{
  "listings": [
    {
      "slug": "gorgias",
      "name": "Gorgias API + MCP",
      "company": "Gorgias Inc.",
      "grade": "C",
      "fit": "yes",
      "why": "get_reporting_stats and ticket_pattern_breakdown group tickets by contact reason, messages carry stripped_text, and add_internal_note writes back.",
      "source": "https://docs.gorgias.com/en-US/explore-gorgias-mcp-tools-9131180",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/gorgias"
    },
    {
      "slug": "helpdesk",
      "name": "HelpDesk",
      "company": "Text, Inc.",
      "grade": "D",
      "fit": "yes",
      "why": "About thirty report endpoints cover new tickets, status, response and resolution time, tickets page by cursor, and a private message writes the summary back. Calls are metered against the Text plan.",
      "source": "https://www.text.com/docs/api/ticketing/openapi.json",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/helpdesk"
    },
    {
      "slug": "intercom",
      "name": "Intercom API + MCP",
      "company": "Intercom, Inc. (with Intercom R\u0026D Unlimited Company in Ireland)",
      "grade": "BB",
      "fit": "yes",
      "why": "Conversations page by cursor, reporting data exports run as jobs, and add_internal_note writes the summary back without reaching the customer.",
      "source": "https://raw.githubusercontent.com/intercom/Intercom-OpenAPI/main/descriptions/2.17/api.intercom.io.yaml",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/intercom"
    },
    {
      "slug": "kustomer",
      "name": "Kustomer",
      "company": "Kustomer, LLC",
      "grade": "D",
      "fit": "yes",
      "why": "Search with field selection pages conversations, AI summaries can be fetched in batches, and notes write a summary back.",
      "source": "https://developer.kustomer.com/api/core-resources/create-customer-search.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/kustomer"
    },
    {
      "slug": "plain",
      "name": "Plain API + MCP",
      "company": "Not Just Tickets Ltd",
      "grade": "B",
      "fit": "yes",
      "why": "Threads page by cursor with chosen fields, and notes write the summary back; the MCP server suggests precisely this summary prompt.",
      "source": "https://www.plain.com/docs/integrations/mcp-server.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/plain"
    },
    {
      "slug": "pylon",
      "name": "Pylon API + MCP",
      "company": "Pylon Labs, Inc.",
      "grade": "C",
      "fit": "yes",
      "why": "Issues and their messages page by cursor, search narrows by filter, and /issues/{id}/note writes the summary back as an internal note.",
      "source": "https://docs.usepylon.com/pylon-docs/developer/api/api-reference/issues.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/pylon"
    },
    {
      "slug": "zendesk",
      "name": "Zendesk Support API",
      "company": "Zendesk, Inc.",
      "grade": "B",
      "fit": "yes",
      "why": "Incremental ticket export and search export page to completion, search/count gives counts, and an internal note carries the summary back; acc-12 runs such a monitoring agent.",
      "source": "https://developer.zendesk.com/zendesk/oas.yaml",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/zendesk"
    },
    {
      "slug": "chatway-mcp",
      "name": "Chatway MCP",
      "company": "Poptin Ltd",
      "grade": "C",
      "fit": "caveat",
      "why": "The insights skill pages list-conversations at up to 100 and reads messages by cursor, with add-note for write-back, but it warns of sampling and pagination truncation, and Free keeps 30 days.",
      "source": "https://github.com/Chatway-app/chatway-mcp-server/blob/HEAD/skills/chatway-support-insights/SKILL.md",
      "confidence": "low",
      "url": "https://www.anchorterminal.com/tools/chatway-mcp"
    },
    {
      "slug": "chatwoot",
      "name": "Chatwoot API",
      "company": "Chatwoot Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "Paged conversation lists, messages and report endpoints (counts by inbox, label matrix) exist, and a private note can carry the summary, but cloud rate limits are unpublished and records have no field selection.",
