{"id":27928552,"url":"https://github.com/sultanfariz/mcp-client-db","last_synced_at":"2026-04-16T11:02:10.729Z","repository":{"id":291369994,"uuid":"976963322","full_name":"sultanfariz/mcp-client-db","owner":"sultanfariz","description":"A very simple prototype LLM-powered MCP client to access DB built with Google ADK. Intended for GDGoC IPBxUI Build with AI workshop.","archived":false,"fork":false,"pushed_at":"2025-05-04T06:55:22.000Z","size":3,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-28T19:46:44.951Z","etag":null,"topics":["adk","agent-development-kit","mcp","mcp-client"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sultanfariz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"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":"2025-05-03T05:30:23.000Z","updated_at":"2025-05-04T06:55:25.000Z","dependencies_parsed_at":"2025-05-04T07:30:06.048Z","dependency_job_id":"76bcd1ea-1bfc-4b51-a057-54621dd602cc","html_url":"https://github.com/sultanfariz/mcp-client-db","commit_stats":null,"previous_names":["sultanfariz/mcp-client-db"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sultanfariz/mcp-client-db","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sultanfariz%2Fmcp-client-db","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sultanfariz%2Fmcp-client-db/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sultanfariz%2Fmcp-client-db/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sultanfariz%2Fmcp-client-db/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sultanfariz","download_url":"https://codeload.github.com/sultanfariz/mcp-client-db/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sultanfariz%2Fmcp-client-db/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31882886,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T09:23:21.276Z","status":"ssl_error","status_checked_at":"2026-04-16T09:23:15.028Z","response_time":69,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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":["adk","agent-development-kit","mcp","mcp-client"],"created_at":"2025-05-07T02:40:43.141Z","updated_at":"2026-04-16T11:02:10.683Z","avatar_url":"https://github.com/sultanfariz.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ADK Agent with MCP Database Tool\n\nThis project demonstrates an AI agent built using the Google Agent Development Kit (ADK) that interacts with a database through a Model Context Protocol (MCP) server. The agent translates natural language requests into SQL queries.\n\n## Prerequisites\n\n*   Python 3.x\n*   Node.js (for running the MCP server)\n*   pip (Python package installer)\n*   Access to a database (the specific type depends on your `DATABASE_URI`)\n\n## Installation\n\n1.  **Clone the repository (if applicable):**\n    ```bash\n    git clone \u003crepository-url\u003e\n    cd \u003crepository-directory\u003e\n    ```\n\n2.  **Set up Python Environment:**\n    It's recommended to use a virtual environment:\n    ```bash\n    python3 -m venv .venv\n    source .venv/bin/activate # On Windows use `.venv\\Scripts\\activate`\n    ```\n\n3.  **Install Python Dependencies:**\n    ```bash\n    pip install google-adk python-dotenv\n    ```\n    *(Add any other Python dependencies if needed)*\n\n4.  **Set up MCP Server:**\n    This project assumes you have a separate Node.js-based MCP server. You need to build it and note the path to its main executable (e.g., `index.js` or similar).\n    *(Add specific instructions here if the MCP server code is part of this repo and needs building, e.g., `npm install`, `npm run build`)*\n\n## Configuration\n\n1.  **Create Environment File:**\n    Copy the example environment file:\n    ```bash\n    cp .env.example .env\n    ```\n\n2.  **Edit `.env`:**\n    Open the `.env` file and set the following variables:\n    *   `DATABASE_URI`: Your database connection string (e.g., `postgresql://user:password@host:port/database`).\n    *   `GOOGLE_API_KEY`: Your Google AI API key. Obtain this from Google Vertex or AI Studio and ensure the Gemini APIs are enabled for your project.\n    *   *(Potentially add API keys if the agent uses other services)*\n\n3.  **Update Agent Script:**\n    Open `multi_tool_agent/agent.py` and update the path to your MCP server executable in the `StdioServerParameters` section. **Replace `/path/to/build/index.js` with the actual path to your built MCP server script.**\n    ```python\n    # multi_tool_agent/agent.py\n    ...\n    StdioServerParameters(\n        command='node',\n        args=[\n          \"/path/to/build/index.js\",    # \u003c-- IMPORTANT: UPDATE THIS PATH\n          os.environ.get(\"DATABASE_URI\")\n        ]\n      )\n    ...\n    ```\n\n## Running the Application\n\n1.  **Start the MCP Server:**\n    The Python agent script will start the MCP server automatically when it runs, using the command specified in `agent.py`. Ensure Node.js is in your system's PATH and the path in `agent.py` is correct.\n\n2.  **Run the Python Agent:**\n    Make sure your virtual environment is activated (`source .venv/bin/activate`).\n    Navigate to the root directory of this project (`mcp-client-adk copy`) in your terminal.\n    ```bash\n    adk web\n    ```\n    The agent will attempt to connect to the MCP server and become ready to process requests based on its instructions.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsultanfariz%2Fmcp-client-db","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsultanfariz%2Fmcp-client-db","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsultanfariz%2Fmcp-client-db/lists"}