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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
mcp-motor-current-signature-analysisgithub.com/LGDiMaggio/mcp-motor-current-signature-analysisupdated this year
MCP server for Motor Current Signature Analysis (MCSA) — spectral analysis and fault detection in electric motors in natural language through LLMs
pypi MIT ★ 9 -
CodeRadargithub.com/officialCodeWork/CodeRadarupdated this year
React & TypeScript static analysis that maps every UI component to the APIs, state, and events behind it — and serves that context to AI coding agents over MCP. Screenshot or ticket in; component, data lineage, user journeys, and blast radius out. Deterministic, no LLM in the core.
MIT -
Verified commercial audit of a WhatsApp business number: WAHA export, clean corpus, LLM analysis with a mandatory two-layer verifier (34/60 findings refuted in the original run), XLSX/HTML/DOCX reports, MCP server included. Self-hosted.
MIT -
auto-managergithub.com/Maxpeng59/auto-managerupdated this year
Measurement analysis for mechanical test engineers: messy CSV/TDMS/MDF4 in, vibration/fatigue/thermal answers out — CLI, HTML reports, and an MCP server for LLM-driven analysis.
MIT -
Conversational FRC telemetry analysis with built-in guardrails against LLM overconfidence. MCP server for WPILib and REV logs.
MIT ★ 14 -
Play shogi in Claude Code — an experiment in how far an LLM can play using only self-implemented position-analysis tools, no shogi engine hints.
GPL-3.0 -
Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.
pypi NOASSERTION ★ 22 -
Text2SQL data-analysis agent: three handwritten LangGraph orchestrations (deterministic pipeline / autonomous ReAct loop / Supervisor multi-agent with LLM-as-Judge), 4-layer SQL safety, MCP server+client, human-in-the-loop write path with transactional dry-run. 60-case gold benchmark.
MIT -
Static analysis for the debt AI agents leave in PHP: 34 rules, Claude Code hooks, git-diff review, a Rector and Pint fix pass, Pest expectations, CI annotations and an MCP server. Deterministic, local, no LLM.
MIT ★ 231 -
Static + dynamic malware analysis for Windows. Deep static triage (entropy map, multi-stage strings, code patterns, imports, capabilities), then optional dynamic unpacking under x64dbg in a disposable VM: captures the payload, recovers keys, classifies the family, exports YARA/Sigma/STIX IOCs. One PDF per run, driveable from any LLM via MCP.
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 -
Batteries-included MCP server for email — local cache, operation queue with undo, web dashboard, OAuth2 sign-in, LLM analysis. Works with Gmail, Outlook, Yahoo, Zoho, Fastmail, ProtonMail, and any IMAP provider.
MIT -
Node.js RSS and Atom feed parser with agentic analysis, LLM enrichment, heuristic deduplication, and Model Context Protocol (MCP) server tooling. Drop-in rss-parser compatible. Zero-dependency hand-rolled XML parser with SSRF protection, pluggable storage
npm MIT -
OpenLVgithub.com/hafshari/OpenLVupdated this year
OpenLV converts LabVIEW VIs into a textual model and AST using VI Scripting, enabling analysis, pseudocode, UML/dataflow diagrams, fast graphical-to-script transpilation, and AI/LLM insights through a built-in MCP server.
MIT ★ 5 -
Expose Periphery’s Swift dead-code analysis as a Model Context Protocol (MCP) server so Claude and other LLM agents can run scans, guide the interactive setup, and surface build errors in structured JSON.
-
mcp-character-toolsgithub.com/Aaryan-Kapoor/mcp-character-toolsupdated this year
The last thing you need for your LLM to work with individual characters or count the number of r's in a word. This is an MCP server providing 14+ comprehensive (and pretty) character and text analysis tools to help LLMs work with individual characters - something they struggle with due to tokenization.
MIT ★ 3 -
AutoMemgithub.com/WENGKING219/AutoMemupdated this year
AutoMem is an AI agent specifically built for memory dumps forensics. It is built using DeepAgents framework from LangChain with the integration of Volatility 3 plugins in the MCP server. Ollama acts as the local LLM provider to provide privacy first analysis in local offline environment.
