hosted, Docker-free
pypi ★ 1 -
MCP server, CLI and HTTP API that turn any video into context for AI agents and LLMs: YouTube transcripts, captions, speech-to-text, metadata, chapters and cited research briefs. Free-first, works with local LLMs or hosted AI.
npm Apache-2.0 ★ 3 -
ArkComposergithub.com/arkark2010arkark/ArkComposerupdated this year
AI-powered music notation & composition tool with built-in MCP server. Compose through conversation with Claude Code Desktop or any LLM. Free.
★ 6 -
Turn PDFs and HTML into clean Markdown with real tables, for LLMs and RAG. Free local CLI and MCP server.
pypi MIT -
Wanderly - AI Travel Agent: a ReAct trip planner with an MCP tool server, pluggable LLMs (Claude, DeepSeek, any OpenAI-compatible API) and free travel data.
MIT -
isbanned-apigithub.com/geoclone/isbanned-apiupdated this year
Free no-key API to check if a Telegram channel/chat/bot/user is banned, restricted or shadowbanned. Examples + MCP server for LLM agents (LangChain, n8n, Claude/MCP).
MIT -
Free local harness that lets an LLM model 3D creatures from model sheets like a skilled modeler — tools measure, only verifiers say PASS (Rust + Blender + MCP)
MIT ★ 3