{"id":30869116,"url":"https://github.com/Pipelex/pipelex-mcp","last_synced_at":"2025-09-07T22:16:10.337Z","repository":{"id":296416066,"uuid":"991443556","full_name":"Pipelex/pipelex-mcp","owner":"Pipelex","description":"MCP server to run Pipelex pipelines","archived":false,"fork":false,"pushed_at":"2025-07-09T08:49:29.000Z","size":307,"stargazers_count":2,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-09T09:43:28.563Z","etag":null,"topics":["genai","llm","mcp","pipelex","pipeline"],"latest_commit_sha":null,"homepage":"https://pipelex.com","language":"Makefile","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/Pipelex.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-27T16:22:54.000Z","updated_at":"2025-07-09T08:48:55.000Z","dependencies_parsed_at":"2025-05-30T21:33:29.061Z","dependency_job_id":"61b4e814-0932-4d7c-ae08-61f8fa0d9748","html_url":"https://github.com/Pipelex/pipelex-mcp","commit_stats":null,"previous_names":["pipelex/pipelex-mcp"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/Pipelex/pipelex-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pipelex%2Fpipelex-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pipelex%2Fpipelex-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pipelex%2Fpipelex-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pipelex%2Fpipelex-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Pipelex","download_url":"https://codeload.github.com/Pipelex/pipelex-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Pipelex%2Fpipelex-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274102850,"owners_count":25222680,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-07T02:00:09.463Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["genai","llm","mcp","pipelex","pipeline"],"created_at":"2025-09-07T22:04:01.433Z","updated_at":"2025-09-07T22:16:10.322Z","avatar_url":"https://github.com/Pipelex.png","language":"Makefile","funding_links":[],"categories":["🤖 AI/ML"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003ca href=\"https://www.pipelex.com/\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/Pipelex/pipelex/main/.github/assets/logo.png\" alt=\"Pipelex Logo\" width=\"400\" style=\"max-width: 100%; height: auto;\"\u003e\u003c/a\u003e\n\n  \u003ch3 align=\"center\"\u003eThe Model Context Protocol server for Pipelex\u003c/h3\u003e\n  \u003cp align=\"center\"\u003eMCP is a protocol that enables AI Agents to run Pipelex pipelines\u003cbr/\u003eas native tools in their toolset.\u003c/p\u003e\n\n  \u003cdiv\u003e\n    \u003ca href=\"https://github.com/Pipelex/pipelex/blob/main/doc/Documentation.md\"\u003e\u003cstrong\u003eDocumentation\u003c/strong\u003e\u003c/a\u003e -\n    \u003ca href=\"https://github.com/Pipelex/pipelex-mcp/issues\"\u003e\u003cstrong\u003eReport Bug\u003c/strong\u003e\u003c/a\u003e -\n    \u003ca href=\"https://github.com/Pipelex/pipelex-mcp/discussions\"\u003e\u003cstrong\u003eFeature Request\u003c/strong\u003e\u003c/a\u003e\n  \u003c/div\u003e\n  \u003cbr/\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-blue.svg\" alt=\"MIT License\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://pipelex.com\"\u003e\u003cimg src=\"https://img.shields.io/badge/Web-pipelex.com-03bb95?logo=google-chrome\u0026logoColor=white\u0026style=flat\" alt=\"Website\"\u003e\u003c/a\u003e\n    \u003cbr/\u003e\n    \u003cbr/\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n# 📑 Table of Contents\n\n- [Introduction](#introduction)\n- [Quick Start](#-quick-start)\n  - [Prerequisites](#prerequisites)\n  - [Installation](#installation)\n- [Adding New Tools](#-adding-new-tools)\n- [Known Limitations](#-known-limitations)\n- [Contributing](#-contributing)\n- [Support](#-support)\n- [License](#-license)\n\n# Introduction\n\n\u003e 👉 Check out our [main repository](https://github.com/Pipelex/pipelex) to learn more about Pipelex!\n\nThe Model Context Protocol (MCP) is a specialized component of the Pipelex ecosystem that enables AI Agents to interact with Pipelex pipelines as native tools. This protocol bridges the gap between AI agents and the structured, reliable pipeline execution that Pipelex provides.