{"data":{"slug":"mcp-use-mcp-use","name":"mcp-use","tagline":"MCP framework for AI Agents development","github_url":"https://github.com/mcp-use/mcp-use","owner":"mcp-use","repo":"mcp-use","owner_avatar_url":"https://avatars.githubusercontent.com/u/207005519?v=4","primary_language":"TypeScript","stars":10654,"forks":1467,"topics":["agent-plugins","agentic-framework","ai","apps-sdk","chatgpt","claude-code","claude-connectors","llms","mcp","mcp-apps","mcp-client","mcp-gateway","mcp-inspector","mcp-server","mcp-servers","mcp-tools","mcp-ui","model-context-protocol","modelcontextprotocol","skills"],"archived":false,"github_pushed_at":"2026-09-18T23:57:03+00:00","maintenance_label":"Very active","stars_delta_30d":282,"url":"https://www.graphcanon.com/tools/mcp-use-mcp-use","markdown_url":"https://www.graphcanon.com/tools/mcp-use-mcp-use.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mcp-use-mcp-use","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mcp-use-mcp-use","description":"The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.","homepage_url":"https://manufact.com","license":"MIT","open_issues":74,"watchers":91,"ai_summary":"Develops MCP Apps and Servers supporting ChatGPT and Claude using TypeScript.","readme_excerpt":"
\n \n \"mcp-use\"\n \n

\n\n
\n \n
\n\n\n

\n Fully Typed, native Views and MCP Apps support, built-in Inspector and first class Agent experience.\n

\n\n

\n Documentation\n · Inspector\n · Examples\n · Deploy\n

\n\n

\n \n \"npm\n \n \n \"npm\n \n \n \"made\n \n \n \"MIT\n \n \n \"Discord\"\n \n

\n

\n
\n\n> [!NOTE]\n> **Migrating from v1? Give it to your agent:**\n>\n> ```text\n> Migrate this mcp-use project to v2 following\n> https://docs.mcp-use.com/v2/typescript/server/migration\n> ```\n>\n> [Read the migration guide →](https://docs.mcp-use.com/v2/typescript/server/migration)\n\n## Get started\n\n### Start with your agent\n\n```text\nBuild an MCP server: https://mcp-use.com/prompt.md\n```\n\n[Read the prompt →](https://mcp-use.com/prompt.md)\n\n### Start with code\n\n```bash\nnpx -y create-mcp-use-app@latest\n```\n\nRun `npm run dev` in the generated project · open [`http://localhost:3000/mcp/inspector`](http://localhost:3000/mcp/inspector)\n\n[TS Docs](https://docs.mcp-use.com/v2/typescript/getting-started/welcome)\n\n## Everything you need to ship MCP\n\n\n \n \n \n \n \n \n \n \n
\n

Fully typed

\n

Zod schemas flow from tools to structured results, View props, and tool calls.

\n 		\n

Native Views

\n

Bind React Views directly to tools and ship interactive apps without custom extension wiring.

\n
\n

Agent-first and headless

\n

Scaffold, invoke, inspect, screenshot, and deploy through your agent.

\n 		\n

Built-in debugging tools

\n

Inspect tools and Views in the browser or headlessly through the CLI.

\n
\n\n## Quickstart\n\nThe scaffold gives you the server, TypeScript configuration, development scripts, Inspector, and a React view pipeline. Start it once and the MCP endpoint also serves a client-ready landing page with its connection URL and setup instructions.\n\nReplace its `index.ts` with a view-bound tool like this:\n\n
\n
\nindex.ts — Server entry file for tool definition and metadata\n\n```typescript\nimport { MCPServer } from \"mcp-use\";\nimport { z } from \"zod\";\n\nconst server = new MCPServer({\n name: \"weather-app\",\n title: \"Weather App\",\n version: \"1.0.0\",\n});\n\nconst weatherInput = z.object({\n city: z.string().describe(\"City to look up\"),\n});\n\nconst weatherOutput = z.object({\n city: z.string(),\n temperature: z.number(),\n conditions: z.string()","github_created_at":"2025-03-28T10:06:31+00:00","created_at":"2026-07-11T11:49:35.46196+00:00","updated_at":"2026-09-20T06:39:22.961688+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"agentic-framework","name":"agentic-framework"},{"slug":"ai","name":"ai"},{"slug":"apps-sdk","name":"apps-sdk"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"claude-code","name":"claude-code"},{"slug":"llms","name":"llms"}],"trust":{"provenance":{"is_fork":false,"github_id":956472076,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T03:50:39.558Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":1,"last_release_at":"2026-09-18T21:41:14Z","stars_delta_30d":282,"open_issues_delta_30d":-48},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:49:36.600Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T03:50:40.593Z"},"languages":{"value":["typescript"],"source":"github.language","observed_at":"2026-09-20T03:50:40.593Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T03:50:40.593Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If your project involves building an application or server that needs to be integrated with both ChatGPT and Claude using TypeScript, then mcp-use is tailored for this scenario.","Use when you are creating a full-stack development environment specifically focused on the Model Context Protocol (MCP) for AI agents that require comprehensive interaction with language models."],"when_not_to_use":["Do not use if your project requires a different programming language, as mcp-use strictly supports TypeScript.","Avoid using it when your application does not need integration with ChatGPT and Claude, since the framework is specifically designed for these two platforms."],"source":"enrich:decision_facts","observed_at":"2026-07-17T03:19:40.479Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"The MCP framework for AI Agents development supports TypeScript-based development of applications and servers that integrate with ChatGPT and Claude."}]}}