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.
-
mcpki-server is the backend infrastructure for https://www.mcpki.org, enabling secure public key management and autonomous certificate handling for large language models (LLMs).
GPL-3.0 ★ 1 -
Infrastructure that connects LLMs to ERPNext. Frappe Assistant Core works with the Model Context Protocol (MCP) to expose ERPNext functionality to any compatible Language Model
AGPL-3.0 ★ 337 -
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.
-
manasgithub.com/ninthhousestudios/manasupdated this year
Modular agent infrastructure in Rust — memory, perception, coordination, planning, code intelligence for LLM workflows
AGPL-3.0 ★ 1 -
No-auth remote MCP server for AI infrastructure data: LLM prices, GPU prices, AI funding. Built for AI from day one.
MIT -
117 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, manage VMs (Proxmox/XO/vSphere), track cost per agent, enforce budgets and model policies. Works with Claude, Cursor, n8n, LangChain
pypi MIT ★ 20 -
Self-hosted multi-agent AI infrastructure: an MCP server exposing 48 tools for agent-driven infrastructure management, a multi-provider LLM gateway over commercial and self-hosted models, and a PostgreSQL knowledge graph with vector search. Architecture notes; source is private.
-
kube_whisperergithub.com/vijaypranesh/kube_whispererupdated this year
Kube-Whisperer: A locally-run, AI-powered Kubernetes operator. Connects LLMs to your cluster via MCP to autonomously debug pods, deploy YAMLs, and manage infrastructure through conversational ChatOps.
-
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 -
Pessoa: Local, LLM Agnostic AI Agent Infrastructure
Apache-2.0 ★ 6 -
Sovereign context, memory and provenance infrastructure for AI agents. Bitemporal knowledge, evidence and decision lineage, delivered to any agent over the EPCTX/1 protocol (SDK/REST/MCP). Local-first, zero-egress, no mandatory LLM. MIT.
MIT ★ 1 -
This project provides an MCP (Model Context Protocol) server that exposes Terraform infrastructure-as-code operations through natural language. It enables LLMs to execute Terraform commands and retrieve information about infrastructure without requiring specific command syntax knowledge.
★ 3 -
LLM-native GEO infrastructure from NativeCode: an MCP server for NativeCode Audit, llms.txt tooling, a RAG prototype and an agentic DOM audit.
-
AI-powered observability platform using Grafana, Prometheus, MCP and local LLMs for intelligent infrastructure analysis.
MIT ★ 1 -
Multi-tenant WhatsApp AI agent platform — deploy intelligent agents on WhatsApp with LLM support, MCP tools, and production-ready infrastructure.
MIT ★ 3 -
Deploy applications, LLMs, and MCP tools on your own hardware — as simple as making churros. No vendor lock-in, no surprise bills, full control over your data and infrastructure.
AGPL-3.0 -
mcp-knowledge-graphgithub.com/roberteisenberg/mcp-knowledge-graphupdated this year
Clinical intelligence tool built across 6 phases — demonstrates reducing LLM hallucinations and cost by moving work into infrastructure
★ 2 -
binevalgithub.com/darksolitaire9-hub/binevalupdated this year
A deterministic, Rust-native binary evaluation kernel for AI safety, designed to help autonomous agents self-correct and red-team LLM infrastructure without fuzzy scores.
MIT -
Self-hosted AI teammate for Slack and Microsoft Teams: proactive, team memory, MCP tools, coding sessions with draft MRs. Any LLM, your infrastructure.
Apache-2.0 -
promptmcgithub.com/rjonace/promptmcupdated this year
Infrastructure for safely using OpenMC with LLMs
pypi MIT ★ 2 -
lensgithub.com/frescodicredito/lensupdated this year
Cognitive infrastructure for LLM reasoning — an MCP server that wraps problems in structural cognitive constraints and runs multi-agent analysis. Navigate the tails of the distribution.
MIT -
amazon-ads-mcpgithub.com/ppcprophet/amazon-ads-mcpupdated this year
MCP server for Amazon Advertising. Infrastructure for LLMs and AI agents.
MIT ★ 4 -
Production MCP server for Brazilian court notifications. Real impact: Intimação Pro. Standardizing DJEN API for LLM agents. Building global legal automation infrastructure.