\n\nMCP allows AI agents to:\n- Discover available pipelines\n- Execute pipelines with specific inputs\n- Receive structured outputs in a format they can understand and use\n\nTo learn more about MCP itself, check out the [official MCP documentation](https://docs.anthropic.com/en/docs/agents-and-tools/mcp) from Anthropic.\n\n# 🚀 Quick Start\n\n## Prerequisites\n\n- Python \u003e=3.11,\u003c3.12\n- [uv](https://github.com/astral-sh/uv) package manager\n\n## Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/Pipelex/pipelex-mcp.git\ncd pipelex-mcp\n```\n\n2. Install dependencies:\n```bash\nmake install\n```\n\n3. Set up your environment:\n```bash\ncp pipelex_mcp/.env.example pipelex_mcp/.env\n# Edit pipelex_mcp/.env with your configuration\n```\n\n4. Add your API keys:\nConfigure your API keys in the `.env` file. These will be used by the MCP server to authenticate with various services.\n\n# MCP Clients\n\n### Cursor\nCursor comes with built-in MCP support. Simply describe the tool you want to use in the chat, and Cursor will automatically invoke it.\n\n[Learn more about MCP in Cursor](https://docs.cursor.com/context/model-context-protocol)\n\n### Claude Desktop\nClaude Desktop uses its own configuration format. Check the MCP documentation for setup details:\n\n[Claude Desktop MCP Setup Guide](https://modelcontextprotocol.io/quickstart/server)\n\n### Other Clients\nMCP is an open protocol - any client that implements the protocol can interact with MCP servers. Check the MCP documentation for a full list of available clients.\n\n# 🛠 Adding New Tools\n\nAdding a new tool (pipe) to the MCP server is straightforward. Here's a basic example:\n\n```python\n@mcp.tool(\"generate_company_mascott\")\nasync def generate_company_mascott(company_context: str) -\u003e dict:\n    \"\"\"Generate multiple mascot options for a company using the complete design process.\n    Output the links of the images.\n    \n    Args:\n        company_context: Context about the company\n        \n    Returns:\n        dict: Response containing generated mascot images\n    \"\"\"\n    # Your implementation here\n    return {\"images\": [...]}\n```\n\nKey points when adding a new tool:\n1. Use the `@mcp.tool` decorator with a unique name\n2. Define clear input parameters with type hints\n3. Write a comprehensive docstring explaining the tool's purpose\n4. Return structured data that the AI agent can understand\n\nFor more complex examples and to understand the underlying Pipelex technology, check out the [Pipelex Documentation](https://github.com/Pipelex/pipelex/blob/main/doc/Documentation.md).\n\n# ⚠️ Known Limitations\n\nWe are actively working on improving these aspects of the repository:\n\n## Library Duplication\nCurrently, the `pipelex_libraries` folder needs to exist in two locations:\n- At the root of the project\n- Inside the `pipelex_mcp` folder\n\nThis duplication is not ideal and we're working on a better solution for managing shared libraries.\n\n## Logging Configuration\nThe current logging system has some limitations:\n- Difficulty in redirecting logs to specific files\n- Limited control over log formatting and destinations\n- No built-in log rotation or management\n\nWe're planning to implement a more robust logging system in future updates.\n\n## Long-Running Pipelines\nFor pipelines that take longer than the MCP client timeout to complete, we need to implement a session ID system. This would allow:\n- Handling of timeouts gracefully\n- Resuming pipeline execution\n- Status tracking for long-running operations\n\nThis feature is planned for future releases to better support extended pipeline operations.\n\n## 🤝 Contributing\n\nWe welcome contributions! Please check our issues page or submit a pull request.\n\n## 💬 Support\n\n- **GitHub Issues**: For bug reports and feature requests\n- **Discussions**: For questions and community discussions\n- [**Documentation**](https://github.com/Pipelex/pipelex/blob/main/doc/Documentation.md)\n\n## 📝 License\n\nThis project is licensed under the [MIT license](LICENSE).\n\n---\n\n\"Pipelex\" is a trademark of Evotis S.A.S.\n\n© 2025 Evotis S.A.S.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FPipelex%2Fpipelex-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FPipelex%2Fpipelex-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FPipelex%2Fpipelex-mcp/lists"}