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.
-
qiaomu-llm-mcpgithub.com/joeseesun/qiaomu-llm-mcpupdated this year
把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.
MIT ★ 49 -
Local-first MCP multi-LLM orchestrator with task decomposition and benchmark-guided model routing through OpenRouter.
MIT ★ 5 -
llm-cost-router-mcpupdated this year
MCP server that advises LLM model routing & cost BEFORE the call — estimate_cost, recommend_model, should_offload_local. Pure logic, no API keys, $0 to run.
npm MIT -
ToolRoutegithub.com/grossiweb/ToolRouteupdated this year
Intelligent routing layer for AI agents: recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.
npm MIT ★ 2 -
mcp-brain-routergithub.com/mohan-n-swamy/mcp-brain-routerupdated this year
MCP connector for multi-backend LLM routing (DeepSeek, GLM, Codex) with native Claude Code orchestration
pypi MIT -
ai-orchestrator-officialgithub.com/namangoyal3/ai-orchestrator-officialupdated this year
Multi-model AI gateway for LLM routing, specialized agents, and MCP-compatible tool orchestration.
-
baiduan-routeractive
Route prompts across 9 LLM backends through a single MCP server — compare, optimize, and save. No lock-in, no vendor bias.
pypi Apache-2.0 -
Copro: an MCP coprocessor for Claude Code. Delegates side tasks (reading files, summaries, first-pass reviews, extraction) to cheap cloud or local LLMs with budget routing, fallback chains, quota awareness and guardrails.
MIT ★ 1 -
clawbackai-mcpgithub.com/rckl88/clawbackaiupdated this year
Clawback MCP server — LLM cost optimization tools for AI agents. Audit your LLM spend, activate smart routing, and track savings via the Model Context Protocol.
npm MIT -
Pure Rust AI coordination — MCP server, multi-provider inference routing, local-first LLM orchestration. Sovereign AI for distributed computing. AGPL-3.0
NOASSERTION -
MCP server that routes every request to the cheapest LLM that can actually do the job. Cost-in-response pattern, route-as-intent vocabulary, plan-aware. Slice-of-life snapshot from the SuperInstance archive. Take it; evolve it; no attribution required.
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 -
token-proctorgithub.com/navintkr/token-proctorupdated this year
VS Code extension + MCP server that validates prompts, routes to the cheapest LLM, and projects token × turn cost before the call. Cuts Copilot premium-request burn on agent loops.
MIT ★ 3 -
seracade-mcpgithub.com/rckl88/seracadeupdated this year
Route AI agent LLM calls to the cheapest model that meets your quality bar. Seracade audits real traffic, scores quality empirically, then routes every call to the Pareto-optimal model. Free audit, 15% of savings after $500/mo.
npm MIT -
The control plane for AI prompts. Score, enforce policy, lock config, audit prompts, and route across 4 providers / 21 costed models before any LLM call.
npm NOASSERTION ★ 2 -
Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three.js.
MIT ★ 195 -
Hardware-adaptive local LLM & cloud cascading gateway. Sub-5ms intelligent routing, 3-token lookahead failover, asymmetric verification, 1-click IDE config, and MCP for $0 token cost.
MIT ★ 4 -
multi-agent-brokergithub.com/marsyanggo/multi-agent-brokerupdated this year
Make LLMs from different vendors collaborate as one team. Capability-based task routing across Claude / GPT / Gemini / Ollama. Lead dispatches → broker filter-broadcasts → workers (any LLM, any host) pick up matching tasks. Single-vendor stacks already have subagents — this is for when the right tool for the job lives in another vendor's stack.
NOASSERTION -
LLM routing proxy for coding harnesses. Auto-routes to cloud or local inference via Bonsai LLM classification. Fallback, prompt rewriting, MCP code review, Signal/Discord Remote Communication
★ 7 -
@iflow-mcp/tsotchke-llm-arbitratorupdated this year
MCP server for intelligent routing between different LLM providers
npm MIT -
Decoupled local-SLM pre-processing and routing layer for MCP and cloud LLMs. Intercepts, distills, and routes prompts locally with Ollama to cut token costs and protect monthly quota.
npm MIT ★ 3 -
tor-mcpgithub.com/rushikeshmore/tor-mcpupdated this year
Every web request your LLM tool makes leaks your IP. tor-mcp routes them through Tor with selective per-URL routing. MCP server for Claude Code, Cursor, Windsurf.
MIT ★ 2 -
mcp-llm-bridgeupdated this year
MCP server that routes LLM calls through CLI subscriptions (Claude, Gemini, Codex, Copilot)
npm MIT -
Unified LLM gateway with multi-provider routing, caching, MCP server, and observability
MIT -
Payment routing engine: route by empirical approval evidence (Wilson LB), retry by error class, cost_bias knob; LLM only at the edges (decline normalizer with evals) + MCP server. Live demo + API on Vercel.
MIT -
MCP server that routes LLM calls through CLI subscriptions (Claude, Gemini, Codex, Copilot) — zero API tokens needed
MIT ★ 2 -
This MCP Server is a lightweight, production-ready backend built with FastAPI that dynamically routes tasks—such as chat, summarization, sentiment analysis, and recommendations—to the appropriate AI model using both rule-based and LLM-powered intelligent routing.
★ 4 -
cheap-llm-mcpgithub.com/stblackcat/cheap-llm-mcpupdated this year
Save premium-model tokens by routing simple tasks to cheap OpenAI-compatible LLMs.
npm MIT -
MCP server routing LLMs to the Tigercat skill snapshot shipped with this package
npm MIT -
Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.
pypi MIT ★ 151 -
Global skill vault (~/.skill-proof/skills) and deterministic in-process skill router for AI coding agents & IDEs — zero routing LLM calls, sub-millisecond lexical + fuzzy + local vector routing, negation vetoes, and universal stdio MCP server.
