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.
-
Unified LLM gateway with multi-provider routing, caching, MCP server, and observability
MIT -
A Model Context Protocol (MCP) server providing unified access to multiple LLM providers with cost optimization
pypi MIT License Copyright (c) 2025 Jeffrey Emanuel -
LLM Security Gateway — AI application firewall, prompt injection risk analysis & sovereign audit runtime.
Apache-2.0 -
Self-hosted LLM gateway that turns flat-rate AI subscriptions (Claude Code Max, ChatGPT Plus, Codex, Copilot, M365, Gemini) into one OpenAI/Anthropic-compatible API. Unified subscription wallet, OAuth passthrough on /v1/responses, prompt-injection + PII defense, MCP server, semantic cache, time-travel replay.
Apache-2.0 ★ 15 -
MCP server providing unified access to Claude Code, Codex, Gemini, Grok and Mistral CLIs with session management, retry logic, and async job orchestration.
go MIT ★ 18 -
llm-guard-gatewaygithub.com/ShreyAC962/llm-guard-gatewayupdated this year
Governance gateway for LLM and agent traffic: blocks prompt injection, redacts PII, enforces per-tenant token budgets, and serves repeat prompts from a semantic cache, cutting served p50 from 44.2 ms to 4.6 ms in the included benchmark. REST + MCP surfaces, offline-first local profile.
MIT -
llm-differential-privacy-gatewaygithub.com/yashmahajan10/llm-differential-privacy-gatewayupdated this year
Noisegate: a differential privacy gateway that lets an untrusted LLM agent query sensitive data over MCP (Model Context Protocol), with a formal guarantee no individual's record can leak even if the agent is adversarial - enforcement lives in trusted code below the model, validated by a runnable attack gallery.
Apache-2.0 ★ 31 -
A specialized RAG gateway providing language models with Cardano blockchain knowledge. Enables AI assistants to access documentation, validate smart contracts, understand UTXO patterns, and discover development resources. Built on the MCP TypeScript SDK. Open-source.
MIT ★ 1 -
claude-india-dpigithub.com/romichandra/claude-india-dpiupdated this year
An enterprise-grade AI gateway framework designed to safely and deterministically scale frontier language models across India's Digital Public Infrastructure (DPI) registries via MCP, Pydantic type-guards, and SymPy validation.
-
ai-security-gatewaygithub.com/etho0/ai-security-gatewayupdated this year
Hybrid AI Security Gateway — rule-based + LLM-assisted (Nemotron + Llama) prompt injection detection + MCP security (rules+policy+AI Assisted)
MIT ★ 2 -
Run Claude Code on any LLM: a Cloudflare Workers AI gateway and LLM proxy that speaks the Anthropic Messages API and routes to Workers AI, OpenAI, Gemini, DeepSeek or Anthropic, with a prompt-injection session guard, red-team harness and MCP server.
MIT -
zero-ai-gatewaygithub.com/vishtechie07/zero-ai-gatewayupdated this year
Zero-Trust AI Gateway: Dual-pass PII redaction (Regex + LLM), real-time security monitoring with Kafka/WebSockets, and MCP-powered compliance auditing for enterprise AI safety.
MIT -
Intelligent gateway for biological samples using MCP, LLM (Ollama), FastAPI, and React. Extracts metadata from natural language, validates it, and submits to BioSamples (EMBL-EBI).
★ 1 -
Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.
pypi Apache-2.0 ★ 17 -
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 -
promptforge-mcpgithub.com/promptforge/promptforge-mcpupdated this year
Prompt Forge MCP server for secure LLM gateway access
pypi MIT License -
Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.
pypi MIT ★ 151 -
LLM gateway in Go: RBAC, quota, multi-layer cache, audit, OpenAI-shaped API, 8 MCP services. 88 tests.
