Category · Work & business apps
Customer support and helpdesk APIs for AI agents
Helpdesks and shared inboxes an agent can work in. Tickets, conversations, contacts, notes and statuses. Compared on permissions, safe handoff to a person, audit trail and API coverage.
Best customer support and helpdesk APIs for AI agents, the shortlist211 head-to-head comparisons
Capability keys support.tickets · support.conversations · support.contacts · support.notes · support.webhooks · All tools
letme.dev/support.tickets picks the top-graded tool in this list and says how to call it direct (how letme works).
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/search
Filters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 149 | Intercom API + MCPIntercom · HTTP API | Support | BB | 74.2 | 4.0 (2) | n/a | n/a | $29 / seat-mo | OAuth or key | Hosted | ||
|
Intercom's REST API (conversations, contacts, companies, tickets, notes, tags, articles, data attributes and webhooks) and its official hosted MCP server. Top strength Versioned OpenAPI per API version, 259 operations in 2.17, every one described Top weakness MCP can't reply, assign, snooze or close, those need the REST API |
||||||||||||
| 301 | Front API + MCPFront · HTTP API | Support | BB | 70.1 | 4.0 (2) | n/a | n/a | $25 / seat-mo | OAuth or key | Hosted | ||
|
Front's Core API for its shared inbox (conversations, messages, drafts, comments, tags, contacts, accounts, inboxes, teammates and webhooks) and its official hosted MCP server at https://mcp.frontapp.com/mcp. Top strength MCP sending needs its own Top weakness MCP needs your own OAuth app with a client secret, no Dynamic Client Registration |
||||||||||||
| 340 | Zendesk Support APIZendesk · HTTP API | Support | B | 69.3 | 3.5 (2) | n/a | n/a | $19 / seat-mo | OAuth or key | Local | ||
|
REST API for Zendesk Support. Top strength OAuth 2.0 with read, write and per-resource scopes, expiring tokens and revocation endpoints Top weakness No documented MCP server; the /api/mcp endpoint has no public docs or tool list |
||||||||||||
| 348 | Zoho DeskZoho · HTTP API | Support | B | 69.1 | 3.5 (4) | n/a | n/a | $7 / seat-mo | OAuth | Local | ||
|
Zoho Desk is a hosted helpdesk from Zoho for tickets, contacts, knowledge base articles and support channels. Agents reach it through the REST API v1 behind OAuth 2.0, described in public OpenAPI 3.1 files. Top strength OpenAPI 3.1 files for 210 resources and 1,077 operations are public on GitHub, last changed on 29 October 2026 Top weakness No SLA found, and the Terms of Service disclaim uninterrupted service |
||||||||||||
| 448 | Plain API + MCPPlain · HTTP API | Support | B | 67.1 | 4.5 (2) | n/a | n/a | $45 / seat-mo | OAuth or key | Hosted | ||
|
API-first B2B support platform. Top strength Machine-user API keys with fine-grained permissions and several keys per user for rotation Top weakness Rate limits aren't published, only the 429 and Retry-After behaviour via the SDK |
||||||||||||
| 657 | Help Scout API + MCPHelp Scout · HTTP API | Support | B | 62.6 | 3.0 (2) | n/a | n/a | $25 / seat-mo | OAuth | Hosted | ||
|
Help Scout's Inbox API 2.0 (conversations, threads, replies, notes, customers, mailboxes, tags, users, workflows, reports and webhooks) and its official hosted MCP server at https://mcp.helpscout.net/mcp, GA since July 2026. Top strength MCP server read-only for new connections and limited by each user's mailbox permissions Top weakness MCP can't write, so a draft, note and status loop needs the REST API |
||||||||||||
| 754 | Chatway MCPChatway (Poptin Ltd) · MCP server | Support | C | 60.4 | 3.3 (4) | n/a | n/a | $31 / mo | OAuth | Hosted | ||
|
Chatway MCP is the hosted MCP server for Chatway, a live chat and support inbox from Poptin Ltd. Assistants such as Claude and ChatGPT sign in by OAuth to read, reply to, tag, assign and resolve conversations. Top strength OAuth 2.1 with PKCE and dynamic client registration, so no key is pasted. Each connection is limited to chosen widgets, channels and 18 named permissions Top weakness No status page was found (status.chatway.app did not resolve on 17 October), no SLA, and the terms disclaim liability for downtime |
||||||||||||
| 846 | Pylon API + MCPPylon · HTTP API | Support | C | 58.2 | 2.0 (2) | n/a | n/a | Paid | OAuth or key | Hosted | ||
|
B2B support platform built around Slack, Teams and email channels, with a REST API over issues, accounts, contacts and messages, and an official hosted MCP server with 103 tools. Top strength Per-endpoint rate limits of 30 to 300 a minute, with Retry-After and backoff guidance Top weakness No self-serve trial; seats start at $89 on an annual contract |
||||||||||||
| 889 | Gorgias API + MCPGorgias · HTTP API | Support | C | 57 | 2.5 (2) | n/a | n/a | $10 / mo | OAuth or key | Hosted | ||
|
Helpdesk for ecommerce brands, priced by tickets rather than seats, with a REST API over tickets, messages, customers and integrations and an official hosted MCP server that acts with the user's Gorgias role. Top strength OAuth2 apps choose read or write per resource across 14 scope pairs Top weakness Private API keys use Basic auth with the user's email and have no scopes |
||||||||||||