★ 1 -
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
go MIT ★ 1,086 -
giorriagithub.com/ryaneoin/giorriaupdated this year
AI-powered network automation lab combining Containerlab, Arista cEOS, and the Model Context Protocol (MCP). Features offline config analysis via Batfish, live telemetry with gNMI/Prometheus, structured audit trails in Loki, TACACS+ accounting, and a unified MCP server giving LLMs natural-language access to all network operations data.
MIT ★ 1 -
Solitarius-mcpgithub.com/lcmd-epfl/Solitarius-mcpupdated this year
MCP server exposing REINVENT4 generative molecule design as LLM-callable tools sampling, transfer learning, staged RL with interactive scoring-function design, custom scoring plugins, and generated-molecule analysis. Runs in Docker with GPU
Apache-2.0 -
Solitarius-mcpgithub.com/pregHosh/Solitarius-mcpupdated this year
MCP server exposing REINVENT4 generative molecule design as LLM-callable tools sampling, transfer learning, staged RL with interactive scoring-function design, custom scoring plugins, and generated-molecule analysis. Runs in Docker with GPU
Apache-2.0 ★ 1 -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
rlmgithub.com/SaschaOnTour/rlmupdated this year
Context broker for AI coding agents (CLI + MCP). Queries codebases via progressive disclosure instead of feeding entire files into context — reducing token waste and context rot. AST-aware retrieval, surgical editing with syntax guard, semantic search. Inspired by Recursive Language Models research (MIT/Stanford, 2025). Built in Rust.
NOASSERTION ★ 2 -
Stockfish + LLM chess coach: an MCP server and web board that explain your mistakes in plain English
MIT ★ 58 -
Use UrbanMapper in an LLM Model Context Protocol (MCP) setting!
MIT ★ 1 -
openfoam-mcp-servergithub.com/webworn/openfoam-mcp-serverupdated this year
LLM-powered OpenFOAM MCP server for intelligent CFD education with Socratic questioning and expert error resolution
NOASSERTION ★ 129 -
@klitchevo/code-councilgithub.com/klitchevo/code-councilupdated this year
Multi-model AI code review server using OpenRouter - get diverse perspectives from multiple LLMs in parallel
npm MIT -
MCP server that lets Claude investigate millions of log lines, metrics and traces in SereneDB. Every number in the answer links to the SQL that produced it.
★ 2 -
TechDebtMCPgithub.com/PierreJanineh/TechDebtMCPupdated this year
MCP server for analyzing and managing technical debt in codebases via the Model Context Protocol
npm MIT ★ 7 -
mcp-sentiment-agentgithub.com/amirhosseinazami1373/mcp-sentiment-agentupdated this year
This project is my first attempt in making a MCP based agent for simple task of sentimemnt analysis.
-
r-stats-mcpgithub.com/Ian3738/r-stats-mcpupdated this year
MCP server for statistical analysis in R: hypothesis tests, regression, psychometrics, survival analysis and time series over a persistent R session
MIT ★ 1 -
美股投研 Agent 原型:通过 MCP 提供行情、SEC 财报检索(RAG 带引用)、财务数据、组合风险和模拟下单工具,下单必须人工确认;内置 Agent 评测(任务成功率、工具调用准确率、成本与延迟)。
mcpb MIT ★ 1 -
pocket_disasmgithub.com/whoisqwerz/pocket_disasmupdated this year
Multi-session IDALib MCP router for coding agents. Analyze multiple binaries in parallel with IDA-compatible reverse engineering tools.
MIT ★ 43 -
csv_analyzer_mcp_servergithub.com/juanmaalt/csv_analyzer_mcp_serverupdated this year
MCP server that enables LLMs to analyze CSV files. Returns structured summaries in JSON or Markdown.
★ 1 -
AI agent drafts QA scores via MCP tools; guardrails validate; humans approve in a review queue. Golden-set eval. Synthetic data.
MIT -
Deterministic AST Safety Guard, High-Throughput Compound Pipelines, Bidirectional Intent Synthesizer, Polyglot Graph & Zero-Dependency MCP Server in Pure Safe Rust.
NOASSERTION ★ 1 -
LangfuseMCPgithub.com/DrishtantKaushal/LangfuseMCPupdated this year
Langfuse MCP server with built-in analytics. 34 tools — traces, observations, sessions, scores, prompts, datasets + accuracy metrics, failure detection, token percentiles, cost breakdowns, latency analysis, context breach scanning. Works with Claude Code, Cursor, Codex.
