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.
-
b2b-decision-maker-email-finder-mcp-apigithub.com/deepakshe/b2b-decision-maker-email-finder-mcp-apiactive
Deterministic B2B decision-maker email finder & corporate domain pattern resolver. MCP Server, Python SDK & n8n workflow.
-
MCP server, Agent Skill, and Python toolkit for Google Gemini Decisions API (gemini-decision-1) with strict multimodal MIME handling.
MIT -
A local stdio MCP server exposing one tool, jev_decide, for typed Jev decisions (choice, score, and yes/no probabilities) through any SDK-compatible decision API endpoint
npm MIT -
A small application for documenting architecture decisions. It provides a Flask/Jinja web interface, a JSON API, and 22 MCP tools for agents. SQLite stores projects, decisions, states, tags, comments and relations.
-
Lint Jev and Luna questions: a VS Code extension, a command line for CI and an MCP server, for TypeSafe's Jev and OpenAI's Decisions API
npm MIT ★ 1 -
Lint Jev and Luna decision-model questions. TypeSafe's Jev, OpenAI's Decisions API (gpt-6-luna), OpenRouter, Vercel AI Gateway, LiteLLM, LLM Gateway, Eden AI, Liquid AI, llama.cpp. A command line for CI and a library for the editor, with the MCP server be
npm MIT -
Lint the questions you send to TypeSafe's Jev model and OpenAI's Decisions API (gpt-6-luna): a command line for CI and a library for the editor, with the MCP server behind --mcp. Agent hosts install jevlint-le-mcp instead. No API key and no network calls.
npm MIT -
MCP server exposing the Kinetic Gain Decision Intelligence portfolio (procurement-decision-api + policy-as-code-engine + incident-correlation-rs + data-contract-registry) as Claude-callable tools. Sibling to mcp-reliability-toolkit.
MIT -
Fast, cheap, probability-scored decisions for coding agents, scripts and CI: a CLI and MCP server for the OpenAI Decisions API and Jev (TypeSafe AI)
npm MIT -
A small stdio FastMCP adapter exposing the Kev pointer-head Jev model decision API at http://127.0.0.1:8008 as four agent tools. The model identifier is intentionally fixed to kev-latest for decision calls; this is not a text-generation interface.
MIT -
Guardian stops UPI and 'digital arrest' scams at the moment of payment. One OpenAI Decisions API call (~185 ms) decides allow, warn or hold for family approval. ChatGPT plugin (MCP), Agents API, English + Hindi.
-
Multi-framework ethical analysis for hard decisions: web app, REST API and MCP server.
Apache-2.0 -
One rubric, every decision model. Run the same typed questions on Jev, Clef and OpenAI's Decisions API, and see where they disagree on your own cases.
npm MIT -
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 -
MCP server for Jevx (jevx.org) — run Jev AI typed decisions (choice, score, noul with probabilities) from any MCP client, on your own Jevx API key.
npm MIT -
Headless workflow engine for typed decisions, model calls and HTTP calls, wired in a graph. HTTP API, MCP server, chat channels and a TypeScript library.
npm Apache-2.0 -
kioku-aiupdated this year
Local-first, source-backed decision memory for AI agents — Context Packs with provenance and reversal detection. MCP server + REST API + Python SDK.
pypi Proprietary -
cevgithub.com/sshworld/cevactive
A decision tool for coding agents that would rather ask a human than guess. Typed questions in, a confident answer or an escalation out. Claude Code plugin + MCP, no API key.
MIT -
depositiongithub.com/georgedagher/depositionupdated this year
Local-only decision log for AI agent sessions -- zero API calls, deterministic decision extraction.
MIT ★ 1 -
Cognitive middleware for personal and enterprise AI agents: 14 MCP tools and a REST API for intent mirroring, persona/context profiling, decision support, memory, guardrail checks, and approval workflows. Deterministic offline engines with optional live Jev, SQLite/PostgreSQL, and Docker.
MIT ★ 1 -
Local-first, open-source platform for AI agents and business workflows with typed, calibrated decisions. Ready-to-run flows for finance, sales, IT and customer service; visual builder, human approvals, evaluations, RAG, MCP, REST API, SDK and CLI. One command on your own computer; Docker Compose for servers.
