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 descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
meok-mcp-explainabilitygithub.com/meok-ai-labs/mcp-explainabilityupdated this year
MCP server for AI explainability and transparency
npm MIT -
cmd-explaingithub.com/zmwaiworld/cmd-explainupdated this year
Explains CLI commands in one sentence. MCP server for AI coding agents.
npm MIT -
stock-moves-explainedgithub.com/justhappened-corp/stock-moves-explainedupdated this year
MCP server for AI-powered stock movement analysis - explains why US stocks moved
NOASSERTION ★ 1 -
@indiekitai/pg-explaingithub.com/indiekitai/pg-explainupdated this year
PostgreSQL EXPLAIN ANALYZE in your terminal. The only CLI/MCP alternative to web-based visualizers.
npm MIT -
@tac0de/code-explainer-mcpupdated this year
An MCP server that explains repository structure and file roles in plain language.
npm MIT -
code-explainer-mcpupdated this year
MCP server that renders AI-generated code explanations as beautiful HTML pages
npm MIT -
explain-changes-mcpupdated this year
MCP tool for AI to visualize code changes with inline annotations in VS Code/Cursor
npm MIT -
@thinkhive/mcp-explainergithub.com/abdul-omira/thinkhivemindupdated this year
MCP server for ThinkHive Explainer API v3 - Run-centric architecture with facts vs inferences, deterministic linking, calibrated predictions, and AI agent observability
npm MIT -
Repo_Explainer_MCPgithub.com/Pranavvr/Repo_Explainer_MCPupdated this year
MCP server that gives AI assistants live access to any GitHub repo — summarize, explain files, audit dependencies, and track recent changes in real time.
-
Excalidraw MCP for Claude Code: Claude answers with clean diagrams (notation check, layout pass, legend). Mac app.
MIT -
AI agent that summarizes governance proposals from Snapshot & Agora — enables voter clarity and stores summaries onchain using MCP.
★ 3 -
An explainable AI healthcare system that predicts diabetes risk using ML, MCP, and SHAP-based insights. It delivers transparent, clinically meaningful assessments through a modern microservices architecture, enabling healthcare professionals to make clear, data-driven decisions.
MIT -
🔌 Exposes By [MEOK AI Labs](https://meok.ai) | An over MCP — for AI explainability and transparency reports.
pypi MIT ★ 1 -
Paste a developer error, get the real cause and the fix. Offline, zero-dependency explainers for CORS, ESM/CJS, npm ERESOLVE, ChunkLoadError, Postgres/Supabase DATABASE_URL and Next.js build errors.
npm MIT -
MCP server that lets Claude explain ML model predictions with SHAP: feature importance, per-prediction explanations, what-if analysis and plots. Read-only and works with any joblib model.
-
AI whiteboard animation video generator: turn a topic or script into a narrated explainer video with subtitles. CLI, MCP server, and GitHub Action for faceless YouTube and Shorts automation.
MIT ★ 1 -
Why is this PostgreSQL query slow? MCP server and CLI that reads EXPLAIN output and ranks what to fix. Never connects to your database.
npm MIT -
Anistroph - multi-domain predictive analytics architecture for temporal and non-temporal modeling, explainability, multidimensional evaluation, and MCP-based inference with Claude and AI agents.
GPL-3.0 -
@jkumonpm/regex-tester-mcpupdated this year
Regex Tester MCP server — test, explain, and template regular expressions
npm MIT -
weather-shap-mcpgithub.com/sumayabee/weather-mcpupdated this year
MCP server for 7-day weather intelligence — rain, UV, heat & air quality with real SHAP explainability
pypi MIT -
MCP server launcher for buttery: agent-friendly 2D explainer animations where the scene is a pure function of time.
npm MIT -
@chasca/mcpactive
Chasca MCP server: let Claude, Cursor and other MCP clients make and edit narrated whiteboard explainer videos.
npm MIT -
dataxplan-mcpgithub.com/arikanatakan/dataxplan-mcpupdated this year
Read PostgreSQL EXPLAIN plans for AI agents: bottlenecks, estimation errors, fixes, charts.
pypi MIT ★ 2 -
Explainable Java property-insurance underwriting agent with RAG, deterministic rules, MCP tools, and auditable workflows.
-
Explainable TabPFN predictions using verified row-level precedents, MCP, agents and tamper-evident auditability.
MIT -
Read-only-by-default MCP server for PostgreSQL. Query, introspect schemas, explain plans, health checks.
npm MIT ★ 10 -
@captain_americka/tsiky-mcpactive
Turn your photo into a cartoon character and make short animated explainer videos with your AI assistant, step by step. mcprush.com-0d3539c8f4e5bf31c108bbfc
npm ISC -
Secure read-only MCP server for typed job search, deterministic ranking, explainable matching, adversarial defenses, and audited tool use.
MIT -
KolaVid: remote MCP server, REST API examples and Python/JS SDKs for narrated AI whiteboard explainer videos
MIT -
glingithub.com/akashchatterjee/glinno update data
Exactly explainable classifiers for agents: train, tune, predict, explain on CSV or Excel.
pypi -
Interactive data systems lab and MCP-native runtime copilot for explainability, regression testing, and operational diagnostics.
MIT -
Animated map videos for explainers and Shorts: highlight countries and states on satellite or paper maps, globe dive, camera flights. CLI, MCP server and AI skill.
npm MIT ★ 7 -
Vox-style paper-collage explainer videos from JSON. Real maps, any language, 100% local rendering, MCP server for Claude & AI assistants.
MIT -
Seven kinds of website, one AI agent. A WebMCP-powered interactive explainer where your agent proves what agents do to the web, room by room.
