You authorize remote MCP with OAuth, client credentials, or enterprise policy while keeping application identity separate. URL validation and SSRF protections stay enabled.
10 focused minutesNot started
Unit example (nearest native match)
See the idea in context
let transport = AxMCPStreamableHTTPTransport::new(endpoint, json!({}))?;
let mcp = Arc::new(Mutex::new(AxMCPClient::new(
Box::new(transport),
json!({"namespace":"inventory"}),
)));
let context = AxExecutionContext::new(vec![mcp.clone()], vec![])?;
let catalog = mcp.lock().unwrap().inspect_catalog(false)?;
println!("MCP catalog: {} tools, {} resources, {} templates",
catalog.tools.len(), catalog.resources.len(),
catalog.resource_templates.len());
let mut program = ax("request:string -> answer:string")?.with_execution_context(context)?;
let mut llm = OpenAICompatibleClient::new(key, "gpt-5.4-mini");
println!("{}", program.forward(
&mut llm, json!({"request":"Reindex inventory."}),
)?);
mcp.lock().unwrap().close()?;
Run itIn your own project
cargo add axllm
use axllm::{ai, ax};
use serde_json::json;
let llm = ai("openai", json!({"apiKey": std::env::var("OPENAI_API_KEY")?}))?;
let classify = ax("review:string -> sentiment:class \"positive, negative, neutral\"")?;
Set OPENAI_APIKEY in your environment before running provider-backed code.
In the ax repo
From a clone of the ax repo:
npm run example -- rust src/examples/rust/mcp/native_mcp_tools.rs