You'll noticeTier: how much it should matter to you
3Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
MCPArea: what it touches
ImprovementsKind: in v2.1.282,
ImprovementsSection of the release
What
MCP (Model Context Protocol, the standard Claude Code uses to connect to outside tools) requests carry a block of extra information called _meta. When a subagent (a helper agent that the main session starts to handle part of a task) calls a tool on a qualifying MCP server, that block now also includes:
claudecode/agentId, the subagent's ID
claudecode/agentType, the kind of subagent, cut to at most 128 characters
claudecode/isObserver, added when the subagent was started, directly or further up the chain, by an observer-type task
Calls made by the main session are unchanged. This applies to only one specific server that Claude Code has built in, not to every MCP server, and it covers both ways Claude Code makes MCP tool calls.
Why
The receiving server can now tell which subagent made each call instead of seeing them all as coming from the same session.
Read from
Names in the bundle_meta
Since it was published
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Confirmed sinceAnthropic's documentation has since written up _meta, on Authentication for connectors.* Support CIMD instead. Claude selects CIMD only when your authorization server metadata advertises both `"client_id_metadata_document_supported": true` and `"none"` in `token_endpoint_auth_methods_supported`. The second is required becaus…connectors/building/authenticationsee the edit
How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtIt is not clear exactly which MCP server qualifies for this extra information.
Anthropic's documentation agreesAnthropic's documentation has since written up _meta, on Authentication for connectors.
