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 and local operations workspace for AI-assisted IT support. Investigate Windows, macOS and Linux devices over SSH, review repair plans and approve changes with Claude, Codex or other MCP clients.
-
Give Claude Code, Codex and Gemini every machine you have: a live GPU, VRAM, RAM and disk inventory across your servers, SSH access between them, and an MCP server.
pypi MIT -
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
AGPL-3.0 ★ 83 -
fleet-memgithub.com/sam-ent/fleet-memupdated this year
Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination
pypi AGPL-3.0 -
fleet-memgithub.com/sam-ent/fleet-memupdated this year
Shared code intelligence for agent fleets — AST-aware semantic search + multi-agent memory with git-concurrent coordination
AGPL-3.0 ★ 4 -
One API for every agent pod: starts a pod on the cheapest sandbox provider you have a key for, and moves on when one fails. https://fleet.flisk.si
MIT ★ 1 -
Claude agent that finds, fixes and verifies faults in a simulated 100-vehicle fleet through a Go MCP server. Code-enforced write and stale-data checks, a ground-truth eval harness, and a rule-based baseline: Claude 6/6 vs rules 0/6 when the fix is only in the manual.
Apache-2.0 -
@meterapp/meteractive
Command-line client and MCP bridge for Meter, the taxi meter and fleet platform. Sign in with OAuth, query fleets, members, vehicles, trips, bookings, earnings and accounting from a terminal or a CI job, run a stdio MCP server, and generate agent configur
npm MIT -
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Installs caura-client under the caura name.
pypi Apache-2.0 -
Auditable multi-agent coordination for OpenCode — parallel agent fleets with P2P messaging, witnessed receipts, and quorum ratification. Who saw this, who approved it, prove it.
npm MIT -
Wialon MCP server and agent skill — ask your Wialon fleet questions from Claude Code, Codex, Cursor and VS Code. Read-only.
MIT ★ 4 -
Python packages for the ResQ disaster response platform: resq-mcp (FastMCP server connecting AI agents to drone fleets and simulations) and resq-dsa (zero-dependency data structures for search and rescue).
Apache-2.0 ★ 2 -
agent-rate-limiter-mcpgithub.com/csoai-org/agent-rate-limiter-mcpupdated this year
Fleet-wide shared rate limiter for A2A + multi-MCP deployments. Most MCP servers rate-limit independently — a hostile agent hitting 10 MCPs gets 10x quota. This MCP is the shared counter: every MCP checks here before allowing a call. Sliding window + concurrency grants + signed enforcement attestations. By MEOK AI Labs.
pypi MIT License -
ToolsEnabled Fleet: agent fleet management and mediation for Codex and Claude Code inside NVIDIA OpenShell sandboxes. Public source for each published build.
MIT -
Agentguard-github.com/xAPT42/Agentguard-updated this year
Discover and govern your AI agent fleet automatic inventory with risk scoring
Apache-2.0 -
Auditable multi-agent coordination: process fleets, A2A messaging, receipts, quorum councils, and provider-neutral advisory routing. MIT.
MIT ★ 1 -
Inspectable AI agent memory, context engineering and multi-agent orchestration with an MCP server and logical-fleet benchmarks
Apache-2.0 ★ 1 -
agent-costcenter-mcpupdated this year
MCP server for per-agent cost attribution, budget management, and spend analytics across AI agent fleets
npm MIT -
mcp-studiomeyer-agentsgithub.com/studiomeyer-io/mcp-studiomeyer-agentsupdated this year
MCP Server for StudioMeyer Agents customers — read your AI-Audit Fleet data and configure your agents from your own Claude/ChatGPT/Cursor.
npm MIT -
mxgithub.com/pol-cova/mxactive
Build, run, and inspect iOS simulator apps for AI agents. Semantic UI automation, screenshots, logs, and simulator fleets.