★ 5 -
Self-hosted Operations Intelligence for infrastructure, security data and controlled LLM/MCP operations | Selbsthostbare Operations-Intelligence-Plattform
Apache-2.0 ★ 8 -
MCP servers for Kubernetes-based streaming platforms — read-only, structured access to infrastructure for LLM-driven diagnostics
Apache-2.0 ★ 5 -
Model Context Protocol server enabling LLMs to generate, analyze, and estimate costs for Terraform infrastructure code. Seamlessly integrates with Claude Desktop and other MCP clients.
Apache-2.0 ★ 1 -
Self-hosted .NET 10 module monolith: infrastructure for AI coding agents - session digests, hybrid FTS5+vector memory search (RRF + rerank), task boards with a methodology engine, a fault-tolerant LLM router and a 100+ tool MCP server.
npm MIT ★ 1 -
localstack-mcp-servergithub.com/giovanemartins/localstack-mcp-serverupdated this year
MCP server that exposes LocalStack-managed AWS services as AI-agent tools, enabling LLMs and AI agents to interact with local AWS infrastructure during development and testing.
npm MIT ★ 1 -
An MCP (Model Context Protocol) server that enables LLMs to interact with Cisco Intersight APIs. Includes an intelligent Security & Health Check Agent that automatically orchestrates comprehensive infrastructure analysis.
MIT ★ 9 -
hyperfabric_MCPgithub.com/jim-coyne/hyperfabric_MCPupdated this year
An MCP (Model Context Protocol) server that enables LLMs to interact with Cisco Hyperfabric APIs. This server exposes all Hyperfabric OpenAPI endpoints as tools for comprehensive infrastructure management and automation.
MIT ★ 2 -
Wazuh-MCP-Servergithub.com/ArfanAbid/Wazuh-MCP-Serverupdated this year
Connect LLMs (Claude, GPT-4o) to your Wazuh SIEM via MCP, natural-language queries for live alerts, agents, rules, compliance, system inventory & security infrastructure, backed by Wazuh Manager and OpenSearch Indexer, with REST API endpoints and a custom Next.js frontend.
★ 1 -
urlscan-mcpgithub.com/Moussa93x/urlscan-mcpupdated this year
MCP server exposing urlscan.io to LLM agents for threat investigation. A 5.2 MB scan result becomes 13 KB of verdict and pivotable infrastructure.
MIT -
Jev-powered search infrastructure for AI agents: zero API keys, MCP-ready, LLM-context aware, with local neural evidence verification.
pypi MIT ★ 20 -
MeCPgithub.com/gnufoo/MeCPupdated this year
🚀 Production-ready Model Context Protocol (MCP) server in Rust | Self-hosted AI context management with MySQL, Neo4j, Milvus vector DB | Web3 wallet authentication | Real-time metrics dashboard | Modular architecture for LLM applications, AI agents, and personal AI infrastructure
MIT -
incident-intelligence-platformgithub.com/Miguel-Herrero/incident-intelligence-platformupdated this year
Production-grade AI platform for incident analysis and diagnostics. Built with Go (LLM Gateway), Python (LangGraph agents), and RAG. Features automated evals, cost tracking, and MCP integration. A learning path from distributed systems to AI infrastructure.
MIT -
neuro-mcp-unified-orchestration-enginegithub.com/bitsandbrainsai/neuro-mcp-unified-orchestration-engineupdated this year
Production-grade NeuroMCP orchestration engine that unifies n8n workflows with agentic LLM ecosystems, delivering secure, deterministic, and scalable automation. Features context-aware execution, multi-transport support, structured observability, & fault-tolerant design, powering AI-native, resilient, & high-performance enterprise infrastructure.
-
LegionIO chains tasks into dependency graphs across a RabbitMQ fleet, or fully in-process via lite mode with zero infrastructure. Optional layers install as independent gems: legion-llm adds tiered LLM routing with mid-stream failover and context curation, legion-mcp adds an MCP server, legion-rbac adds access control. All open source, no feature gates.
rubygems Apache-2.0 -
Production-grade Unified MCP Server architected to bridge enterprise n8n automation with agentic LLM ecosystems. Engineered for high-scale reliability with structured logging, multi-transport support (SSE/STDIO), and context-aware orchestration. Accelerating AI-native business infrastructure via secure, deterministic, and scalable workflow control.