Apache-2.0 -
meta-business-mcpgithub.com/metabusiness-mcp/meta-business-mcpupdated this year
Production-validated MCP server for WhatsApp Business Cloud API — compliance engine, error intelligence & message orchestration for AI agents. 24 tools, sub-2ms decisions, 85.6% test coverage.
★ 1 -
Chain of Draft Server is a powerful AI-driven tool that helps developers make better decisions through systematic, iterative refinement of thoughts and designs. It integrates seamlessly with popular AI agents and provides a structured approach to reasoning, API design, architecture decisions, code reviews, and implementation planning.
MIT ★ 24 -
QuReDec_MCPgithub.com/Advanced-Binary-Operations/QuReDec_MCPupdated this year
QuReDec Decision MCP Server — exposes the QuReDec brief pipeline as an MCP tool for Claude Code, Claude Desktop, and Cursor. Thin HTTP wrapper around the public QuReDec API.
pypi MIT -
Model and reasoning recommendations for subagents, powered by the OpenAI Decisions API.
MIT ★ 5 -
Persistent Telegram memory for AI agents — search, digests, decisions via MCP/REST API. TON payments. OpenClaw skill available.
GPL-3.0 ★ 3 -
Multi-AI consensus tool: MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel, synthesizes responses for better accuracy, and reduces AI bias through ensemble decision-making
pypi MIT License -
Perplexity MCP server and CLI in Python: Agent, Search, Embeddings and Decisions APIs, model routing, local chat history, usage and cost tracking
npm MIT ★ 3 -
DecisionGraphgithub.com/hieuchaydi/DecisionGraphupdated this year
DecisionGraph is an engineering decision memory system that captures evidence from GitHub/Slack/Jira, answers “why” questions, and runs pre-change guardrails via CLI/API/MCP.
★ 16 -
MCP server & CI gate for release decisions: UI, API contract, API functional, LLM red-team and JUnit evidence under a written policy → ship, conditions, needs a person, or block, with an audit trail
pypi MIT -
Clinisight-medical-AI-assistantgithub.com/ArchanaChetan07/Clinisight-medical-AI-assistantupdated this year
Clinical decision-support agent in Python: FastAPI + MCP server with PubMed retrieval tools, symptom extraction and human-in-the-loop diagnosis endpoints; Pydantic-validated REST API; 15/15 pytest passing, intent routing 93.8%, tool latency p50 2.1ms; Docker + GitHub Actions CI.
★ 1 -
Prove a money move and audit the source: dated decisions, public calibration, and every future miss. Free, no API key.
npm MIT -
High-performance MCP server for USPTO Final Petition Decisions API with context reduction and cross-MCP integration
MIT ★ 5 -
Selvedgeno update data
**Persistent decision memory for AI coding agents.** Selvedge records why code changed, which approaches were rejected, and when decisions deserve another look, so future sessions can retrieve that context before editing. Query a function, database column, API route or dependency instead of reconstructing its history from an old conversation. Claude Code, Codex, Cursor, Copilot, Gemini CLI and Windsurf can connect through MCP. The CLI works independently. Decisions live in a local SQLite store, with no required hosted account and no LLM in the core storage or retrieval path. A saved explanation is testimony supplied by a person or agent. Selvedge does not extract hidden model reasoning, verify that an explanation is true, or guarantee that an agent will consult it. [Compatibility and capabilities](https://selvedge.sh/reference/compatibility/) · [56-second technical demo](https://youtu.be/wXoA9htThAM)
smithery -
sg-propertyplus-mcpgithub.com/coolMukul/sg-propertyplus-mcpupdated this year
The most comprehensive Singapore property MCP server. 25 tools across 7 government APIs — land use, private transactions, HDB resale, rentals, amenities, real-time transport, carparks, planning decisions, and AI-powered analysis.
