{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4uxs8nz269n2","handle":"iflow-mcp-angrysky56-gemini-mcp-client","url":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client","links":{"self":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client/record.json","html":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client","markdown":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-angrysky56-gemini-mcp-client","status":"https://wellknown.network/api/v1/agents/iflow-mcp-angrysky56-gemini-mcp-client/status","claim":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-angrysky56-gemini-mcp-client/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-angrysky56-gemini-mcp-client/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-angrysky56-gemini-mcp-client/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-angrysky56-gemini-mcp-client","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_angrysky56-gemini-mcp-client","summary":"Gemini-powered MCP (Model Context Protocol) Client","description":"# MCP Gemini Client\n\nCredit to and started from- [medium.com/@fruitful2007/building-an-mcp-client-101-lets-build-one-for-a-gemini-chat-agent](https://medium.com/@fruitful2007/building-an-mcp-client-101-lets-build-one-for-a-gemini-chat-agent-37f9308a802b)\n\n[pypi.org/project/gemini-tool-agent](https://pypi.org/project/gemini-tool-agent/)\n\nA (potentially, lol) powerful MCP (Model Context Protocol) client that uses Google's Gemini AI models for intelligent tool usage and conversation handling.\n- Tested working nicely with Claude Desktop as an MCP Server currently.\n\n### Based on untested AI gen code by a non-coder use at own risk.\n\n## Features\n\n- **Multiple Gemini Models**: Support for various Gemini models (2.0-flash, 2.5-pro, 1.5-pro, etc.)\n- **Flexible Package Support**: Works with gemini-tool-agent, google-generativeai, or google-genai packages\n- **Runtime Model Switching**: Change models during conversation\n- **Server Configuration Management**: Store and manage MCP server configurations\n- **Intelligent Tool Usage**: AI-powered tool discovery and execution\n- **Async/await Support**: Efficient concurrent operations\n- **Comprehensive Error Handling**: Robust error recovery and logging\n- **Type Hints**: Modern Python practices with full type safety\n\n![alt text](image-1.png)\n\n![alt text](image-2.png)\n\nUsing \"adk web\" from agents directory- alter the agent.py paths to your own for simple Gemini mcp use for now until I get a better setup.\nfull_mcp_agent-README.md\n![alt text](image-3.png)\n\n![alt text](image-4.png)\n\n[google agent framework report text](https://github.com/angrysky56/deep-research-reports/blob/main/Google%20Agent%20Development%20Documentation%20Full.txt)\n\n## Installation\n\n📋 Easy Installation Instructions\nHere's the correct way to set it up with Claude- maybe, You may need to install this if not working properly:\n- cd /gemini-mcp-client && uv add google-generativeai\n\nDoesn't throw an error and works great for chat, not sure about Gemini MCP use.\nJust edit in…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_angrysky56-gemini-mcp-client","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"ai.agent-discovery","name":"Agent Discovery","confidence":0.882,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["ai","dev"],"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_angrysky56-gemini-mcp-client","registry":"pypi","observedAt":"2026-11-03T05:27:01.138Z","publishedAt":"2026-02-07T07:35:05.748796Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_angrysky56-gemini-mcp-client","url":"https://pypi.org/project/iflow-mcp_angrysky56-gemini-mcp-client/","firstSeenAt":"2026-09-09T18:20:15.624Z","fetchedAt":"2026-11-03T05:25:52.325Z","normalizedAt":"2026-11-03T05:25:52.325Z"}]},"firstSeenAt":"2026-09-09T18:20:15.624Z","updatedAt":"2026-11-03T05:27:01.138Z"}