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.
-
Documentation Augmented Generation (DAG) MCP Server - First multi-ecosystem, version-aware MCP server to reduce AI code hallucinations
MIT ★ 2 -
The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.
MIT ★ 44 -
Visual and code-based DAG builder for Apache Airflow 3: design on a canvas, generate readable Python, validate with DagBag, deploy to a folder, object storage or git. Runs as an Airflow plugin, standalone server or MCP server.
Apache-2.0 -
lossless-codegithub.com/GodsBoy/lossless-codeupdated this year
DAG-based Lossless Context Management for Claude Code. Every message preserved, summaries cascade as a DAG, patterns extracted via Lossless Dream — full recall and reflection across sessions.
MIT ★ 15 -
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 -
CLI tool for structured software specifications. Validate .dog files, compile .dag graphs, query via MCP.
npm MIT -
axmggithub.com/dchrnv/axmgactive
Deterministic Merkle DAG associative memory engine with Model Context Protocol (MCP) for local LLMs and autonomous agents.
AGPL-3.0 -
deep-thinkergithub.com/nachosystems/deep-thinkerupdated this year
Advanced cognitive reasoning MCP server — DAG thought graph, 10 strategies, metacognition, self-critique, knowledge integration, and pruning
MIT ★ 15 -
QuDAG Protocol (Quantum-Resistant DAG-Based Anonymous Communication System) - Claude Code implementation of a Test-Driven Development Implementation Plan for QuDAG Protocol with Claude Code
MIT ★ 199 -
Decompose DAG: an epistemic scaffold for vibe coding. A claims graph the agent must verify bottom-up with evidence, an MCP server for agents, a live dashboard for humans.
npm MIT -
agent-boardgithub.com/quentintou/agent-boardupdated this year
Open-source multi-agent task board for OpenClaw. Kanban + DAG dependencies + MCP server + auto-retry + audit trail. Built for autonomous AI agent teams.
MIT ★ 34 -
QuDAG MCP server over stdio: ML-KEM-768 key exchange and ML-DSA-65 signing via @qudag/napi-core, plus simulated quantum-circuit and DAG tools.
npm MIT -
opcodegithub.com/rendis/opcodeupdated this year
Zero-token execution layer for AI agents — define workflows once, execute forever. DAG engine with reasoning nodes, event sourcing, scheduling, and secret vault via 6 MCP tools over SSE.
MIT ★ 1 -
MCP server that lets ChatGPT, Codex, Claude Code and other agents hand off coding tasks and DAG batches to local Oh My Pi (OMP) workers.
npm MIT -
Memory that forgets: a persistent, self-revising belief-state MCP server for agentic R&D. Uses a hypothesis DAG to auto-prune dead ends and deduce truth without extra probes.
pypi MIT -
@iflow-mcp/jnmetacode-agency-orchestratorgithub.com/jnmetacode/agency-orchestratorupdated this year
Multi-agent YAML workflow engine — 211 AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 10 LLM providers, 7 need no API key.
npm Apache-2.0 -
Memory that forgets: a persistent, self-revising belief-state MCP server and Python API for agentic R&D. Uses a hypothesis DAG to auto-prune dead ends and deduce truth without extra probes.
MIT ★ 12 -
Git DAG indexing, AST symbol graphs, and hybrid semantic code search MCP server for AI coding agents (Claude Code, Cursor, Windsurf). Maps repositories into PostgreSQL + pgvector with recursive caller/callee dependency graphs and temporal recency decay.