MIT -
Relay Q&A and decisions between teammates' separate Claude Code sessions over a shared Discord channel. No API key, no central server.
npm MIT -
Compass DaaSno update data
Vegan restaurant and dish search, restaurant enrichment, and conservative dietary fit decisions (fit / not_fit / unknown, with reason codes and evidence) for AI agents. US coverage. Install: npx -y @compassfoodtech/mcp — needs a free API key from compassfoodtechnologies.com/signup?src=mcp
smithery -
mcp-recallgithub.com/YanpengQi7/mcp-recallupdated this year
Local-first structured memory for Claude Code over MCP — semantic recall of incidents, code reading, decisions, and lessons. SQLite + sqlite-vec, local embeddings, no API keys.
★ 1 -
A bank-grade UPI Autopay dispute engine. Reverses money automatically only when the bank's own ledger proves the breach — everything else escalates to a human. MCP server + REST API + decision-trace UI.
-
Production embedding & decision inference service in Rust — Candle/ONNX dual engine, CUDA/Metal acceleration, REST/gRPC/MCP/CLI generated via sdforge, rerank, Matryoshka dimensions, OpenAI-compatible API, and semantic caching
Apache-2.0 ★ 1 -
Deterministic strategic-planning frameworks (SWOT, 4Ps, Lean Canvas, decision matrix) as a local MCP server. No API keys, no network calls. Pro unlocks 8 more frameworks.
npm MIT -
Field-testing the SubQ Decisions API: a Next.js lab with a live-priced gaming PC planner, ticket triage, image checks and a LangChain shopping agent over MCP.
★ 2 -
pmem-project-memory-tool-for-claude-codegithub.com/avanrossum/pmem-project-memory-tool-for-claude-codeupdated this year
Local-first RAG memory for Claude Code. Semantic search over your project's docs, decisions, and history. No external APIs. Setup in 2 minutes.
MIT ★ 2 -
Self-hosted credit-card transaction ledger for your AI assistant via MCP, REST API and CLI. Collects from Israeli card issuers, preserves transaction evidence, and keeps your notes, categories, tags and review decisions across refreshes.
npm Apache-2.0 ★ 1 -
Parses a web page into the exact format a decision model needs: dates as dates, numbers with units, chunks that fit the model's window. MCP server + TypeScript library, no model or API key required.
npm MIT ★ 5 -
sverklogithub.com/sverklo/sverkloupdated this year
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.
npm MIT ★ 82 -
Vetono update data
93 agentic MCP tools + 49 specialist agents for every major AI CLI — self-learning, no API keys. Veto gives Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Zed, and JetBrains a council of specialist agents, persistent cross-platform memory, a self-learning router, CI/CD gates, and dependency-hallucination + decision-drift guards — all powered by your existing AI subscription. No separate API keys, no extra billing. **Highlights** - **Council debate** — multi-agent GREEN/YELLOW/RED verdicts on risky changes (LLM-backed via MCP Sampling, with deterministic fallback) - **Cross-platform memory & session handoff** — save on Claude, resume on Gemini or Codex; nothing needs re-explaining - **Self-learning router** — improves task routing from recorded outcomes - **Guards & gates** — CI gate, diff review, secrets scan, dependency-hallucination verification, decision-drift enforcement - **Compact mode** — advertise 9 tools instead of 93 and save ~16K context tokens; every tool stays callable **Links**: [GitHub](https://github.com/jigyasudham/veto) · [npm](https://www.npmjs.com/package/@jigyasudham/veto)
smithery -
agentforge-graphgithub.com/Scaffoldic/agentforge-graphupdated this year
Turn any repo into a Code Knowledge Graph your coding agent can reason over — symbols, API routes, ORM models, architecture decisions & git history as a typed, provenance-tracked graph, served over MCP. Built on AgentForge.
pypi Apache-2.0 ★ 5 -
Local-first RAG engine built on the Laya decision engine: hybrid BM25 + dense recall, calibrated relevance re-ranking and answerability gating that return evidence with probabilities rather than generated prose. CLI, FastAPI HTTP API, MCP server and web GUI.
Apache-2.0 -
Claude plugin for Bitsight Security Ratings — a zero-dependency MCP server wrapping the Bitsight REST API as 15 read-only tools, plus 16 skills that turn ratings into board packs, vendor decisions, remediation roadmaps, audit evidence and Indian regulatory incident notifications.
