{"version":"2.1.323","anchor":"mcp-tasks-poller-handoff-polledby-serviceclient-added-to","canonical_anchor":"mcp-tasks-poller-handoff-polledby-serviceclient-added-to","heading":"Long-running MCP tasks can now record who is checking on them","tier":"internal","area":"MCP","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/mcp-tasks-poller-handoff-polledby-serviceclient-added-to","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Long-running MCP tasks can now record who is checking on them\n\nRecords of long-running MCP tasks now note whether a service or Claude Code itself is checking for progress, with handoff details\n\n**What**\n\nSome MCP servers, add-ons that give Claude Code extra tools, can run long tasks in the background. Claude Code used to check on such a task by asking the server directly, again and again (this is called polling). Task records now note who does that checking:\n\n- Whether a service or Claude Code itself (the client) is polling.\n\n- Offers to take over polling, when polling started and whether it stopped.\n\n- Times a poller gave up.\n\n- A \"not taken\" result when Claude Code keeps polling itself.\n\nThe polling loop can now wait on another poller and send extra request headers. When a task ends, follow-up steps can be queued to run afterwards. A check for servers that are not configured is skipped while another poller is in charge.\n\n**Why**\n\nThis looks like a way to hand polling of long MCP tasks to a service, so Claude Code would no longer need to keep checking on them itself.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}