llms-client
Rust library for Gemini, chatGPT, etc. with automatic context management
Links
README
From the repo.
Gemini
Installation
cargo add gemini-client-api
view at crate.io
Overview
A Rust library to use Google's Gemini API with macro super powers! It is extremely flexible and modular to integrate with any framework.
For example, since Actix supports stream of Result<Bytes, Error> for response streaming, you can get it directly instead of making a wrapper stream around a response stream of futures, which is a pain.
Features
- Automatic context management
- Automatic function calling. Trust me!
- Automatic JSON schema generation
- Inbuilt markdown to parts parser enables AI to see markdown images or files, even if they are from your device storage!
- Vision to see images
- Code execution by Gemini
- File reading like PDF or any document, even audio files like MP3
- Function call support
- Thinking and Safety setting
- Context Caching
- Supports Session management in WASM environment with
default-features = false
TODO
- Do the same for OpenAI
Collected info
- ★ 25 stars
- ⎇ 6 forks
- Language: Rust
- Source updated: 9/1/2026
Config for your environment
Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.
Tool
OS
Config file: ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"url": "{MCP_ENDPOINT_URL}"
}
}
}Paste into mcpServers in the config file. Restart Cursor after saving.
If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.