{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/productivity.read-channel/",
    "json": "https://www.anchorterminal.com/niches/productivity.read-channel/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/productivity.read-channel/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/productivity.read-channel/index.min.md"
  },
  "markdown": "Two or three companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 2 | 2 | 6 | 17 | 5 |\n\n## What counts as done\n\nEvery message in the window returned in order with authors and thread replies, paged to completion, and private channels or DMs excluded unless the user asked for them.\n\nMeasured, for our own tests: paging to completion without hitting throttling.\n\nHow agents ask for it: catch me up on #incident; what did I miss in this chat; summarise this thread; export this Teams chat\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Mattermost (Mattermost, Inc.)**: GET /channels/{id}/posts pages with page and per_page (up to 200), before and after post ids or since a time, and GET /posts/{id}/thread returns replies in order. A bot sees only channels it is added to.\n- **Zulip (Kandra Labs, Inc.)**: GET /messages pages a channel or topic in order from an anchor (oldest, newest or a message id) with num_before and num_after, and topics act as threads, so a window pages to completion.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Microsoft Teams (Microsoft Graph) (Microsoft Corporation)**: List channel messages pages with $top up to 50 and @odata.nextLink, with replies via $expand or their own nextLink past 200. acc-24 found chat endpoints throttled aggressively, and the delegated read permission is ChannelMessage.Read.All.\n- **Slack MCP Server (official) (Slack Technologies, LLC (a Salesforce company))**: Read a channel and read a thread return the complete history, at Tier 3 (50+ a minute), and DMs and private channels need their own history scopes. Unlisted clients are barred, so only Marketplace or internal apps reach it (acc-06).\n\n- not this job: Atlassian Rovo MCP Server (Atlassian Pty Ltd): The server covers Jira, Confluence, JSM, Bitbucket, Loom and the Teamwork Graph; it has no chat channel or thread history tools.\n- not this job: Linear MCP (Linear Orbit, Inc.): Linear is an issue tracker; it has no chat channels or threads to read beyond issue comments.\n- not this job: Notion MCP (Notion Labs, Inc.): Notion has no chat channels; connector search can query Slack on paid AI plans but does not page a channel's history in order.\n- not this job: Outline (General Outline, Inc.): No chat channels exist; document comments are the only threads.\n\n## What stops agents finishing\n\n- tenant admin consent needed for Graph chat scopes\n- chat read throttled before the history is complete\n- only listed partner clients may connect (Slack)\n\n## Around it\n\nBefore: chat.user-request. After: productivity.write-doc, productivity.file-issue.\n\n## Where this comes from\n\nWeight 17 of 100 in Work \u0026 productivity: 5 of 36 accounts: a shared read-only Slack bot, Slack context for status, Teams export blocked by admin consent, Teams chat throttling, a Graph unread-message poller\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/productivity.read-channel.json, or the MCP tool get_use_case with id productivity.read-channel. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Read and summarise a channel, chat or thread",
        "url": ""
      }
    ],
    "description": "Read and summarise a channel, chat or thread: 2 companies fully do it, 2 with a limit, 6 carry the tag. Every listing in Work \u0026 productivity with the reason and a source.",
    "facts": null,
    "h1": "Read and summarise a channel, chat or thread",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/productivity.read-channel/",
    "published": "",
    "section": "agents",
    "title": "Read and summarise a channel, chat or thread | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/productivity.read-channel/"
  },
  "tokens": {
    "markdown": 1000,
    "slim": 230
  },
  "version": 1
}
