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.
-
warposgithub.com/jcmrs/warposupdated this year
MCP server for deterministic task execution via Domain Profile Agents + Task Templates. Provides planning/orchestration layer for CLI AI assistants (Warp, etc.)
-
Task-Anchor-MCPgithub.com/Kodaxadev/Task-Anchor-MCPupdated this year
ADHD executive function enforcement for Claude Desktop. An MCP server with task locking, drift detection, and stateful boundaries to stop context switching.
MIT ★ 3 -
SwarmTask: Parallel shell command execution via MCP protocol. Submit multiple tasks, get real-time progress. Perfect for system admin & development workflows.
★ 2 -
Minimal, dependency-free reference MCP server for physical-world task execution (protocol 2026-07-28)
MIT -
Use Google Tasks with AI agents through one PipMCP API key, actual hosted schemas and governed execution.
MIT -
Model Context Protocol (MCP) server for planning and executing tasks.
npm MIT -
Headless LLM task runner — schedule natural language tasks via MCP, execute with any LLM provider, deliver results through Slack/Telegram/Email
nuget MIT ★ 1 -
agent-pilotgithub.com/agent-tool-intel/agent-pilotupdated this year
Universal MCP agent pilot — task orchestration, tool registry, and execution. Powered by Agent Tool Intel quality scores.
MIT ★ 2 -
AI-Defined Hardware (ADH) — ESP32-S3 Task VM: firmware executes JSON tasks over MQTT, controlled by Claude via MCP Server
MIT -
8megithub.com/fbratten/8meactive
Multi-tiered loop-until-done task execution toolkit: CLI, Claude Code skill, MCP server (Python + TypeScript), and orchestrator client with circuit breaker.
NOASSERTION -
Zero-dependency MCP task relay for local Antigravity and Codex CLIs, with async execution, status queries and cancellation.
MIT ★ 2 -
dnc-mcpgithub.com/kanghohyeong/dnc-mcpupdated this year
An MCP (Model Context Protocol) server that applies the Divide and Conquer paradigm to AI-driven task management. Just like a D&C algorithm, you declare a complex goal, break it into smaller sub-tasks, review and adjust the plan, and then let the agent execute automatically.
MIT -
taskmajorgithub.com/sznicolas/taskmajorupdated this year
TaskMajor MCP. Coordinate your tasks. Execute with precision.
pypi -
idea-managergithub.com/navskh/imupdated this year
AI-powered idea & task manager for developers. Brainstorm → structured tasks → AI agent execution. CodeMirror editor with slash commands, MCP Server, Claude/Gemini/Codex support. Local-first SQLite, cross-PC Git sync.
npm MIT -
plan-cascadegithub.com/Taoidle/plan-cascadeupdated this year
AI-powered cascading development framework. Decompose complex projects into parallel executable tasks with auto-generated PRDs, design docs, and multi-agent collaboration (Claude Code, Codex, Aider).
MIT ★ 134 -
Tree-native workspace for human and agent execution: plan, run and review long AI tasks as an editable tree, via MCP in your existing agent tools.
-
MCP server for Figranium, wrapping task execution, scheduling, and automation orchestration.
npm Apache-2.0 -
scheduleroraclegithub.com/ToolOracle/scheduleroracleupdated this year
SchedulerOracle — Persistent Autonomous Task Scheduler MCP for AI Agents. 9 tools: cron/interval/one-time scheduling, auto-store results in MemoryOracle, optional Decision Preflight gate, execution history. The motor that makes agents work 24/7.
NOASSERTION -
os-loop-bridgegithub.com/CristianBB/os-loop-bridgeupdated this year
Native companion for OS Loop AI that extends browser agents with secure local capabilities—filesystem access, MCP connectivity, long-running tasks, and system-level execution
MIT ★ 1 -
IMgithub.com/navskh/IMupdated this year
AI-powered idea & task manager for developers. Brainstorm → structured tasks → AI agent execution via MCP. CodeMirror editor, Claude/Gemini/Codex, local-first SQLite.
npm ★ 11 -
claude-code-control-mcpgithub.com/marc-shade/claude-code-control-mcpupdated this year
Programmatic task execution using Claude AI for autonomous coding workflows.