MIT ★ 2 -
Local-first MCP server that detects potential PHI flows into LLM, logging, and analytics calls in source code.
npm MIT -
Decompile binaries directly in Claude, Cursor & LLMs using Ghidra, Hex-Rays & Binary Ninja via Dogbolt.
MIT ★ 1 -
A statistical analyst in your AI chat. Bring a dataset and a question, get back a citable, re-runnable analysis with its method named. Works in Claude, Cursor, and any MCP client.
npm MIT ★ 9 -
insight-link-progithub.com/Lonishubh48/insight-link-proupdated this year
Hallucination Killer — MCP server that grounds LLM answers in live repo context and real-time docs
★ 2 -
AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec. Analyze any codebase in minutes.
MIT ★ 12 -
An MCP server with a built in lightweight proxy server & DB to capture & analyze network traffic within an AI agent
-
Multi-agent contract scanner that flags clauses that can cost you money in leases and other documents. Every finding is checked against a quote from the source. TypeScript, MCP and Next.js.
-
Answer "what breaks if I change this?" Reverse dependency analysis, cycle detection, and token-budgeted context packs. Rust CLI with built-in MCP server.
cargo GPL-3.0 ★ 78 -
findatamcpgithub.com/hanlinlibham/findatamcpupdated this year
Feed LLMs financial data and interactive charts in one call — an MCP server for A-share quotes, financials, and macro indicators, 42 tools with results-as-UI.
MIT ★ 1 -
sheafgithub.com/sheaf-data/sheafupdated this year
Pinpoint the doc, test, and example gaps in your APIs and CLIs — cited, reproducible, MCP-ready — so coding agents stop guessing.
Apache-2.0 -
🪵 Local log analysis MCP server for AI agents (Cursor/Claude Code). Tail, search, filter, stats & root-cause diagnosis with local Ollama or a built-in rule engine.
MIT -
AI-native code-intelligence engine in Rust — risk-ranked blast radius, PR review targeting, and cross-service call graphs across 13 languages. Runs as a CLI, an MCP server for AI agents, and a resident file-watching daemon.
Apache-2.0 ★ 1 -
The definitive all-in-one Model Context Protocol server for AI-assisted coding across 30+ platforms
npm MIT -
reposense-mcp-edgegithub.com/vityk-dev/reposense-mcp-edgeupdated this year
Give AI assistants deep access to GitHub repos via Model Context Protocol - smart file ranking, stack detection, code search, and 14 built-in analysis prompts. Python + Cloudflare Worker
MIT -
Local, version-exact API index of the packages installed in your Python/TS projects, with a static checker that catches hallucinated or misused APIs in code an LLM just wrote - without ever running that code. FastAPI + React, MCP server included.
MIT -
videoseek-mcpgithub.com/kennyzheng-builds/videoseek-mcpupdated this year
VideoSeek MCP — Find anything in any video. Semantic video search, video Q&A, persistent memory, and social media import for AI agents.
★ 2 -
Give your AI agent full native Windows control via System Informer MCP — inspect processes, services, network, memory & more in C.
NOASSERTION ★ 1 -
MCP server that gives coding agents an accurate call graph of your codebase. Feature-complete as of 1.0.0; in maintenance mode (bug fixes and security updates only, no new features).
cargo MIT -
Native Model Context Protocol (MCP) server embedded in Ghidra 12.1.4 - 70 tools for LLM-driven reverse engineering, vulnerability assessment and binary patching.
Apache-2.0 -
froggy-sregithub.com/froggychips/froggy-sreupdated this year
MCP-based SRE incident response agent for macOS. Feed a Kubernetes alert → get root cause, fix, and risk in one tool call. Native Swift, on-device LLM by default.
-
@iflow-mcp/flesler-mcp-filesgithub.com/flesler/mcp-filesupdated this year
Enables agents to quickly find and edit code in a codebase with surgical precision. Find symbols, edit them everywhere
npm MIT -
clarityaui-mcpactive
Ask any codebase's structure over MCP — deterministic concept map, real dependency evidence, in seconds. Local, offline, no LLM, no API key. `npx clarityaui-mcp <repo>`.
npm SEE LICENSE IN LICENSE -
AI agent toolkit for 1C:Enterprise 8.3 (BSL): rules, skills and MCP servers so the agent works from your real code, plus byte-perfect metadata editing verified in a test base. Docs in Russian.
MIT ★ 36