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.
-
MCP server in Go for LLM-powered (Jev) classification of text, local files, and line ranges using custom criteria.
-
MCP server: measure how many of your LLM's classification/routing decisions a CPU model can take alone (free NoGPU report)
MIT -
LLM-based HFACS classification of ASRS aviation incident reports. Includes experimental data processing, classification models, evaluation methods, and MCP server for data access.
NOASSERTION ★ 2 -
Self-hosted Slack knowledge dashboard: LLM classification, quiz generation, schedule tracking, and a scoped platform API/MCP server
MIT -
LLM routing proxy for coding harnesses. Auto-routes to cloud or local inference via Bonsai LLM classification. Fallback, prompt rewriting, MCP code review, Signal/Discord Remote Communication
★ 7 -
Clinical lab results analyzer: deterministic severity classification served over MCP, with LLM explanations that are machine-verified against the facts they were generated from. FastAPI + React + Gemini.
-
Agentic-Multimodal-Expense-Processinggithub.com/uditsanghvi07/Agentic-Multimodal-Expense-Processingupdated this year
Agentic Multimodal Expense Processing (AMEP): End-to-end GenAI pipeline using Multimodal LLMs for zero-shot data extraction from invoice images. Implements an Agentic MCP server for autonomous classification, transforming unstructured documents into structured expense reports in real-time Google Sheets for analytics.
-
Scan C/C++/Go/Python/Java/Rust/etc. codebases and generate directed call graphs with call ordering, conditions, conditional compilation paths, concurrency analysis, and confidence classification. Designed to give LLM agents global-to-local code understanding — first load a compact context pack, then drill into specific functions on demand.
MIT ★ 1 -
SEO Performanceno update data
Post-publish SEO performance MCP. Unifies **Google Search Console, Matomo, GA4, Microsoft Clarity, and AI-citation signals** per URL and emits a **verdict per post** (refresh / expand / merge / kill / double_down / hold) with deterministic reason codes and a 0-1 confidence score. Reporting only — never mutates posts. Works with any CMS via XML sitemap; optional Ghost Admin API integration for richer metadata. ## Tools - **posts.list** — discover posts via XML sitemap, JSON override, Ghost Admin API, or explicit URL list. - **posts.snapshot** — unified 30/60/90-day signal pull across every configured source for one URL. - **posts.decay_curve** — weekly GSC bucket + decay / plateau / growth classification. - **posts.verdict** — rule-based verdict engine: refresh, expand, merge, kill, double_down, hold. - **posts.refresh_brief** — markdown brief: verdict + reasons + numbers + suggested actions. - **posts.cite_loss** — list of LLMs that previously cited this URL but no longer do. - **cohort.report** — verdict engine across a cohort, ranked by verdict priority + confidence. - **gsc.quick_wins** — pages at positions 5-15 with low CTR, ranked by impressions. ## Prompts - **audit_cohort** — run cohort.report and generate refresh briefs for every actionable URL. - **find_quick_wins** — propose query-verbatim title and H1 rewrites for SERP underperformers. - **citation_loss_sweep** — find URLs that lost LLM citations and recover them. ## How it works Each source is best-effort: if its env vars are missing the field is omitted. Returns whatever is available. Optional DuckDB cache layer for historical comparisons. Platform-agnostic — works with WordPress, Hugo, Astro, Next.js, Webflow, Framer, Wix, Squarespace, Substack, Ghost, and any CMS that exposes a sitemap.
smithery -
briefmark-mcpgithub.com/vladyankovenko/briefmarkupdated this year
Universal MCP server for project documentation with smart classification
pypi MIT -
—
MIT ★ 1 -
@theyahia/yandexgpt-mcpgithub.com/theyahia/yandexgpt-mcpupdated this year
MCP server for YandexGPT — completions, embeddings, classification, summarization (Russia)
npm MIT -
sic-codes-mcpgithub.com/jackmmaher/siccodes.co.ukupdated this year
UK SIC code lookup, GICS/ICB mapping and Companies House search for AI agents - a zero-dependency proxy to the hosted MCP server at siccodes.co.uk (8 tools, SIC 2026 aware).
npm MIT -
CLI, TUI, MCP server and web console for the Jev (System One) API via OpenCode
MIT -
Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
cargo Apache-2.0 ★ 46 -
Typed decision tools for AI agents, powered by TypeSafe Jev
pypi MIT -
Zero-shot forecasting, tabular classification, and regression via MCP — exposes Google TimesFM 2.5 and TabFM v1.0.0 to AI assistants. Just attach a CSV and describe what you want to predict.
Apache-2.0 ★ 32 -
Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.
MIT ★ 1 -
mcp-session-insightgithub.com/ArtLjn/mcp-session-insightupdated this year
MCP Server for Claude Code Session Insight — structured data extraction with LLM synthesis guidance
MIT ★ 1 -
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
MIT ★ 49 -
A Swiss Army knife that lets AI agents get the most out of decision models, simply. Typed yes/no, choice and score judgments over MCP, REST and a CLI, to gate and triage agent work. Written in Rust.
MIT ★ 2 -
korgi-vision-ossgithub.com/c0de4un/korgi-vision-ossupdated this year
Open-source, self-hosted platform for distributed image analysis using local Vision LLMs (Moondream 2 / Qwen 2.5). Built with Rust, Axum, and Vue 3.
