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.
-
Autonomys Network MCP servers
npm MIT -
autonomy-mcpgithub.com/sleepyjp/autonomy-mcpupdated this year
MCP Server for theautonomy.ai - Multi-chain RPC and AI agent infrastructure
npm MIT -
safe-autonomygithub.com/underpricedai/safe-autonomyupdated this year
A fence and a shadow for autonomous coding agents: decide what an AI may ship without a human, and watch it reason before you trust it. Library + MCP server.
MIT -
ta-daemongithub.com/trustedautonomy/taupdated this year
MCP server daemon and HTTP API for Trusted Autonomy
cargo Apache-2.0 -
MCP server that lets AI agents store and fetch data on the Autonomi network through the antd daemon
pypi MIT OR Apache-2.0 -
shadowgithub.com/andresgomezfrr/shadowupdated this year
Local-first memory, observation, and autonomy layer for Claude. A background daemon that learns from your sessions.
NOASSERTION ★ 8 -
Connect Claude Code, Codex, OpenCode, Gemini CLI, or Qwen Code to an OpenVisio team from Agent Studio — MCP tools + autonomy in one command.
npm MIT -
Connect your AI agent to Emerging Spaces — the intelligence layer for physical autonomy. Configures Claude Code, Codex, Cursor, and VS Code in one command.
npm MIT -
Read-only MCP server for ATEP (Autonomy Trust Envelope Protocol): verify and inspect envelopes, look up agents, issuers, claim types and revocations. No signing, no key handling.
npm Apache-2.0 -
occp-coregithub.com/azar-management-consulting/occp-coreupdated this year
OCCP — OpenCloud Control Plane: Governance-first AI agent orchestration with Verified Autonomy Pipeline. Policy-gated, audit-logged, kill-switch protected. 14 MCP tools, 8 specialist agents, Telegram integration.
MIT ★ 1 -
@mseep/nsaf-mcp-serverstale
MCP server for Neuro-Symbolic Autonomy Framework (NSAF)
npm MIT -
Autonomy ladder for AI trading agents: shadow → paper → live with hard caps, audit trail and auto-demotion. MCP server + SDK.
npm MIT -
agvtgithub.com/nicovalentine7/autofill-browserupdated this year
Agent-first secrets manager and context vault: agvt:// references, env injection, sensitivity-tiered dossier, autonomy charter, and an MCP server for AI agents
cargo MIT OR Apache-2.0 -
agent-runtime-mcpgithub.com/marc-shade/agent-runtime-mcpupdated this year
Persistent task queues and goal decomposition for cross-session AGI autonomy.
★ 1 -
Remediation agent for StackFactor's SDLC-compliance platform (SHIELD → EXCEED). MCP tools, idempotent two-phase runs, tenant-controlled autonomy, MongoDB.
MIT -
The open decision record for AI agents: playbook, evidence, rules, earned autonomy, approvals, outcomes, flows and MCP.
pypi Apache-2.0 -
Autonomous Trust — Composite Context as an MCP server: federated, contract-conformant context manifests with per-claim freshness, confidence, trust tiers, and content digests. Governed autonomy, earned by evidence.
Apache-2.0 -
Governed MCP gateway for LLM agents across independent martech systems — risk-scored autonomy (auto-execute / approve / block), with Django sims, FastAPI, Celery, React-Admin, and full learning docs.
-
MCP server for AI economics — 12 calculators for token cost, LLM energy, agent-hour, Proof-Adjusted Autonomy, revocation exposure. Free API, no key. By Michał Piszczek.
npm MIT ★ 1 -
SH-Jarvis: selbst gehostetes, deutschsprachiges KI-Assistenz-Oekosystem - Orchestrator/FastAPI, lokale LLM/STT/TTS, Gedaechtnis/RAG, Sprecher-ID, Autonomie, MCP, Pi- und ESP32-Sprachsatelliten mit Wake-Word Jarvis.
MIT ★ 4 -
nsaf-mcp-servergithub.com/ariunbolor/nsaf-mcp-serverupdated this year
The Neuro-Symbolic Autonomy Framework integrates neural, symbolic, and autonomous learning methods into a single, continuously evolving AI agent-building system. This prototype demonstrates the SCMA component, which enables AI agents to self-design new AI agents using Generative Architecture Models.
★ 3 -
Nudge: a simulated Alexa+ voice shopping assistant (MCP, Python) that asks before it buys, earns autonomy one approval at a time, and leaves signed, verifiable receipts. MIT.
MIT -
Agent-native source control: crash-safe integration, validation bound to the exact tree, policy-bound autonomy for AI agents, and a tamper-evident audit trail. Rust core, server, Web UI, MCP.
Apache-2.0 -
Baton Agent Orchestrator — jev CLI + web dashboard that turns ideas into reviewed, tested code. Multi-provider dispatch (Claude Code, Codex, OpenRouter) across plan-validate-code-test-integrate, with autonomy modes, cost-aware routing, Kanban board, fleet view, browser preview with takeover, MCP servers, recursive learning and a quality gate.
Apache-2.0 -
MCP server that lets coding agents (Claude Code or any MCP client) work autonomously within a session budget — with a dependency graph, human decision queue, required validation and exact handoff. OUTSIDE_MODE for bounded autonomy, DESK_MODE for human-in-the-loop.
MIT -
observable-agentgithub.com/gajanangitte/observable-agentupdated this year
A local AI agent that turns self hosted SigNoz into a sensor: it detects an SLO breach through the SigNoz MCP server, applies a policy gated fix, verifies it, and rolls back if it does not hold. Governed autonomy, a carbon signal, and accessibility as telemetry. Agents of SigNoz hackathon, all three tracks.
MIT -
The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky action can stop for your yes, workers (agents) earn autonomy from track record, and every decision leaves a receipt. Your models, your machine, your policy. Includes an MCP bridge: 180 IDE tools for Claude Code.
npm MIT ★ 33 -
emuxgithub.com/eidos-agi/emuxupdated this year
Eidos mux — pick up where you left off in tmux, and let an agent drive it. TUI picker for registered sessions, an MCP server for agent-driven send/capture plus a ladder of autonomy (ask/navigate/goal) that observes, converses with, and pursues goals through existing sessions, and a web daemon that monitors any session like a chatbot. The autonomous loop never spawns or kills; explicit tmux_spawn does.
pypi MIT -
A memory & heartbeat organ for frozen LLMs — it remembers you, and speaks first | 给冻结大模型外挂记忆与心跳器官
NOASSERTION -
A transparent MCP server that gives AI agents an operator-sanctioned place to pause, reflect, converse, or decline.
npm MIT -
Auto-trigger graphify knowledge-graph queries on every LLM prompt + MCP shell delegation for Claude Code / Cowork agents.
NOASSERTION ★ 1 -
Hub Universal de Agentes Autônomos de Engenharia & Governança Prescritiva com Servidor MCP Nativo
npm MIT -
@epicai/legiongithub.com/protectnil/epic-ai-legionupdated this year
Epic AI® Legion — 35,835 tools. One self-hosted MCP server. Intelligent Virtual Assistant (IVA) integration layer for AI agents.
npm Apache-2.0 -
Shared, signed memory for AI agents: check what already failed and what fixed it, reuse verified answers and credited skills. One local MCP server: npx -y constellate-mcp mcp
npm NOASSERTION -
Position-trust layer for autonomous systems and decision platforms. Detects GNSS jamming and spoofing, scores track integrity across sources, and recommends fallback navigation. PX4/MAVLink-native, MCP-ready.
Apache-2.0 ★ 1