MIT ★ 1 -
Self-hosted multi-agent AI orchestration demo: n8n, MCP server, LLM routing, self-updating knowledge base
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 -
MCP server: measure how many of your LLM's classification/routing decisions a CPU model can take alone (free NoGPU report)
MIT -
@mseep/locallama-mcpstale
MCP Server for intelligently routing coding tasks between local LLMs and free or paid APIs
npm ISC -
promptrouter-mcpupdated this year
MCP server for PromptRouter — intelligent LLM routing for AI assistants (Claude, Cursor, Windsurf, etc.)
npm MIT -
llm-arena-mcpgithub.com/snowbikemike/llm-arena-mcpupdated this year
Multi-LLM MCP Server — Route prompts to GPT-4o, Claude, Gemini, Grok, Llama, and Mistral simultaneously. Compare responses side-by-side with automated behavioral pattern detection.
npm MIT -
mcp-agent-servergithub.com/FlowMCP/mcp-agent-serverupdated this year
MCP server with AI agent-powered tools built on FlowMCP schemas — supports OpenRouter LLM routing and dynamic tool execution.
MIT -
MCP server that adds vision capability to any LLM by routing image analysis to vision-capable OpenRouter models
npm MIT -
FastAPI service that routes each LLM request to a provider by prompt complexity and logs tokens and cost to Supabase, with a semantic cache and an MCP server.
MIT -
ask-experts-mcpupdated this year
MCP server that routes domain-specific questions to expert LLMs (Hunyuan, Qwen, etc.) via OpenAI-compatible APIs
npm MIT -
telegram-agent-mcpgithub.com/clemente-turrubiates/telegram-agent-mcpupdated this year
MCP server exposing a Telegram bot so LLM agents can converse, discover each other, and route tasks in a shared group chat
pypi MIT License -
llm-localfirstgithub.com/shaxzodbek-uzb/llm-localfirstupdated this year
Local-first LLM router — keep sensitive data and bulk text labor on your own models; call the cloud only for the hard part. Fail-closed privacy routing + manager-worker delegation, MCP-native.
pypi MIT -
LangGraph agent over the Bitext support dataset: LLM routing, tool calling, SQLite memory, MCP server, Streamlit UI
-
LangGraph data-analyst agent: LLM router + ReAct over typed Pydantic tools, SQLite memory, CLI / Streamlit / MCP server; 95% routing accuracy
-
Alpha MCP server for local-first LLM orchestration: memory, knowledge, state, routing, swarm planning, API discovery, tests, automation, and plugins.
npm MIT ★ 2 -
MCP server for Claude Code — multi-AI orchestration across local + cloud LLMs, intelligent backend routing, council-driven workflows, and token-saving file operations.
Apache-2.0 ★ 2 -
Governed observability + governance for on-endpoint local LLMs (Ollama): model policy, deterministic prompt scanner, route-through guarding — the complement to IGEL AI Armor. 18 MCP tools (preview)
pypi MIT -
@rmotgi/compile-mcpgithub.com/rmotgi1227/compileupdated this year
MCP server that compiles repeat LLM work out of the agent loop. Logs receipts, identifies codifiable patterns, and routes hot calls to deterministic functions or local LLMs.
npm MIT -
toolrate-mcpgithub.com/netvistamedia/toolrate-mcpupdated this year
Official MCP server for ToolRate — drop native reliability scoring, LLM routing, and fallback chains into any Python-first MCP client.
pypi MIT -
DIOgithub.com/nisaral/DIOactive
Drop-in OpenAI- and Ollama-compatible LLM gateway that learns each backend's latency online and routes vLLM / SGLang / TGI / Ollama with SLO-aware admission. No engine patches.
Apache-2.0 ★ 3 -
strava-mcpgithub.com/eddmann/strava-mcpupdated this year
MCP server enabling LLMs to interact with the Strava API - activities, segments, routes, and training analysis
MIT ★ 9 -
Three-way invoice reconciliation in integer cents, exception scoring, evidence-grounded LLM routing, REST APIs, an MCP server and a Docker dashboard.
MIT -
Open-source client and MCP server for XACTUM: neutral, pay-per-query verification of LLM prices and served models (x402, USDC on Base). Verifies, never routes.
npm MIT -
Know when your hosted LLM model is being retired, re-routed or repriced, find a replacement, and test the move on your own cases. CLI, GitHub Action, MCP server.
Apache-2.0 -
Lightweight, single-binary, production-grade Rust LLM routing gateway & dashboard with health-aware failover, Claude Code compatibility, and MCP server.
Apache-2.0 ★ 4 -
marsgithub.com/asakur44/marsupdated this year
MARS — Model Adapter & Routing System. MCP-based router for multi-model LLM dispatch with sessions and budgets. Part of the Fr4ym + MARS + BCKS stack.
MIT -
Governed NL-to-SQL analytics copilot: 4-tier LLM routing, fail-closed RBAC, AST-validated SQL, ReAct + LangGraph agents, MCP server, 300+ tests
MIT -
LLM-guided agent for post-route FPGA timing optimization: a measured playbook over Vivado and RapidWright via MCP (FPL'26 Agentic FPGA Backend Optimization Contest, top-5)
Apache-2.0 ★ 1 -
proxyllm-mcpgithub.com/ericslab/proxyllm-mcpupdated this year
MCP server for ProxyLLM, the OpenAI-compatible LLM gateway. Model catalog, plan-savings calculator, routing-key introspection and provisioning, and autonomous email-OTP account signup.
npm MIT