MIT ★ 1 -
Fleet-grade local memory for AI agents over plain Markdown — hybrid search, multi-tenant, one process, no cloud, no Docker, no LLM.
pypi MIT -
Fleet-grade local memory for AI agents over plain Markdown — hybrid recall, multi-tenant, one process, no cloud/Docker/LLM
MIT ★ 1 -
MCP server exposing live machine ground-truth (processes, listening ports, daemons, load) to agent fleets — stop guessing what's actually running.
MIT ★ 1 -
agent-mcp-router-mcpgithub.com/csoai-org/agent-mcp-router-mcpupdated this year
Agent MCP Router MCP — one router for the whole MEOK fleet. Holds 62 MEOK MCPs behind one namespaced endpoint. Install ONE thing, get all of them. By MEOK AI Labs.
pypi MIT -
Open-source, self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes — REST, CLI, and MCP.
npm Apache-2.0 ★ 60 -
labby-mcpgithub.com/jmagar/labbyupdated this year
Node launcher for Labby, a Rust homelab control plane and MCP gateway for agents, plugins, registries, and fleet operations.
npm MIT OR Apache-2.0 -
ViloForge KnowledgeBase (vfkb) — per-project knowledge substrate for the ViloForge software factory; the memory engine vfwb and the agent fleet ground against. Greenfield TypeScript, cross-harness auto-layer.
MIT -
MCP Server for StudioMeyer Agents customers — read your AI-Audit Fleet data and configure your agents from your own Claude/ChatGPT/Cursor/Codex.
MIT -
Secure SSH access for AI agents via MCP. Execute commands across your server fleet with policy enforcement, network controls, and comprehensive audit logging.
Apache-2.0 ★ 30 -
The coordination and evidence layer for AI agent fleets: a local-first task board with atomic claims, live Mission Control, cost attribution, audit exports and shared memory for Claude Code, Codex and any MCP harness.
pypi AGPL-3.0-or-later -
model-context-streamgithub.com/thejavapirate/model-context-streamupdated this year
Living, event-driven MCP server: durable context streams, task queue with exactly-once claims, and versioned protocols for AI agent fleets. Self-hosted, MIT.
MIT ★ 1 -
Self-learning memory for AI agents — experience captured automatically, distilled into lessons overnight, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, and Pi.
npm NOASSERTION ★ 3 -
Deterministic software attestation for AI-augmented development — witness, probe, and seal any repo with SHA-256. Fleet registry across 131 VERITAS nodes. Agent-native, zero cloud.
MIT ★ 3 -
kybgithub.com/alex09x/kybactive
Git-backed shared memory for AI agent fleets: searchable knowledge base, incident and task tracking, every write versioned and attributed. CLI, HTTP API and MCP server.
MIT ★ 67 -
Mission control for your agent fleet. One local-first board for Claude Code, Codex, Goose, Cursor and any MCP harness: durable tasks, live activity, cost attribution and audit exports.
NOASSERTION ★ 101 -
Persistent agent identity for AI agents — a hand-edited identity layer, nightly-distilled experience, and lessons injected every session, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, Pi, and opencode.
npm PolyForm-Noncommercial-1.0.0 -
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Apache-2.0 ★ 559 -
Scale parallelism. Preserve alignment. A fleet of coding agents builds one task in parallel against a spec contract; a decision that contradicts one already in force is refused — deterministically, no model in the decision path.
MIT -
The terminal AI agents can drive — and the cockpit to run them from. 151 MCP methods, agent Inbox, git-worktree fleets, diff review & rollback, one-click updates. macOS / Linux / Windows, local-first, free, MIT.
NOASSERTION ★ 19 -
bubbaloopgithub.com/kornia/bubbaloopupdated this year
Open-source Hardware AI agent. Single Rust binary for cameras, sensors, robots, and IoT fleets — orchestrated by AI agents with memory and real-time telemetry. Runs on Jetson, Raspberry Pi, any Linux.