MIT -
rizgithub.com/24X7/rizupdated this year
Self-hosted AWS Lambda runtime — HTTP API Gateway v2 + WebSocket, Bun/Node.js/Python/Rust handlers, built-in MCP server + OpenAI-compatible LLM gateway. Single Rust binary.
Apache-2.0 ★ 3 -
@2kw/ai-mcp-serveractive
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Claude Code, Cursor, and Windsurf.
npm SEE LICENSE IN LICENSE -
llm-hubgithub.com/xordej/llm-hubupdated this year
Self-hosted hub for local & cloud LLMs. Unifies Ollama, Anthropic, Google & OpenAI behind one OpenAI-compatible gateway. Features an MCP server generator, Anthropic skills manager, SQLite-backed chat storage, and a bilingual (UA/EN) UI. Dockerized.
-
AISIX AI Gatewaygithub.com/api7/aisixno update data
Self-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint
oci -
Self-hosted AI API key manager and LLM gateway. Store OpenAI, Gemini, Claude, OpenRouter and Groq keys once, call any model by name. Key rotation, OpenAI-compatible proxy, web dashboard, and an MCP server with sandboxed Code Mode for Claude Code, Cursor and Codex.
MIT -
croit AIplane — one plane for all your AI. Self-hosted AI infrastructure connecting applications and users with models, agents, tools and enterprise data: an OpenAI-compatible LLM gateway, server-side agent execution, MCP, RAG, memory, sandbox, identity, RBAC and quotas. Routes across vLLM, SGLang, Ollama and hosted APIs.
AGPL-3.0 ★ 34 -
Microservices-based API Gateway for weather data, favorites, and alerts, with OAuth2 authentication and LLM integration via MCP.
-
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 -
payhere-agent-docsgithub.com/theepankaja/payhere-agent-docsupdated this year
MCP server & llm.txt for PayHere payment gateway — AI-ready docs for Claude Code, Cursor, Windsurf, Copilot & more
npm MIT -
Official Model Context Protocol (MCP) server for ModelGate: run LLM inference through the ModelGate gateway and inspect models, usage, cost and request traces from Claude, Cursor, VS Code and any MCP client.
npm MIT -
Lightweight, single-binary, production-grade Rust LLM routing gateway & dashboard with health-aware failover, Claude Code compatibility, and MCP server.
Apache-2.0 ★ 4 -
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 -
Open-source, self-hosted AI platform for teams. Run private AI chat, manage Ray/vLLM GPU clusters, and connect apps and agents through an OpenAI-compatible LLM gateway and MCP.
Apache-2.0 ★ 2 -
polybridge-mcpgithub.com/madjeek-web/polybridge-mcpupdated this year
A universal multi-bridge MCP hub connect any LLM to n8n, Blender, Notion and more through a single pedagogical gateway
MIT ★ 6 -
A universal multi-bridge MCP hub connect any LLM to n8n, Blender, Notion and more through a single pedagogical gateway
MIT ★ 4 -
Self-hosted panel gateway for LLMs: ask a collection of models at once, keep every answer side by side, rotate explorer models in, and let your verdicts pick the next panel. OpenAI, Anthropic, Gemini and Ollama APIs, an MCP server, Python stdlib.
npm MIT ★ 1 -
MCP server for Octopus LLM gateway — manage channels, API keys, model pricing, and usage stats via AI. Go-based, Docker-ready
-
GuardBee MCP DB Gatewayno update data
KVKK/GDPR-compliant MCP gateway between LLMs and databases. Automatically masks PII fields (TC kimlik, IBAN, email, phone), enforces role-based table access, rate limits queries, and writes audit logs. Supports Prisma and any database.
smithery -
Next-generation AI/LLM-native proxy for authorized security research: proxy gateway, pool manager, session proxy with capture, multi-IP edge proxy and MCP control. Rust. https://proxyx.dev/
AGPL-3.0 ★ 1 -
Official MCP server for OrcaRouter — the LLM gateway with auto-routing and fallback chains. Browse models and chat from Claude Desktop, Cursor, Windsurf, or any MCP client.