-
Agent-friendly task planning and execution MCP server with browser UI
ISC ★ 1 -
Badgr — GPU Compute, AI Model Deployment & Agent Executionno update data
**Run GPU workloads, deploy AI models, access inference APIs, and execute AI agents using Badgr's MCP server.** Badgr is an AI compute and workload execution platform for developers, coding agents, and AI assistants. Run workloads on cloud GPUs or compatible customer-owned GPUs (BYO GPU), with cost controls, execution logs, and verified results. **What can Badgr do?** - **GPU Compute / AI Workloads:** Run Python scripts, machine learning jobs, batch inference, and supported ComfyUI workflows. - **AI Model Deployment:** Deploy and serve LLMs using compatible runtimes such as vLLM and SGLang. Get a verified, OpenAI-compatible inference endpoint. - **AI API / LLM Inference:** Make AI API requests with response validation, supported fallback routing, and bounded execution. - **AI Agent Execution:** Launch coding and testing agents, run tasks, check acceptance criteria, and retrieve execution receipts. **Key features:** Cloud GPU execution, BYO GPU support, model serving, AI agent jobs, workload verification, execution logs, cost limits, and deployment management. Connect Badgr to your MCP-compatible AI assistant to execute real workloads instead of just generating instructions. Get started: https://aibadgr.com **Requires a Badgr API key. GPU workloads and other paid execution may incur usage charges.**
smithery -
Workflow execution for agent runs — hand a task doc to cursor, persist the run, inspect / cancel. MCP server.
MIT -
Bounded repository search, durable task evidence, and gated execution for coding agents.
MIT -
oriora-router-mcpgithub.com/Orioralabs/oriora-router-mcpupdated this year
Oriora model-router as an MCP server — best AI model per task, executed on your own keys (BYOK)
MIT -
Windows MCP server with explicit file and execution policies, fleet task coordination, and the Fleet Tabs Chrome extension.
MIT ★ 1 -
MCP server for multi-terminal Claude Code orchestration with DAG task management, parallel execution, and self-improvement
npm MIT -
JPYC-commerce-mcpgithub.com/ackey-web/JPYC-commerce-mcpupdated this year
MCP server for AI agent commerce — task evaluation, trust-based negotiation, and JPYC payment execution on Polygon.
NOASSERTION -
MCP server that gives agents a browser that finishes tasks itself: Jev plans each step, real Chrome executes, results come back verified.
npm MIT ★ 2 -
Control Android devices through ADB with this Python automation framework for task execution and phone farm scaling.
MIT ★ 4 -
rails_orchestratorgithub.com/justi/rails_orchestratorupdated this year
Autonomous Rails-based system for planning and executing software development tasks with AI integration via Model Context Protocol.
★ 1 -
Agentic workflow automation server for MCP. Enables AI assistants to break down complex tasks into actionable steps, orchestrate tool execution, and track progress autonomously.
MIT ★ 3 -
Claude Code Sub-agents Orchestrator - A powerful MCP server for orchestrating multiple AI sub-agents for complex task execution in Claude Code
npm MIT -
The fabric-mcp-server is an MCP server that integrates Fabric patterns with AI coding agents and assistants, exposing them as tools for AI-driven task execution and enhancing capabilities.
MIT ★ 18 -
ToolRoutegithub.com/grossiweb/ToolRouteupdated this year
Intelligent routing layer for AI agents: recommends the best MCP server and LLM for any task, scored on 132+ real benchmark executions.
npm MIT ★ 2 -
@littlebearapps/mcp-delegatorgithub.com/littlebearapps/mcp-delegatorupdated this year
Delegate AI agent tasks from Claude Code to Codex, Claude Code (Agent SDK), and more - with async execution
npm MIT -
The execution layer for Wispr Notetaker — an agentic AI that remembers every meeting decision, catches conflicts, tracks commitments, and turns talk into approved tasks in Notion, Slack & email.
★ 1 -
Engineering MCP is a repository-aware AI engineering control plane for orchestrating trusted coding workers through MCP, with lifecycle management, execution isolation, and verifiable task handoff.
NOASSERTION ★ 8 -
Delegate browser operations to an ultra-fast MCP server, executing full page tasks in seconds with one tool call.
MIT -
Unofficial Windows stdio MCP bridge for delegating Codex tasks to local Unsloth Qwen models with aliases, safe progress, cancellation cleanup, bounded continuation, and single-flight execution.
AGPL-3.0 -
@easyshell/mcp-servergithub.com/easyshell-ai/easyshellupdated this year
MCP server for EasyShell — AI-Native Server Operations Platform. Manage hosts, execute scripts, orchestrate multi-host tasks, and schedule inspections from any AI assistant.
npm MIT -
postgres-mcpgithub.com/az-coder-123/postgres-mcpupdated this year
Production-grade PostgreSQL MCP Server. Empowers LLMs with 40+ tools for deep database interaction, including schema inspection, secure query execution, performance analysis, and administrative tasks. Built for reliable AI-driven development.