MIT ★ 1 -
MCP server for TypeSafe AI's Jev: typed yes/no, choice and score answers with act / review / abstain gating.
npm MIT ★ 2 -
RAG Q&A + autonomous triage agent for customer feedback. Built on Gemini free tier with ChromaDB, structured JSON validation, and deterministic routing.
-
Small decision models for your app's yes/no, choice and score questions: CLI, Python and TypeScript clients, MCP server
npm MIT -
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
npm MIT ★ 7 -
MCP server that gives AI agents typed decisions instead of prose: classify, route, score, and flag with calibrated probabilities. npx -y openjev-mcp
npm MIT ★ 1 -
Fast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
npm MIT ★ 8 -
tuimlgithub.com/tuiml/tuimlactive
An open-source agentic ML ecosystem with a clean Python API, MCP server for AI agents, and a community Hub for sharing algorithms, datasets, and models
pypi BSD-3-Clause -
decomposegithub.com/echology-io/decomposeupdated this year
The missing cognitive primitive for AI agents. Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.
pypi MIT ★ 10 -
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code
MIT ★ 4 -
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.
pypi Apache-2.0 ★ 135 -
Copiloto de IA para parceiros de marketplace: classifica 37 mil avaliações reais em PT-BR, encontra os motivos das reclamações e gera plano de ação verificado contra os dados. Agente com tool calling, evals de fidelidade, BERTimbau e servidor MCP.
MIT -
Local-first web research pipeline (multi-lane search, headless rendering, keyless captcha solving, relevance gates, citable Master Guide) + self-learning RAG loop with knowledge-ingestor: search → quality-gate → ingest → permanent offline library. MCP-native: pi, Claude Code, CortexAgent
Apache-2.0 ★ 1 -
Contextual Memory Intelligence for AI Systems - Persistent memory, cognitive tools, and adaptive reasoning capabilities for LLMs (evolved from Clay-CXD)
NOASSERTION ★ 4 -
@morningljn/mcp-session-insightupdated this year
MCP Server for Claude Code Session Insight — structured data extraction, git log collection, and LLM synthesis guidance
npm MIT -
WorldOfTaxonomygithub.com/colaberry/WorldOfTaxonomyupdated this year
1,000+ open taxonomy systems with 1.2M+ codes and 320K+ crosswalk edges. NAICS, ISIC, NACE, HS, SOC, ISCO, ESCO, CPC, UNSPSC, ICD-10/11, Patent CPC, GDPR, and more - all connected. REST API + MCP server for AI agents. Open source (MIT) by Colaberry Inc.
MIT ★ 11 -
An MCP-compliant server and client for chest X-ray classification and segmentation using TorchXRayVision.
-
MCP server for ClickHouse — explore, query, and manage with SQL-classification-based security modes and access-control flags.
npm MIT ★ 3 -
MCP server exposing Koma Gate prompt-injection classification as a tool for AI agents.
npm MIT -
Cheap, confidence-scored question answering over knowledge graphs: each hop is a calibrated classification decision. Library, CLI, and MCP server.
pypi Apache-2.0 -
compliance-shield-mcpgithub.com/mdfifty50-boop/compliance-shield-mcpupdated this year
MCP server for EU AI Act compliance — risk classification, audit trails, evidence generation
npm -
AI support desk built with Google ADK 2.5 — ticket classification, a deterministic resolution workflow with human-in-the-loop refunds, and MCP tools.
-
AI bookkeeping agent (番頭) — automated journal-entry classification, duplicate detection & monthly reports for accounting SaaS like freee. MCP server for Claude. By Synapse Arrows.
npm MIT ★ 2 -
Deterministic prompt injection classification, secret entropy detection, PII redacting, and synthetic dataset bias auditing.
MIT -
Ethics-aware OSINT investigation planning, collection, and risk evaluation, delivered as an MCP server. Classification, risk tiers, hard stops, and defensible documentation — driven by local YAML doctrine.
MIT ★ 9 -
MCP server for GenCC (Gene Curation Coalition): harmonized gene–disease validity classifications across member submitters, with consensus and conflict detection per gene–disease pair.
MIT -
mcp-server-ai-compliancegithub.com/alerterra/mcp-server-ai-complianceupdated this year
AI risk classification under EU AI Act, Colorado AI Act, NIST AI RMF, and ISO 42001
npm MIT -
Model Context Protocol (MCP) server for MQTT: safe, read-only, multi-broker access for AI agents - topic discovery, payload classification, diagnostics. Pre-release.
Apache-2.0 -
🦉 Lekto reads your documents so you don't have to: self-hosted DMS with OCR, explainable classification, hybrid search and an MCP server for AI clients.
GPL-3.0 ★ 5 -
Model Context Protocol server that fronts the open-source accounting suite's deterministic tools: bank-statement and OFX parsing, document classification, workpaper-spec validation, exact money math, and webhook HMAC verification.
Apache-2.0 ★ 2 -
MCP server for NCBI ClinVar: variant clinical significance and gene-level classifications, served from a local SQLite index built from the ClinVar weekly bulk release — not the eUtils API.
MIT -
roshan-fahm-mcpgithub.com/dwin-gharibi/roshan-fahm-mcpupdated this year
Model Context Protocol server for Roshan AI's Fahm (فهم) platform. Supports chat over documents, translation, summarization, text generation, correction, classification, and information extraction across multiple self-hosted deployments.
NOASSERTION -
Human-approved AI triage for a 401(k) service desk: PII tokenization, call-type classification, plan and payroll record checks, routing, and a code-enforced close guard. MCP servers and a an AI agent(Claude).