MIT -
dagrgithub.com/mjzd7/dagractive
The DAG-Native Symbolic AST Slicing Hypervisor & Safety Sandbox for AI Coding Agents
Apache-2.0 -
MCP-native modular ML workflow engine — YAML-config-driven, DAG-orchestrated data analysis & model training, exposed as MCP tools
MIT -
autobeatgithub.com/dean0x/autobeatupdated this year
AI coding agent orchestration at scale. Karpathy optimization loops, multi-agent pipelines, DAG dependencies, autoscaling workers. Claude, Codex, Gemini.
npm MIT -
MCP server for multi-terminal Claude Code orchestration with DAG task management, parallel execution, and self-improvement
npm MIT -
substreams-search-mcpgithub.com/paulieb14/substreams-search-mcpupdated this year
MCP server to search and inspect Substreams packages — browse the registry and introspect .spkg module graphs, protobuf types, and DAG dependencies
npm MIT -
Rust 插件中台:契约治理 · 注册发现 · 声明式编排 · 事件总线 · MCP 工具面 / Out-of-process plugin hub in Rust: contracts, discovery, DAG orchestration, event bus, MCP tool surface
MIT ★ 4 -
Independent incident-response MCP server for Apache Airflow: diagnose failed DAGs from UI links with bounded logs, multi-instance routing, and opt-in recovery.
Apache-2.0 ★ 2 -
autobeatgithub.com/dean0x/autobeatupdated this year
Autonomous coding agent orchestration. Give it a goal, walk away, come back to finished work. Eval loops, multi-agent pipelines, DAG dependencies, crash-proof persistence.
MIT ★ 6 -
🧭 Strategic BDI cognitive reasoning engine for AI agents. Goal decomposition DAGs, multi-factor utility scoring, risk evaluation, and adaptive replanning over MCP.
npm MIT ★ 13 -
ChatGPT Ads MCP Server & Agent Skill for OpenAI Ads Manager Beta: Context Hints, Delta Feeds, CAPI oppref tracking & Bulk DAG automation
MIT -
Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.
MIT ★ 12 -
Zero-trust L0-L5 verification gateway in Zig 0.17: native Z3 proof-DAG checker, Belnap B4 logic, 42 Lean 4 theorems (0 sorry), 8-lane SIMD BLAKE3 (.kimg) & MCP server.
NOASSERTION ★ 13 -
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 -
A job scheduler and orchestrator in a single binary, for scripts, pipelines and AI agents alike. Cron, DAGs, retries, timeouts and alerts over a directory of YAML, plus task results, idle timeouts, run-time fan-out and an MCP server for agentic jobs.
0BSD ★ 3 -
Passive OSINT radar that scores investment websites for Ponzi and pyramid scheme risk. Python DAG pipeline + MCP server for Claude: RDAP, DNS, certificate transparency, Wayback, company and regulator lookups, evidence-checked answers and a chain-of-custody risk dossier. EN / PT-BR.
-
agent-workflow-mcpgithub.com/mdfifty50-boop/agent-workflow-mcpupdated this year
Multi-step workflow orchestration for AI agents — define, execute, pause, resume complex pipelines
-
A powerful Workflow Orchestration Engine with simple declarative YAML API. Zero-dependency, single binary for Linux, macOS, and Windows.
npm GPL-3.0 -
beads-vizgithub.com/pyros-projects/beads-vizupdated this year
Read-only task graph visualizer for Beads projects — MCP App for Claude Desktop and VS Code Copilot
npm MIT -
specdaggithub.com/japorto100/specdagupdated this year
A CLI and MCP server for validating, assembling, and rendering dependency maps in Event-Spec-Driven Development (ESDD)
-
mmcp-coregithub.com/ragavrida/mmcpupdated this year
MMCP — Multi-Model Collaboration Pipeline. Auto-routes tasks to Claude, GPT, Gemini, DeepSeek with RL routing, cost optimization, and MCP server support.
pypi MIT -
Beta — Local-first visual data quality tool for Excel/CSV/TSV. Visual canvas, built-in AI assistant, CLI + MCP server. All validation runs on your machine.
Apache-2.0 ★ 3 -
Chain of Thoughts (zoth-cot): zero-dependency working memory and reasoning log for AI agents, with an MCP server. Free and open source.
-
Control Apache Airflow with natural language via MCP. Chat with your workflows using Claude, GPT, or any LLM — no REST API calls needed. Supports Airflow 2.x (43 tools) & 3.0+ (45+ tools).
MIT ★ 54