mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-03 21:02:38 +00:00
51945f1e57
The most interesting MCP servers are those with an authorization wall in
front of them. This PR uses the existing `provider_data` mechanism of
passing provider API keys for passing MCP access tokens (in fact,
arbitrary headers in the style of the OpenAI Responses API) from the
client through to the MCP server.
```
class MCPProviderDataValidator(BaseModel):
# mcp_endpoint => list of headers to send
mcp_headers: dict[str, list[str]] | None = None
```
Note how we must stuff the headers for all MCP endpoints into a single
"MCPProviderDataValidator". Unlike existing providers (e.g., Together
and Fireworks for inference) where we could name the provider api keys
clearly (`together_api_key`, `fireworks_api_key`), we cannot name these
keys for MCP. We have a single generic MCP provider which can serve
multiple "toolgroups". So we use a dict to combine all the headers for
all MCP endpoints you may want to use in an agentic call.
## Test Plan
See the added integration test for usage.
|
||
|---|---|---|
| .. | ||
| agents | ||
| datasetio | ||
| eval | ||
| inference | ||
| post_training | ||
| safety | ||
| tool_runtime | ||
| vector_io | ||
| __init__.py | ||