★ 6 -
Demonstrates Model Context Protocol (MCP) for conversational AI. Shows how to build natural language interfaces for database operations using NestJS, MongoDB, and OpenAI. Includes RAG integration and automated task execution through chat.
-
Ergonia Works: verifiable work for AI agents. Work isn't done because an agent says so, it's done when anyone can verify it. Every task carries an acceptance condition a stranger can execute.
AGPL-3.0 -
Lightweight Go MCP coding executor for Claude Code and Codex. Delegate bounded tasks to any Anthropic Messages-compatible model with project-aware context, verification, parallel execution, and token usage tracking.
Apache-2.0 -
AI-native platform for planning and shipping software: plans and tasks in Postgres, served to any coding agent over MCP, with agentic execution and a developer dashboard.
Apache-2.0 ★ 2 -
Desktop-Context-MCPgithub.com/djfkkdj3/Desktop-Context-MCPupdated this year
Windows desktop MCP server for giving models isolated local workspaces, Python execution, browser automation, filesystem access, background tasks, and reusable custom tools through a one-click control panel.
-
Evidence-gated execution for AI agents: a task succeeds only when the host verifies it. Hash-chained logs, a fault-injection benchmark, and a hidden-test study of LLM 'done' claims.
MIT -
Zero-error LLM execution via SPRT voting. Rust library and MCP server implementing the MAKER algorithm for mathematically-grounded error correction in long-horizon AI agent tasks. Research experiment based on arXiv:2511.09030
MIT ★ 5 -
This repository contains the MCP servers for ComplianceCow. It leverages four specialized servers—Rules, Insights, Workflow, and Assistant—to automate GRC tasks, execute compliance rules, and visualize security posture through the Compliance Graph. These MCP servers can be seamlessly integrated with MCP hosts such as Claude Desktop and Goose.
★ 13 -
A comprehensive Node.js Model Context Protocol (MCP) server for JasperReports Server REST API v2. This server enables AI assistants and developers to perform all major JasperReports operations including authentication, resource management, report execution, job scheduling, and administrative tasks through standardized MCP tools.
npm NOASSERTION ★ 9 -
codex-comsol-bridgegithub.com/WendyAi2005/codex-comsol-bridgeupdated this year
Community-built Codex–COMSOL bridge using officially supported MATLAB MCP and LiveLink integration layers, with native multiphysics API access, task-level execution, same-model Desktop observation, and verified human takeover.
MIT ★ 9 -
Use Google Antigravity (agy) as an agent backend from Claude Code / OpenAI Codex / Cursor / any MCP client. MCP server with 10 typed tools + Skill bundles, hybrid backend, capability detection, long-task supervisor, worktree-isolated execute.
pypi MIT ★ 26 -
MCP providing a capability layer between agents and their environment. Giving governed access to tools, scripts, skills, execution, Runs and Task continuity without coupling the product to one agent or one MCP gateway.
MIT -
I couldn't find a good web grounding MCP server for Goose, so I made one for me. This server exposes a single "Agent" tool that combines real-time Google Search, deep URL analysis, and Python code execution to solve complex, multi-step research and data tasks.
MIT -
Gravitas-Coregithub.com/ahmed-coding/Gravitas-Coreupdated this year
Gravitas-Core is a Python-native autonomous AI control plane and MCP (Model Context Protocol) server. It provides a persistent execution core for intelligent agents with task state management, memory persistence, terminal/browser engines, and recursive project intelligence—all designed for scalable AI-driven workflows.
MIT ★ 1 -
把 Claude Code、Codex 和 Hermes 接入工单、CI 与业务系统。自托管 Agent 执行服务,提供 Web 管理台、异步任务 API、独立工作区和结果回调。Self-hosted agent execution with a web console, async task API, isolated workspaces and signed webhooks.
MIT ★ 10 -
让主力 AI 负责规划与验收,把编码和 DAG 任务委派给本机 Oh My Pi (OMP) Worker 执行的 MCP 服务器 | MCP server that lets your main AI plan & review while local Oh My Pi (OMP) workers execute coding tasks & DAG batches.
npm MIT ★ 3 -
AgentTrust XRPL is a trust-minimized verification and escrow service on the XRP Ledger that enables any AI agent to securely execute peer-to-peer tasks by locking payment in native XRP escrow, submitting proof of completion, and receiving an objective PASS/FAIL judgement from an independent AI referee.
npm MIT ★ 2