      "source": "https://developers.chatwoot.com/llms.txt",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/chatwoot"
    },
    {
      "slug": "crisp",
      "name": "Crisp API + MCP",
      "company": "Crisp IM SAS",
      "grade": "D",
      "fit": "caveat",
      "why": "Conversations and messages page through REST and a note carries the summary back, but pages stop at 50 and the daily token quotas limit how many conversations one run can read.",
      "source": "https://docs.crisp.chat/references/rest-api/v1/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/crisp"
    },
    {
      "slug": "dixa",
      "name": "Dixa",
      "company": "Dixa ApS",
      "grade": "D",
      "fit": "caveat",
      "why": "Messages, notes and activity logs are readable and a note writes back, but paging uses opaque pageKey at 10 requests a second per token, slow for thousands of conversations.",
      "source": "https://docs.dixa.io/openapi-specs/dixa-v1.yaml",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/dixa"
    },
    {
      "slug": "drag",
      "name": "Drag",
      "company": "DragApp.com Ltd",
      "grade": "E",
      "fit": "caveat",
      "why": "get_thread reads a thread, analytics tools give response times and daily activity, and add_comment writes back; how far list_threads pages was not documented.",
      "source": "https://www.dragapp.com/docs/mcp/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/drag"
    },
    {
      "slug": "freescout",
      "name": "FreeScout",
      "company": "FreeScout",
      "grade": "F",
      "fit": "caveat",
      "why": "Conversations page up to 100 at a time with threads embedded, Get Report gives queue figures, and a note thread writes back; no rate limits are documented, so pacing depends on the operator's server.",
      "source": "https://api-docs.freescout.net/",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/freescout"
    },
    {
      "slug": "freshdesk",
      "name": "Freshdesk API + MCP",
      "company": "Freshworks Inc.",
      "grade": "D",
      "fit": "caveat",
      "why": "Conversations return body_text and a private note carries the summary, but ticket lists stop at 300 pages and closed tickets archive after 120 days of inactivity.",
      "source": "https://developers.freshdesk.com/api/",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/freshdesk"
    },
    {
      "slug": "front",
      "name": "Front API + MCP",
      "company": "FrontApp, Inc.",
      "grade": "BB",
      "fit": "caveat",
      "why": "read_conversation returns the whole timeline and read_message strips quoted replies; add_comment writes the summary back. Bulk counts mean paging at 50 requests a minute on Starter.",
      "source": "https://dev.frontapp.com/docs/mcp-server.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/front"
    },
    {
      "slug": "gladly",
      "name": "Gladly",
      "company": "Gladly Software, Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "The Export API sends conversations as daily files and a note can carry a summary back, but files are removed after 14 days and reports allow 10 calls a minute.",
      "source": "https://developer.gladly.com/llms-full.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/gladly"
    },
    {
      "slug": "help-scout",
      "name": "Help Scout API + MCP",
      "company": "Help Scout PBC",
      "grade": "B",
      "fit": "caveat",
      "why": "Reports endpoints (volumes, productivity, drilldowns) and paged conversation lists cover the queue, and Create Note writes back, but reports need Plus or Pro and each v3 search counts double.",
      "source": "https://developer.helpscout.com/llms.txt",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/help-scout"
    },
    {
      "slug": "liveagent",
      "name": "LiveAgent",
      "company": "Quality Unit, s. r. o.",
      "grade": "D",
      "fit": "caveat",
      "why": "get_ticket_summary returns an AI summary on personal connections and add_note writes back, but v3 GET /tickets returns at most 10,000 tickets per filter and rate-limit responses are undocumented.",
      "source": "https://support.liveagent.com/578762-MCP-tools-reference",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/liveagent"
    },
    {
      "slug": "missive",