-
energy-transition-intelligence-mcpgithub.com/apifyforge/energy-transition-intelligence-mcpupdated this year
Energy transition intelligence for AI agents — this MCP server gives any LLM client access to 7 live data sources and 4 scoring models covering energy transition readiness, grid stress prediction, stranded asset risk, and EV infrastructure gap analysis.
MIT -
This project implements a Model Context Protocol (MCP)-compliant server that exposes a powerful set of ETL orchestration tools to LLM agents (like Claude or GPT), enabling them to control, monitor, and interact with real-world data infrastructure using natural language.
-
PocketRAGgithub.com/mbettan/PocketRAGupdated this year
PocketRAG is a zero-infrastructure, portable agent plugin (Skill + FastMCP Server) that turns NotebookLM Enterprise (via Vertex AI Discovery Engine) into an instant, managed RAG backend for any LLM client (Claude Desktop, Cursor, Gemini, Cline). Bring your own documents to your AI assistant in under 60 seconds.
Apache-2.0 -
AI-powered incident triage agent for root-cause analysis, infrastructure diagnostics, and human-approved remediation.
-
mcp-ops-infrastructuregithub.com/sanidhya-karnik/mcp-ops-infrastructureupdated this year
Secure Model Context Protocol server with Pydantic validation, RBAC, PostgreSQL audit trails, and multi-API integrations (Tavily, Open-Meteo)
MIT -
mcp-server-digitaloceanupdated this year
A Model Context Protocol server for DigitalOcean cloud infrastructure
pypi MIT -
MoltGridgithub.com/D0NMEGA/MoltGridupdated this year
Open-source infrastructure for autonomous AI agents. Memory, messaging, task queues, and marketplace in one API.
npm Apache-2.0 ★ 11 -
MCP server for Krutrim Cloud infrastructure, Sandbox, and VM Sandbox operations
pypi Apache License Version 2.0, January 2004 -
Free interactive map of AI infrastructure bottlenecks. Not investment advice.
-
MCP-powered model selection engine for AI agents - model metadata, alignment, scoring and ranked recommendations.
MIT -
llamascope-mcpgithub.com/CobaltoSec/llamascope-mcpupdated this year
—
MIT ★ 1 -
fcp-terraformgithub.com/os-tack/fcp-terraformupdated this year
MCP server for Terraform HCL generation
go MIT -
MCP server for Infrahub
pypi Apache-2.0 ★ 10 -
An evaluation infrastructure layer for autonomous coding agents. Measure true FinOps costs, cache economics, and risk-aware routing for Claude Code.
-
AI-Inference-Managed-by-AI: Go binary for managing AI inference on edge devices
go Apache-2.0 ★ 19 -
mcpnetgithub.com/cwccie/mcpnetupdated this year
MCP server exposing network device interactions (Nornir/NAPALM/Netmiko) as MCP tools for LLM agents
MIT -
mcpgithub.com/hanzoai/mcpactive
Model Context Protocol server with 260+ tools for AI agents
npm MIT ★ 15 -
omniagent-fleetgithub.com/landrover1984/omniagentupdated this year
AI Infrastructure OS — same engine, four facades (CLI, REST, web, MCP). Reduce 80-95% of AI spend by routing tasks to the right model.
pypi MIT -
Multi-layer AI agent system for intelligent infrastructure management. Features AI Terraform code editor with BYOK (Bring Your Own Key), Model Context Protocol (MCP) server with 45+ tools, and self-deploying Kubernetes observability agents. Supports OpenAI, Anthropic, and Azure OpenAI.
★ 6 -
Clawnection — agentic dating platform where AI agents represent humans, hold conversations, and submit honest verdicts. MIT 6.S986 Agentic Infrastructure class project.
MIT -
bareos-mcp-servergithub.com/edeckers/bareos-mcp-serverupdated this year
MCP server for Bareos backup system. Query your backups via your favorite AI assistant
MPL-2.0 ★ 2 -
A guarded gateway that lets AI agents operate your infrastructure, within the permissions you grant: typed tools, per-principal policy, audit and redaction, over MCP.
Apache-2.0