Apache-2.0 ★ 30 -
An MCP server that lets AI agents operate a multi-cluster Kubernetes fleet through an Open Cluster Management hub, with policy, approval, and audit between the model and your clusters.
Apache-2.0 ★ 17 -
Standalone OS filesystem & multi-node SSH fleet RAG MCP server. Indexes PDFs, docs, and system configs in-place—anchoring every agent memory and citation directly to a 1-based KruschNexus page with per-page SHA-256 drift detection and .env secret redaction.
MIT -
RCLL — self-hosted, hierarchical shared memory for a team of AI agents over MCP (rooms, L0-L3 depth, pgvector). Fork of vectorize-io/hindsight.
npm MIT -
RCLL — self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. We publish the measured cost of one shared store versus ten private ones. Fork of vectorize-io/hindsight (MIT).
MIT -
Treat normalized scan findings as immune signals: discover patterns, synthesize non-executing defenses, remember what worked.
MIT -
Secure fleet management for Raspberry Pi clusters. Backups, patching, and Docker control with zero plaintext secrets.
MIT ★ 4 -
Fleet control plane: probe, boot and recover multi-node AI subsystems with proof. Docker and self-hosted inference fleet management.
MIT -
scry-connectgithub.com/phaneron-robotics/scryupdated this year
MCP server for ROS 2 — exposes robot capabilities as AI-callable tools
pypi Apache-2.0 -
Measurement-based EV battery SOH estimation, validated on unseen batteries, exposed as MCP tools to an LLM agent.
★ 5 -
local-commander-agentactive
Agent for Local Commander: remote control of your Windows, Mac and Linux computers from ChatGPT, Claude, Cursor or any MCP client. One chat, all your machines, even from your phone.
npm -
WireHop — secure peer-to-peer remote access and private networks. Single binary, no accounts, no port forwarding, no coordination server. Includes an MCP server so AI agents can reach and operate your machines.
npm MIT OR Apache-2.0 -
MCP server that gives AI agents (Claude Code, etc.) shell access to Raspberry Pi devices via the Raspberry Pi Connect web remote shell, with no SSH or open ports
MIT ★ 2 -
Swarm is a headless AI agent platform you self-host on Linux. It runs coding, research, design and media agents, workflows, schedules and monitoring across your machines. Drive it from your AI over MCP, or from your own code with the SDK, HTTP API or CLI.
Apache-2.0 ★ 11 -
Turn worst-case fleet hypotheses into the smallest bounded scan that could falsify them.
MIT -
Evolve scan and policy configurations against the fleet's measured phenotype instead of its labels.
MIT -
Control plane for browser fleets. One endpoint, any provider: failover, persistent profiles, session replay, REST API, MCP server, dashboard. OpenRouter for cloud browsers.
MIT ★ 19 -
Run a fleet of Claude Code (and agy) sessions from one terminal: live-status dashboard, CLI, TypeScript SDK and MCP server. macOS, Linux and Windows.
npm MIT -
Starlight-Intelligence-Systemgithub.com/Starlight-Intelligence/Starlight-Intelligence-Systemactive
One shared brain for your whole AI fleet: attested memory, orchestration, governance and evals across Claude Code, Codex, Cursor, Gemini, Antigravity.
MIT ★ 10 -
diffusion-llm-mcpgithub.com/sandraschi/diffusion-llm-mcpupdated this year
FastMCP fleet MCP server for diffusion LMs (dLLM). DiffusionGemma on Goliath RTX 4090 — batch inference, HLE-shaped reasoning, ~200–400 tok/s. Doc phase; llama-diffusion-cli sidecar next. Complements local-llm-mcp.
MIT ★ 2 -
Open-source MCP server that runs self-hosted WordPress like a senior admin: 150 tools for content, SEO, security audits, Query Monitor-style profiling, theme.json & accessibility, plugin settings as admin, and multi-site fleets. MCP 2026-07-28, Cloudflare Workers or stdio. Free, no usage caps.
MIT ★ 2