      "name": "Missive API + MCP",
      "company": "Heliom Inc.",
      "grade": "C",
      "fit": "caveat",
      "why": "Analytics reports, message and comment lists, and posts for writing a summary back exist, but message bodies come only from Get a Message, one at a time.",
      "source": "https://missiveapp.com/docs/developers/rest-api/endpoints.md",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/missive"
    },
    {
      "slug": "zammad",
      "name": "Zammad",
      "company": "Zammad GmbH",
      "grade": "E",
      "fit": "caveat",
      "why": "POST /tickets/{id}/summarize returns a summary, but acc-29 hit JSON parse errors on German quotation marks and acc-30 truncation from a hardcoded 1,024 max_tokens, both open. Paging has hard per-page limits.",
      "source": "https://docs.zammad.org/en/latest/api/ticket/ticket-summary.html",
      "confidence": "high",
      "url": "https://www.anchorterminal.com/tools/zammad"
    },
    {
      "slug": "zoho-desk",
      "name": "Zoho Desk",
      "company": "Zoho Corporation Private Limited",
      "grade": "B",
      "fit": "caveat",
      "why": "Threads, metrics and counts are readable and a private comment carries the summary back, but lists page 50 at a time and deep offsets cost up to 100 credits a call against a daily allowance.",
      "source": "https://raw.githubusercontent.com/zoho/zohodesk-oas/master/v1.0/Ticket.json",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/zoho-desk"
    },
    {
      "slug": "landbot-mcp",
      "name": "Landbot MCP server",
      "company": "Landbot",
      "grade": "E",
      "fit": "no",
      "why": "No conversation, transcript or reporting tool is in the tool list.",
      "source": "https://dev.landbot.io/guides/mcp-server",
      "confidence": "medium",
      "url": "https://www.anchorterminal.com/tools/landbot-mcp"
    }
  ],
  "marks": "yes: the docs show it does the job as the success test says. caveat: it does the job with a limit an agent should know. no: it doesn't do this job. unchecked: we couldn't read it.",
  "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"
  },
  "useCase": {
    "accounts": 6,
    "after": [
      "knowledge.write-article",
      "messaging.slack-notify"
    ],
    "area": "business",
    "asks": [
      "summarise this thread",
      "what are the top issues this week",
      "categorise our ticket history",
      "are we falling behind on tickets"
    ],
    "before": [
      "support.research-context"
    ],
    "blockers": [
      "model output rejected by the helpdesk's parser or truncated by a fixed token limit",
      "pagination caps below the number of tickets wanted",
      "each v3 search counts double against the limit"
    ],
    "capabilities": [
      "support.tickets",
      "support.conversations",
      "support.notes"
    ],
    "category": "support",
    "categoryName": "Customer support \u0026 helpdesk",
    "checked": "2026-11-12",
    "companies": {
      "fit": 7,
      "fitWithLimit": 14,
      "tagged": 21
    },
    "competition": "crowded",
    "fits": [
      "gorgias",
      "helpdesk",
      "intercom",
      "kustomer",
      "plain",
      "pylon",
      "zendesk"
    ],
    "fitsWithLimit": [
      "chatway-mcp",
      "chatwoot",
      "crisp",
      "dixa",
      "drag",
      "freescout",
      "freshdesk",
      "front",
      "gladly",
      "help-scout",
      "liveagent",
      "missive",
      "zammad",
      "zoho-desk"
    ],
    "id": "support.summarise-and-report",
    "listings": {
      "caveat": 14,
      "no": 1,
      "notRead": 0,
      "tagged": 21,
      "unchecked": 0,
      "yes": 7
    },
    "name": "Summarise tickets and report on the queue",
    "status": "draft",
    "success": "A summary that names the open questions, or a category table with counts, produced from paged calls without exceeding the rate limit, and written back as a note or left outside the helpdesk. Measured: the summary is under 200 words.",
    "url": "https://www.anchorterminal.com/api/v1/use-cases/support.summarise-and-report.json",
    "weight": 12,
    "weightBasis": "6 of 42 accounts (acc-11, 12, 13, 29, 30, 34); read-only MCP vendors name this as their first use case"
  }
}
