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.
-
langsmith-mcp-server-jsgithub.com/amitrechavia/langsmith-mcp-server-jsupdated this year
A TypeScript implementation of langsmith MCP
MIT ★ 17 -
MCP server for LangSmith observability - traces, prompts, datasets, and experiments
BSD-3-Clause ★ 1 -
Model Context Protocol (MCP) server for LangSmith — inspect traces, runs, and datasets via agent tool calls.
-
Mortgage case pre-assessment agent: ReAct agent, RAG over operational policy, custom MCP case service, traced and evaluated in LangSmith.
-
Enterprise AI knowledge assistant for a (synthetic) commercial bank: LangGraph multi-agent, RLM research agent, Pinecone hybrid RAG, MCP tools, RBAC, guardrails, LangSmith tracing, FastAPI + Streamlit.
-
Multi-agent LangGraph NYC transit planner: supervisor delegating to specialist agents over 3 MCP tool servers (streamable HTTP), Flask SSE gateway, LangSmith evals.
-
agentic-test-generatorgithub.com/Hrushitha12/agentic-test-generatorupdated this year
5-agent AI system using CrewAI, MCP, and A2A Protocol to autonomously generate API test suites from OpenAPI specs — GPT-4o/Claude Sonnet via LiteLLM with LangSmith tracing
-
MCP-powered LLM agent for financial compliance: regulatory lookup, risk scoring, and entity resolution tools, with vector memory, LangSmith-tuned prompts, and human-in-the-loop escalation.
-
Document intelligence service: upload docs, search by meaning, get cited answers from a local LLM (RAG), exposed to AI assistants via MCP. FastAPI, Qdrant, Postgres, Ollama, sentence-transformers, LangSmith.
-
docwise-agenticgithub.com/rakmohan/docwise-agenticupdated this year
Full agentic RAG pipeline: adaptive chunking → Qdrant hybrid search (semantic + BM25 + RRF) → LangGraph ReAct agent → grounded answers with citations, streamed live. Multi-turn conversation, multi-hop reasoning, human-in-the-loop, LangSmith tracing, MCP server. LLM-agnostic — works with Claude or OpenAI.
MIT -
gosce-llm-orchestration-agent-mcpupdated this year
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
pypi MIT -
gosce-llm-orchestration-mcp-agentupdated this year
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
pypi MIT -
mcp-server-customgithub.com/themoizqureshi/mcp-server-customupdated this year
Production MCP server: 3 async tools (job search, salary lookup, LLM resume analysis) for Claude Desktop via stdio. Pydantic structured outputs, aiosqlite, LangSmith tracing.
-
gosce-mcp-native-llm-orchestration-agentupdated this year
Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith tracing.
pypi MIT -
Production-style RAG + LangGraph agent for an AI phone receptionist: pgvector, evals with a CI gate, cost/latency logging, LangSmith, MCP server, FastAPI, Docker
-
MCP server for verifying AI agent claims vs reality — inline grounding-check on retrieval context, swallowed-exception scanner on agent-written code, and multi-turn transcript review for unverified completions + cross-turn contradictions. Sub-second, local, free, MCP-native — the lightweight complement to dashboard-based eval frameworks (DeepEval, Phoenix, LangSmith).
pypi MIT License -
langchain-MCPgithub.com/baixianger/langchain-MCPupdated this year
MCP server for LangChain, LangGraph & DeepAgents knowledge + LangGraph agent debugging (Polly-like)
npm ★ 5 -
AI-Credit-Underwriting-Engine-using-FastMCP-LangGraphgithub.com/SayamAlt/AI-Credit-Underwriting-Engine-using-FastMCP-LangGraphupdated this year
Successfully developed a state-of-the-art AI-driven credit underwriting engine using LangGraph and FastMCP that orchestrates multiple specialized agents to evaluate risk, detect fraud, and generate explainable credit decisions, delivering transparent, auditable, and tailored financial solutions with unmatched efficiency.
Apache-2.0 ★ 6 -
patchbotgithub.com/Samarth1980/patchbotupdated this year
Autonomous DevSecOps Remediation Agent (Python, LangGraph, MCP, Docker)
-
Customer Intelligence Hub: AI Agents for CRM Analytics, Slack & Marketing Automation | LangGraph & MCP
★ 2 -
CLI developer workflow agent — LangGraph + custom MCP server, Groq, Docker shell sandbox (allowlist, no network, read-only project, writable scratch only).
-
Built a 5-stage multi-agent workflow (Triage, Document Verification, Fraud Analysis, Decisioning, Compliance Auditing) with guardrails for input sanitization and PII redaction.
