What are the prerequisites to run the agent?
Python 3.9 or higher, Git, a virtual environment (recommended), and Node.js for MCP.
@gokborayilmaz
基本信息
This AI agent analyzes code repositories, detects potential security vulnerabilities, reviews code quality, and suggests fixes based on Sentry error logs using Sentry and GitHub MCP servers!
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This AI agent analyzes code repositories, detects potential security vulnerabilities, reviews code quality, and suggests fixes based on Sentry error logs. It integrates with GitHub and Sentry MCP servers, and is part of the "A New AI Agent Every Day!" series.
Install prerequisites (Python 3.9+, Git, virtual environment, Node.js for MCP), clone the repository, install dependencies with pip install -r requirements.txt, and create a .env file with Azure OpenAI, GitHub, and Sentry tokens. Start the FastAPI server with uvicorn upsonicai:app --reload and open the UI at http://127.0.0.1:8000/. Configure MCP servers by adding GitHub and Sentry entries to your MCP configuration file.
Python 3.9 or higher, Git, a virtual environment (recommended), and Node.js for MCP.
You need to set `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_API_VERSION`, `AZURE_OPENAI_API_KEY`, `GITHUB_PERSONAL_ACCESS_TOKEN`, and `SENTRY_AUTH_TOKEN` in a `.env` file.
Run `uvicorn upsonicai:app --reload` in the project root, then open `http://127.0.0.1:8000/` in your browser.
Modify your MCP configuration to include a `github` server using `npx` and a `sentry` server using `python -m mcp_server_sentry`, each with the appropriate token.

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app


Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
评论