{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_84qh2czhfe6n","handle":"iflow-mcp-vivian-xie-db-genie-mcp-server","url":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server","links":{"self":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/record.json","html":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server","markdown":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-vivian-xie-db-genie-mcp-server","status":"https://wellknown.network/api/v1/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/status","claim":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-vivian-xie-db-genie-mcp-server/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-vivian-xie-db-genie-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_vivian-xie-db-genie_mcp_server","summary":"Genie MCP Server - A server for interacting with Databricks Genie via MCP StreamableHTTP Protocol","description":"# Genie MCP Server\n\nThis project provides an async server for interacting with Databricks Genie via a MCP StreamableHTTP Protocol. It enables users to query Genie and receive answers or data, leveraging Databricks authentication and robust error handling.\n\n## Features\n\n- Async API server using Starlette and Uvicorn\n- Integration with Databricks Genie for conversational queries\n- Automatic OAuth token management for Databricks\n\n## Project Structure\n\n- `mcp_server.py`: Main server entry point, exposes the tool via MCP StreamableHTTP Protocol.\n- `genie_room.py`: Handles Genie API interactions and conversation logic.\n- `token_minter.py`: Manages Databricks OAuth token minting and refreshing.\n- `requirements.txt`: Python dependencies.\n- `app.yaml`: Example deployment configuration.\n\n## Deploying to Databricks Apps\n\nYou can deploy the Genie MCP Server as a Databricks app by following these steps:\n\n1. **Clone the Repository to Your Workspace**\n\n   In your Databricks workspace, navigate to the directory where you want to deploy the app (e.g., `/Workspace/Users/your.email@databricks.com/genie_mcp_server`). Then, clone the repository:\n\n   ```bash\n   git clone https://github.com/your-org/genie_mcp_server.git\n   ```\n\n2. **Configure the Genie Space ID and Other Environment Variables**\n\n   Open the `app.yaml` file in the root of the cloned repository. Update the `SPACE_ID` value to match your Genie space. \n\n   Example `app.yaml`:\n\n   ```yaml\n   command:\n   - \"python\"\n   - \"mcp_server.py\"\n\n   env:\n   - name: \"SPACE_ID\"\n     value: \"your_space_id\"\n   ```\n\n3. **Create and Deploy the App in Databricks**\n\n   - Go to the Databricks Apps interface.\n   - Create a new app and specify the path to the directory where you cloned the repository.\n   - Complete the app creation and deployment process.\n   ```databricks apps deploy genie-mcp-server --source-code-path /Workspace/Users/your.email@databricks.com/genie_mcp_server```\n\n4. **Access the API**\n\n   Once deployed, your Genie MCP Server app…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_vivian-xie-db-genie_mcp_server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.836,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.825,"provenance":"derived"}],"categories":["dev","security"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_vivian-xie-db-genie_mcp_server","registry":"pypi","observedAt":"2026-09-15T20:21:35.051Z","publishedAt":"2026-01-26T08:36:53.457035Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_vivian-xie-db-genie_mcp_server","url":"https://pypi.org/project/iflow-mcp_vivian-xie-db-genie_mcp_server/","firstSeenAt":"2026-09-09T21:24:49.666Z","fetchedAt":"2026-09-15T20:20:32.548Z","normalizedAt":"2026-09-15T20:20:32.548Z"}]},"firstSeenAt":"2026-09-09T21:24:49.666Z","updatedAt":"2026-09-15T20:21:35.051Z"}