MIT -
Official Model Context Protocol (MCP) Server, Go SDK & Claude Skill for SpeedPainter AI (https://www.speedpainter.org/en) — AI Whiteboard Explainer Video & Speedpaint Generator
-
Recruiting collaboration agent reference implementation: 13 tool calls across 3 scoped agents and 9 structured intents, served over FastMCP (STDIO + Streamable HTTP) and FastAPI, with explainable rule-based matching.
MIT -
AI-powered credit scoring with an explainable LangGraph agent, a FastMCP tool server, LightGBM + SHAP, and a live agent-reasoning dashboard.
MIT -
ATME — Autonomous Technical Media Engine. A local-first Windows studio for narrated, illustrated explainers, external AI direction through MCP, and deterministic rendering.
-
Is this creator worth your time? Deterministic YouTube credibility analyzer with explainable signals, an auditable SHA-384 seal chain, and an MCP agent interface.
MIT -
membraingithub.com/quangdang46/membrainupdated this year
Brain-inspired, local-first memory runtime for AI agents with explainable retrieval, provenance-first storage, and policy-aware memory lifecycles
★ 2 -
Safety observation triage, corrective-action tracking and shift handovers. FastAPI/Postgres workspace, explainable DistilBERT severity, YOLO PPE pipeline, and read-only MCP tools.
MIT ★ 1 -
MCP agent translating natural language questions into explainable, reproducible data insights with built-in quality checks and semantic layer integration.
MIT ★ 2 -
breezemlgithub.com/venomez-viper/breezemlupdated this year
A beginner-friendly, production-aware ML workflow layer for students, analysts, and AI agents. Train, compare, explain, export, and deploy scikit-learn models without the boilerplate.
MIT ★ 3 -
🗄️ Principal Database Administrator (DBA) & Data Architecture MCP Server + Multi-Agent Skill for PostgreSQL & MySQL. Deterministic schema audits, ESR indexing, N+1 detection, EXPLAIN plans & zero-downtime migrations.
-
project-brain-mcpgithub.com/avilashsaha035/project-brain-mcpupdated this year
This is a MCP server which scan your given repo url of github / local project folder and explains you how the codebase works, understand you the architecture of the project, what actually the project does, identify the key files.
MIT ★ 2 -
Python time series forecasting assistant built on skforecast: deterministic decisions, the script that ran, an optional LLM that explains them, and an MCP server for AI agents.
pypi Apache-2.0 ★ 52 -
Explainable, vectorless RAG for AI agents: BM25 + temporal knowledge graph over your files, served over MCP. R@5 0.977 on LongMemEval-S, ~2 ms queries, 0 LLM calls, zero dependencies.
MIT ★ 1 -
nnlensgithub.com/tsuzakiii/nnlensupdated this year
Explain any neural network layer by layer in five linked views — diagram, plain words, math, executed naive code, official implementation. An MCP server + local renderer driven by your own AI subscription; works in any language; explanations grow into a cross-linked library.
pypi MIT ★ 2 -
Read-only MCP server that lets AI assistants diagnose PostgreSQL performance: slow queries, EXPLAIN plans, index advice, locks, and the queries inside database functions. Java 25 · Spring Boot 4 · Spring AI
MIT -
ReelForge: turn a voice recording and one YAML file into finished 1080×1920 explainer videos for TikTok, Reels and Shorts. Visual editor, 62 animated components, English & Arabic captions, MCP + REST for AI agents. Deterministic, local, open source.
Apache-2.0 ★ 2 -
Agentic-BIM-Compliancegithub.com/Prajwalkadam29/Agentic-BIM-Complianceupdated this year
This project replaces error-prone, 2-day manual structural reviews with a 4-minute Agentic AI workflow that parses IFC models for code compliance. It ensures structural safety through real-time 3D visual overlays, explainable reports, and automated "auto-fix" design suggestions.
MIT ★ 1 -
End-to-end ML toolkit automating the complete workflow — data profiling, preprocessing, feature engineering, model selection, training, validation, explainability, drift monitoring, fairness checks, and interactive HTML reporting. Includes a full CLI for zero-code ML pipelines. Python 3.10+.
pypi MIT ★ 16 -
Your Terraform plan, explained — plan explainer, drift narrator, and error decoder. Local-first, BYO-LLM (Anthropic/OpenAI/Ollama), MCP-native.
Apache-2.0 -
Autonomous subscription monitoring system using MCP and LLMs. Detects billing risks, duplicates, budget overruns, and explains them clearly — rules decide, LLM explains.
MIT -
Agentic job-discovery backend: 119 ATS & job-board adapters (Greenhouse, Lever, Workday, JSON-LD), explainable scoring with decision traces, cancellable runs, JobSpy-style search with CSV/JSONL export and Atom feeds, resume-to-job matching with missing skills, a read-only MCP server and optional GPT-6, Claude 5.5, Gemini 4 or Kimi K3.1 enrichment.
★ 102 -
MCP server that turns UK Companies House public data into explainable risk signals — searches, scores and explains company risk for an AI assistant. Free stack: Python, DuckDB, Docker.
★ 1 -
mcp_ml_agentgithub.com/gitmystuff/mcp_ml_agentupdated this year
MCP Tools for Model Metrics and Explainability
-
Rexactgithub.com/nicolasmar91/rexact-mcpno update data
Verify, explain and audit regexes (ReDoS, engine compatibility) offline.
npm -
craftbagno update data
MCP server to list, load, explain, and validate Agent Skills.
smithery -
MCP Server for generating Manim visualizations to explain concepts.
★ 2