-
AI-коуч для фитнес-платформы Tulpar: агент на LangGraph, где изменения программы утверждает тренер. MCP-сервер, Skill, RAG, евалы. Финальный проект nFactorial
-
RAG proof of concept: hybrid retrieval (pgvector HNSW + lexical RRF), cross-encoder reranking, dual embeddings (OpenAI + local GPU/CPU), and an MCP server — Python, PostgreSQL, Docker (NVIDIA/ROCm)
-
evidence-enrichment-enginegithub.com/tinnlo/evidence-enrichment-engineupdated this year
Replay-first evidence enrichment pipeline with hierarchical retrieval, schema-validated typed extraction, AI FinOps cost governance, execution policy capability control (off|audit|enforce), Langfuse-first observability, optional LangGraph retrieval, and MCP tooling.
-
Ai_chatbotgithub.com/adityakumarprasad/Ai_chatbotupdated this year
AI Chat Workspace powered by Next.js and FastAPI. Features persistent PostgreSQL LangGraph checkpointers, multi-document RAG context searches via FAISS, and a custom GitHub MCP (Model Context Protocol) tool server using Gemini AI.
-
hitl-support-agentgithub.com/Ranjith36963/hitl-support-agentupdated this year
Production-grade Human-in-the-Loop customer support agent — LangGraph + real Gmail + real Slack + 3 capability-isolated MCP servers + v3↔v4 multi-agent head-to-head eval. Honest about its limits.
MIT ★ 3 -
A fork of the ShopSmart Customer Support Multi-Agent System that benchmarks 10 inter-service communication protocols (REST, GraphQL, gRPC, Webhook, WebSocket, MQTT, AMQP, SOAP, MCP, A2A) side by side
-
An intelligent Model Context Protocol (MCP) server for Azure AI Search integration with Claude Desktop - Transform enterprise document search into natural AI conversations using LangGraph workflows, Google Gemini, and advanced retrieval-augmented generation (RAG).
MIT -
Noesisgithub.com/chetan0220/Noesisupdated this year
Noesis is an AI‑Powered Data Analysis Platform which streamlines data science workflows by combining Large Language Models with the Model Context Protocol (MCP). It offers automated exploratory analysis, data transformation, data cleaning and data vizualization
★ 1 -
Bridging Generative AI and Classical ML. A production-grade multi-agent system using ReAct orchestration, MCP, A2A, and LMMs for hyper-local property valuation with Evals.
★ 5 -
A LangGraph multi-agent system where 4 AI agents autonomously research any topic, extract insights, write a report, and self-review with a conditional revision loop — powered by Groq (LLaMA 3.3 70B), FastAPI, React, and Supabase.
★ 3 -
The-Autonomous-Merchant-Growth-Agentgithub.com/ben854719/The-Autonomous-Merchant-Growth-Agentactive
An agentic AI that improves merchant performance through an Observe, Diagnose, Decide, Act loop, analyzing key signals to compute KPIs, detect bottlenecks, and generate high‑impact actions like pricing updates, product page fixes, discounts, and inventory alerts.
Apache-2.0 -
System-Stability-and-Performance-Analysisgithub.com/ben854719/System-Stability-and-Performance-Analysisupdated this year
The application workflow leverages AWS Lambda and Agentic AI to diagnose app issues—like network instability or expired tokens—with RS256 authentication. Smart recovery and crash-aware restart maintain user continuity, delivering a secure and reliable experience.
Apache-2.0 ★ 2 -
Autonomous-Security-Orchestration-Layergithub.com/ben854719/Autonomous-Security-Orchestration-Layerupdated this year
ACIS is a self-evolving cyber-immune system that uses telemetry and diagnostics to provide real-time, context-aware defense. Within seconds, it deploys digital antibodies, verifies each action with RS256, continuously simulates risk, and autonomously adapts to emerging threats.
Apache-2.0 ★ 1 -
Mission-Readiness-Scoring-System-Simulation-And-Diagnosticsgithub.com/ben854719/Mission-Readiness-Scoring-System-Simulation-And-Diagnosticsupdated this year
A spec‑driven readiness system using simulation, diagnostics, and agentic AI to produce explainable insights. Outputs include rule paths and RS256‑signed records. It models workload and risk to score readiness, surface bottlenecks, and improve clarity and consistency.
Apache-2.0 ★ 1 -
An Agentic Retrieval-Augmented Generation (RAG) system leveraging LangGraph for workflow orchestration, MCP for tool integration, and PostgreSQL/pgvector for hybrid information retrieval. It dynamically routes queries across document management, database operations, local document search, and web search, with LLM-based relevance refinement to impro
Apache-2.0 -
Hallucination guardrail for AI output about indexed documents. POST a claim, get PASS or FAIL with the exact source passage, checked by a Researcher + Critic LangGraph pipeline (LangChain, Pinecone, GPT-4o). FastAPI service on Render, plus an MCP server, Streamlit UI and eval harness.
MIT -
A lightweight agentic RAG-style chatbot and Model Context Protocol (MCP) server that answers questions about LangChain using local vector retrieval, real-time `llms.txt` document resolution, and Corrective RAG (CRAG) context quality evaluation. Built with LangChain, Chroma, Ollama, FastMCP, and Streamlit.
MIT