What LLM providers are supported?
Mcpixir works with any LLM that supports tool calling, including OpenAI, Anthropic, and Groq. You must configure the corresponding API keys.
@ramonlimaramos
基本信息
🌐 Mcpixir is the open source way to connect any LLM to any MCP server and build custom agents that have tool access, without using closed source or application clients.
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。
Mcpixir is an open-source Elixir library that lets developers connect any LLM supporting tool calling to any MCP server, enabling custom agents with tool access for web browsing, file operations, and more. It is designed for Elixir developers building agent-based applications.
Add mcpixir to your mix.exs dependencies, configure LLM provider API keys (e.g., OPENAI_API_KEY), then create an MCP client, configure your LLM, create an agent, and run queries—all in about six lines of code. Use Mix tasks like mix mcpixir.chat to quickly test examples.
Mcpixir works with any LLM that supports tool calling, including OpenAI, Anthropic, and Groq. You must configure the corresponding API keys.
Yes. Mcpixir supports multi-server configuration. An agent can access tools from all configured servers, and dynamic server selection can be enabled to choose the best server per task.
You can provide a list of disallowed tool names when creating the agent (e.g., `disallowed_tools: ["file_system", "network"]`) to control what the agent can use.
Yes. Mcpixir can connect to MCP servers via HTTP using SSE endpoints, configured via the `url` field in the server configuration.
Elixir 1.15 or later, and API keys for the chosen LLM provider. The library is available on Hex.pm.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

Turn a plain-language guide into a narrated walkthrough video of your deployed web app. Your coding agent can write the guide from the source and bring back the MP4.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

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