{"version":"2.1.282","anchor":"mcp-tool-calls-to-the-claudeai-server-now-carry-subagent-id","canonical_anchor":"mcp-tool-calls-to-the-claudeai-server-now-carry-subagent-id","heading":"MCP tool calls from subagents now say which subagent made them","tier":"notice","area":"MCP","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.282\/e\/mcp-tool-calls-to-the-claudeai-server-now-carry-subagent-id","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.282","markdown":"### MCP tool calls from subagents now say which subagent made them\n\nWhen a subagent calls a tool on certain MCP servers, the request now includes that subagent's ID, its type, and whether it is an observer\n\n**Unclear.** It is not clear exactly which MCP server qualifies for this extra information.\n\n**What**\n\nMCP (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:\n\n- `claudecode\/agentId`, the subagent's ID\n\n- `claudecode\/agentType`, the kind of subagent, cut to at most 128 characters\n\n- `claudecode\/isObserver`, added when the subagent was started, directly or further up the chain, by an observer-type task\n\nCalls 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.\n\n**Why**\n\nThe receiving server can now tell which subagent made each call instead of seeing them all as coming from the same session.\n\n- Area: MCP\n- Names: `_meta`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5"}