{"id":47012415,"url":"https://github.com/diegonogueiradev/mcp-graph-workflow","last_synced_at":"2026-05-15T22:01:35.352Z","repository":{"id":343147069,"uuid":"1172855600","full_name":"DiegoNogueiraDev/mcp-graph-workflow","owner":"DiegoNogueiraDev","description":"MCP local-first CLI tool that converts PRD text files into persistent execution graphs (SQLite) for structured agentic workflows","archived":false,"fork":false,"pushed_at":"2026-04-13T22:48:03.000Z","size":55307,"stargazers_count":28,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-04-13T23:29:32.421Z","etag":null,"topics":["agent-tooling","agentic-workflows","ai-tools","cli","local-first","mcp","mcp-server","model-context-protocol","open-source","prd","rag","semantic-search","sqlite","task-graph","typescript"],"latest_commit_sha":null,"homepage":"https://mcp-graph-workflow.vercel.app","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/DiegoNogueiraDev.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":"SUPPORT.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":"DiegoNogueiraDev"}},"created_at":"2026-03-04T18:57:56.000Z","updated_at":"2026-04-13T22:48:07.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/DiegoNogueiraDev/mcp-graph-workflow","commit_stats":null,"previous_names":["diegonogueiradev/mcp-graph-workflow"],"tags_count":87,"template":false,"template_full_name":null,"purl":"pkg:github/DiegoNogueiraDev/mcp-graph-workflow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiegoNogueiraDev%2Fmcp-graph-workflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiegoNogueiraDev%2Fmcp-graph-workflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiegoNogueiraDev%2Fmcp-graph-workflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiegoNogueiraDev%2Fmcp-graph-workflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DiegoNogueiraDev","download_url":"https://codeload.github.com/DiegoNogueiraDev/mcp-graph-workflow/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DiegoNogueiraDev%2Fmcp-graph-workflow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31866357,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T15:24:51.572Z","status":"ssl_error","status_checked_at":"2026-04-15T15:24:39.138Z","response_time":63,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-tooling","agentic-workflows","ai-tools","cli","local-first","mcp","mcp-server","model-context-protocol","open-source","prd","rag","semantic-search","sqlite","task-graph","typescript"],"created_at":"2026-03-11T21:21:41.643Z","updated_at":"2026-05-15T22:01:35.347Z","avatar_url":"https://github.com/DiegoNogueiraDev.png","language":"TypeScript","funding_links":["https://github.com/sponsors/DiegoNogueiraDev"],"categories":[],"sub_categories":[],"readme":"\u003c!--\n * SPDX-License-Identifier: AGPL-3.0-or-later\n * Copyright © 2026 Diego Lima Nogueira de Paula\n--\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/images/graph-logo.jpg\" alt=\"mcp-graph\" width=\"600\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003emcp-graph\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/DiegoNogueiraDev/mcp-graph-workflow/actions/workflows/ci.yml\"\u003e\u003cimg src=\"https://github.com/DiegoNogueiraDev/mcp-graph-workflow/actions/workflows/ci.yml/badge.svg\" alt=\"CI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.npmjs.com/package/@mcp-graph-workflow/mcp-graph\"\u003e\u003cimg src=\"https://img.shields.io/npm/v/%40mcp-graph-workflow%2Fmcp-graph\" alt=\"npm\"\u003e\u003c/a\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-AGPL_v3-blue.svg\" alt=\"AGPL v3\"\u003e\u003c/a\u003e\n  \u003ca href=\"COMMERCIAL.md\"\u003e\u003cimg src=\"https://img.shields.io/badge/Commercial-available-informational\" alt=\"Commercial license\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n**mcp-graph** turns your PRD into a persistent task graph that your AI agent navigates instead of improvising.\n\nPRD → graph (SQLite) → TDD → production. 100% local, zero cloud.\n\n---\n\n## The problem\n\nEvery AI coding session has the same three problems:\n\n- **The agent forgets** — each new chat starts from zero, the plan gets reinvented\n- **PRDs become walls of text** — nobody re-reads them, the agent improvises\n- **No traceability** — you can't tell what was done, what's blocked, or why\n\n## How it solves them\n\n1. `import_prd` — reads the PRD and creates tasks with acceptance criteria in the graph\n2. `start_task` — agent picks the next task with compressed context in hand\n3. `finish_task` — validates DoD (12 checks), status → done, suggests the next\n\nEverything lives in `workflow-graph/graph.db` — local SQLite, gitignored, never in the cloud.\n\n## Installation\n\n```bash\nnpm install -g @mcp-graph-workflow/mcp-graph\n```\n\nAdd to your project's `.mcp.json` (Claude Code, Cursor, Copilot):\n\n```json\n{\n  \"mcpServers\": {\n    \"mcp-graph\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@mcp-graph-workflow/mcp-graph\"]\n    }\n  }\n}\n```\n\nInitialize in your project:\n\n```bash\nmcp-graph init\n```\n\n**Prerequisites:** Node.js ≥ 18. No Docker. No LLM API key required.\n\n## Getting started\n\n```bash\n# 1. Import a PRD (or create tasks manually)\nmcp-graph import my-prd.md\n\n# 2. See the graph\nmcp-graph status\n\n# 3. Get next task\nmcp-graph next\n\n# 4. Start → implement with TDD → finish\nmcp-graph start \u003cid\u003e\n# ... write test, implement ...\nmcp-graph finish \u003cid\u003e\n```\n\nThe AI agent does this automatically via MCP tools (`start_task`, `finish_task`, `next`).\n\n## What's inside\n\n| Layer | What it does |\n|---|---|\n| 54 MCP tools | Graph, tasks, memory, RAG, sprint, deploy |\n| 130+ REST endpoints | Web dashboard, IDE integration |\n| Local RAG (FTS5 + BM25) | Compressed context without external LLM |\n| React dashboard | Kanban, visual graph, logs, insights |\n| 9-phase lifecycle | ANALYZE → DESIGN → PLAN → IMPLEMENT → VALIDATE → REVIEW → HANDOFF → DEPLOY → LISTENING |\n\n## Privacy\n\nZero telemetry. Zero phone-home. Runs offline after installation.\n\nLLM, embeddings, and external integrations are **opt-in** — nothing active by default.\n\n## Documentation\n\n- [Quickstart](docs/getting-started/QUICKSTART.md) — 60 seconds\n- [Full guide](docs/getting-started/GUIDE.md)\n- [Cheatsheet](docs/getting-started/CHEATSHEET.md) — all commands\n- [Architecture](docs/ARCHITECTURE.md)\n- [Sample PRD](docs/examples/sample-prd.md)\n\n## License\n\n[AGPL-3.0-or-later](LICENSE) — open source with strong copyleft.\nProprietary commercial use: [commercial license available](COMMERCIAL.md).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiegonogueiradev%2Fmcp-graph-workflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdiegonogueiradev%2Fmcp-graph-workflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdiegonogueiradev%2Fmcp-graph-workflow/lists"}