npm MIT ★ 14 -
@hasna/microservicesgithub.com/hasna/microservicesupdated this year
21 production-grade microservice building blocks for AI-native SaaS — auth, billing, LLM gateway, agent registry, RAG, guardrails, tracing, and more. Each with PostgreSQL, HTTP API, MCP server, and CLI.
npm Apache-2.0 -
skillfm-llm-cost-optimizer-mcpgithub.com/ericm1018/skillfm-llm-cost-optimizer-mcpupdated this year
SkillFM gateway MCP for LLM cost optimization and provider usage.
npm MIT -
One API to rule them all. Universal Edge LLM Gateway & Distributed Agent Runtime for 20+ providers. Native MCP Server, SSE streaming, hybrid semantic cache, deterministic flight recorder & zero config.
npm GPL-3.0-or-later -
Multi-tenant operational intelligence platform AI control plane in Go/K8s. Features custom operator, Kafka ingestion, Temporal workflows, MCP LLM gateway, pgvector hybrid search, OpenTelemetry distributed tracing, ArgoCD GitOps, and Redis semantic caching
Apache-2.0 ★ 3 -
MCP Relational AI Gateway 🚀 An elegant, multi-LLM database assistant & dashboard powered by Model Context Protocol (MCP). Interact with MS SQL Server and PostgreSQL databases using natural language, visualize data with drag-to-zoom interactive charts, and switch seamlessly between Google Gemini, Anthropic Claude
★ 1 -
Zero-trust AI control plane: strict stdio MCP server, MCP security gateway (JWT + RBAC), streaming PII guardrail, and a rate-limited failover LLM router, with an end-to-end demo and 348 tests.
-
A gateway service between LLM client and 1C ERP
MIT ★ 5 -
IcyCache - universal LLM gateway with a local cache. I see cache, I burn cache.
pypi MIT -
A secure database access gateway for AI Agents: Empowering LLM (Agents) with database access capabilities.
MIT ★ 6 -
gosce-authenticated-llm-mcp-agentupdated this year
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
pypi MIT -
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 -
Unified local gateway: LLM cache + compressed context drawer, in a single MCP server
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.
-
Teaching MCP server and autonomous agent in Python, using the OmniRoute LLM gateway as a backend
MIT -
api-key-scanner-mcpgithub.com/zhonghp/api-key-scannerupdated this year
Verify LLM API gateway authenticity. Local MCP server, your API key stays on your machine.
pypi Apache Software License -
inferexai-mcpgithub.com/covideoin/inferexaiupdated this year
MCP server for InferexAI — manage your LLM gateway account from Claude Desktop, Claude Code, or any MCP-compatible agent
pypi MIT -
MCP gateway between an LLM and Burp Suite for authorized testing on test and stage environments
MIT -
platformgithub.com/fareboxfun/platformupdated this year
Farebox platform — crypto-native LLM gateway. OpenAI-compatible API, x402 machine payments, MCP server, USDC on Solana.
MIT -
Self-hosted LLM operations gateway in one Go binary: OpenAI-compatible router, durable agent tracker, faithfulness evals + drift, traces, MCP server, console
Apache-2.0 ★ 2 -
brick-bacnet-mcpgithub.com/yveshby27/brick-bacnet-mcpupdated this year
Read-only BACnet/IP gateway exposing Brick + Project Haystack tagged building topology to LLM agents via MCP
pypi MIT License -
@targe/mcp-servergithub.com/pabloleaf/targe-mcp-serverupdated this year
MCP server for the Targe LLM Key Sharing Gateway — use pooled LLM keys from Claude Desktop, Cursor, and other MCP-compatible clients
npm MIT -
Eval-driven SQL reliability for AI agents — generate, validate, safely execute, and regression-test LLM SQL. MCP + FastAPI gateways, execution-truth evals, CI regression gate.
pypi MIT ★ 3