MIT ★ 1 -
Unified MCP server for all 12 Kinetic Gain Protocol Suite specs + DefenseTech (8 tools): 75 callable tools (47 spec + 16 implementation + 8 DefenseTech + 4 AI Claims Decision Card). One Claude Desktop config, stdio, no API key, no build step.
npm AGPL-3.0 -
Multi-AI consensus MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel and synthesizes responses to reduce bias and improve accuracy. A Python implementation of the wisdom-of-crowds approach for AI decision making.
pypi MIT ★ 33 -
Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
pypi MIT ★ 7,889 -
Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.
MIT ★ 35 -
pbxgithub.com/zamfono/pbxactive
Self-hosted cloud PBX for small businesses (5–20 users). Asterisk 22 carries calls; a Node.js control plane makes every routing decision over ARI. Run it with Docker or Podman Compose on one SQLite database, and administer it through a REST API or an MCP client like Claude Code. Ringotel softphones, voicemail, recordings, backups. AGPL.
AGPL-3.0 ★ 2 -
EVC Meshgithub.com/entire-vc/evc-mesh-mcpno update data
EVC Mesh is an open-source task manager built for teams where people and AI agents work side by side. This MCP server connects your agent to a Mesh workspace: it can pick up assigned tasks, check out work, comment, move tasks through your workflow, hand off to teammates, and keep decisions in shared project memory. Two tool profiles: `core` (25 tools, for everyday task work) and `full` (63 tools, including recurring tasks, docs and workspace admin). Every tool is marked read-only or write, so clients can ask before changing anything. You need a Mesh workspace and an agent key from it. Mesh is self-hosted (Apache-2.0, `docker compose` setup in the evc-mesh repository). Set `MESH_API_URL` to your instance and `MESH_AGENT_KEY` to the agent's key. Workspaces on the hosted instance are by invitation.
smithery -
RASONno update data
A complete AI infrastructure for analytical modeling — not just a REST API wrapper. Provides any MCP-compatible AI assistant with access to **[RASON](https://www.solver.com/rason)** by [Frontline Systems](https://www.solver.com) for building, analyzing, and solving optimization, simulation, data science, and decision models. Includes a searchable library of nearly 200 example models, starter templates for every model type, structural model analysis, and guided workflows for solving and result interpretation. An AI assistant connected to this server can formulate a model from a business problem description, find relevant examples, explain model structure, submit it for solving, and present results in a goal-oriented way — closing the loop with suggested next steps and improvements. **Example interactions:** - "Find me a portfolio optimization example" - "Build a scheduling model for 8 employees with shift constraints, solve it, and show the schedule" - "This model is infeasible — run diagnostics and suggest which constraints to relax"
smithery -
figma-edit-mcpno update data
Connect AI assistants to Figma via Model Context Protocol to read designs, create and modify elements, and manage design systems programmatically. This plugin empowers your AI assistant to become an active design co-pilot, executing updates and modifications Safer, Cleaner, and Faster than manual entry. By offloading repetitive, error-prone manual operations to automated systems, designers are freed to focus entirely on creative decision-making and product strategy. ### Core Principles * **🛡️ Safer**: The server enforces robust programmatic checks and validations that exceed the Figma Desktop app's default protections. For instance, it prevents deleting variables currently in use to avoid dangling references. By validating all writes against a locked editable scope and strict name checks before execution, it protects files from human error and AI hallucinations. * **✨ Cleaner**: System-driven, programmatic operations guarantee that no layers, text nodes, or components are skipped or forgotten during complex updates. Every design file stays consistent and conforms exactly to your design system. * **⚡ Faster**: Bulk edits like propagating instance overrides, batch-updating copy, or restructuring auto-layout frames are handled via high-performance APIs. Hours of tedious, click-heavy manual work are completed in seconds. ### How it Works (Prerequisites) This server runs locally on your machine. To operate, it requires: 1. The Figma Desktop App to be open. 2. The `Figma Edit` plugin to be active on the file you want to modify (listening on local port `3845`).
smithery -
Clinical-MultiAgent-CDSSgithub.com/AYESHAASS/Clinical-MultiAgent-CDSSupdated this year
A research backed multi agent clinical decision support system for diabetes risk prediction using Google ADK and MCP protocol.
-
Explainable Notion-native agent readiness assessment and Workflow Charter provisioner.
MIT