Request customizers can't tell which connection a request belongs to

[iuliiasobolevska]

Expected Behavior

A request customizer should be able to find out which configured connection the request it is customizing belongs to.

The cheaper option is a well-known key in the transport context, seeded by the transport, so no signature changes:

Publisher<HttpRequest.Builder> customize(HttpRequest.Builder builder, String method, URI endpoint,
        String body, McpTransportContext context) {
    String connection = (String) context.get(McpTransportContext.CONNECTION_NAME);
    builder.setHeader("Authorization", tokenFor(connection));
    return Mono.just(builder);
}

The transport already knows the name when it is built, so it would set it once in the builder and merge it into whatever context the caller supplied.

The other option is to put it in the signature:

Publisher<HttpRequest.Builder> customize(String connectionName, HttpRequest.Builder builder, String method,
        URI endpoint, String body, McpTransportContext context);

This is breaking, but it lines up with McpClientCustomizer#customize(String name, T spec) in Spring AI, which already takes the name first. If the interface is going to change shape at some point anyway, that's the more consistent end state.

Current Behavior

A request customizer runs for every outbound HTTP request on a transport, but isn't told which connection the request belongs to. On main at fd00498:

// McpAsyncHttpClientRequestCustomizer:27
Publisher<HttpRequest.Builder> customize(HttpRequest.Builder builder, String method, URI endpoint,
        @Nullable String body, McpTransportContext context);

The only discriminator available is the endpoint URI. There is no connection name in the context either: nothing in mcp-core defines or sets one, and the transport passes the caller's context through untouched. HttpClientStreamableHttpTransport reads it the same way on all four request paths, at lines 205, 291, 430, and 514:

var transportContext = ctx.getOrDefault(McpTransportContext.KEY, McpTransportContext.EMPTY);
return Mono.from(this.httpRequestCustomizer.customize(builder, "POST", uri, jsonBody, transportContext));

So a customizer that needs per-connection behavior has to build its own URL-to-name map and reverse-match on the endpoint for every request. That map has to be assembled by re-reading the same configuration that the framework already parsed, and the match breaks as soon as a URL is templated, redirected, or differs by a trailing slash.

The name is known at the point the customizer is installed, since the transport is built per connection. It just isn't carried through to the call.

Context

Callers configure connections by name. In Spring AI, for example:

spring.ai.mcp.client.streamable-http.connections:
  first-server:
    url: https://...
  second-server:
    url: https://...

Anything per-connection needs that name: a different credential or audience per server, per-connection metrics, per-connection logging. We hit this with credentials, where each MCP server is a distinct audience, and the token must be minted for the correct one.

Alternatives considered:

• One customizer instance per connection, closing over the name, installed by whoever builds the transport. This is what we do today. It works, but it only works for the party that owns the builder, and it interacts badly with the single-customizer-slot problem (Allow composing request customizers on the HTTP client transport builders #1073).
• A URL to name map inside the customizer, reverse-matched on endpoint. Fragile for the reasons above, and it duplicates configuration parsing.
• Putting the name into the caller's context at the call site. Requires every caller to know which connection a given client operation will reach, which they generally don't.

Is there a reason the connection name was deliberately omitted from the customizer contract? I might be missing something.