| 967 | Missive API + MCPMissive · HTTP API | Support | C | 55.3 | none | n/a | n/a | $14 / seat-mo | OAuth or key | Hosted | ||
|
Missive is a shared team inbox for email, SMS, WhatsApp and live chat from Heliom Inc. of Quebec City. Agents reach it through a REST API at public.missiveapp.com/v1 or a hosted MCP server with OAuth permissions. Top strength MCP access uses OAuth with PKCE and eight permissions, with drafting and sending granted separately and ungranted tools hidden from the client Top weakness REST tokens are personal with no scopes and reach every account the user can open, shared accounts included |
||||||||||||
| 1008 | GladlyGladly Software, Inc. · HTTP API | Support | C | 54.1 | none | n/a | n/a | Paid | API key | Hosted | ||
|
Gladly is a customer service platform for retail and consumer brands that keeps one conversation timeline per customer across chat, email, SMS, voice and social channels. Its REST API covers customers, conversations, notes, tasks, topics, answers, reports and webhooks. Top strength Public OpenAPI 3.0.1 file with 87 operations, plus Top weakness An API token can make any API request without restriction, per the reference. No scopes and no read-only token |
||||||||||||
| 1059 | Chatwoot APIChatwoot · HTTP API | Support | D | 52.6 | 3.0 (2) | n/a | n/a | $19 / seat-mo | API key | Hosted | ||
|
Open-source omnichannel inbox with REST Application, Client and Platform APIs over conversations, contacts, messages and webhooks. Top strength MIT-licensed core you can self-host for free, same API as Chatwoot Cloud Top weakness No MCP server, official or hosted |
||||||||||||
| 1116 | LiveAgentQuality Unit, s. r. o. · HTTP API | Support | D | 51 | none | n/a | n/a | $15 / seat-mo | OAuth or key | Hosted | ||
|
LiveAgent is a hosted helpdesk from Quality Unit with ticketing, live chat, a call centre and a knowledge base. Agents reach it through a REST API with per-key permissions and a built-in MCP server on each account. Top strength Each v3 key draws on named permissions such as Top weakness API v3 has no operation to reply to a ticket or add a note. Those go through the legacy v1 API or the MCP server |
||||||||||||
| 1130 | KustomerKustomer, LLC · HTTP API | Support | D | 50.3 | none | n/a | n/a | $0.60 / tx | OAuth or key | Hosted | ||
|
Kustomer is a customer service CRM that keeps conversations, messages, notes and custom objects on one customer timeline. Agents reach it through a REST API and a read-only hosted MCP server. It is sold through sales. Top strength API keys take one or more of several hundred roles with read, create, update and delete levels, an expiry in days and an optional CIDR restriction Top weakness Plan prices are not published and no self-serve trial or signup was found, so a person has to go through sales |
||||||||||||
| 1170 | HelpDeskText, Inc. · HTTP API | Support | D | 48.9 | none | n/a | n/a | $19 / seat-mo | OAuth or key | Hosted | ||
|
HelpDesk is a ticketing system from Text, Inc. Its REST API at api.helpdesk.com, which Text also documents as the Ticketing API, creates, lists and updates tickets, messages, private notes, tags, teams, rules, reports and webhooks. Top strength OpenAPI 3.0.3 operations embedded in 133 Markdown method pages, linked from Text's llms.txt Top weakness No rate limit, 429 behaviour or idempotency key found in the docs |
||||||||||||
| 1174 | Freshdesk API + MCPFreshworks · HTTP API | Support | D | 48.8 | 3.0 (2) | n/a | n/a | $19 / seat-mo | API key | Local | ||
|
REST API (v2) for Freshdesk, the Freshworks helpdesk. Top strength Official MCP server GA since 10 September 2026, 37 tools covering tickets, replies, notes, contacts and solutions Top weakness MCP calls are metered, 1,200 a year on Growth, then $15 per 1,000 |
||||||||||||
| 1186 | Crisp API + MCPCrisp · HTTP API | Support | D | 48.1 | 2.5 (2) | n/a | n/a | $45 / mo | OAuth or key | Hosted | ||
|
Chat widget, shared inbox and helpdesk priced per workspace, with a REST API, RTM websocket API, webhooks and an official hosted MCP server at api.crisp.chat/mcp that reads and writes workspace data. Top strength Flat price per workspace, $45 a month for 4 seats on Mini, and a free plan with REST access Top weakness The MCP token holds the website tier with no scopes, and the docs allow it in a ?token= URL parameter |
||||||||||||
| 1202 | DixaDixa ApS · HTTP API | Support | D | 47.5 | none | n/a | n/a | Paid | API key | Hosted | ||
|
Dixa is a customer service platform for phone, email, chat and social channels. Outside agents reach it through the Dixa REST API and a beta MCP server, both authenticated with an administrator-issued API token. Top strength Public OpenAPI 3.0.3 file for API v1 with 126 operations, plus Top weakness No self-serve trial or free tier. The pricing page sends every buyer to a demo |
||||||||||||
| 1324 | DragDragApp.com Ltd · MCP server | Support | E | 41.8 | none | n/a | n/a | $24 / seat-mo | API key | Hosted and local | ||
|
Drag (DragApp) is a shared inbox for Gmail teams that turns addresses such as support@ into boards with assignment, WhatsApp and a help centre. Agents use its hosted MCP server of 47 tools or its REST API v2. Top strength 47 MCP tools, each with readOnlyHint and destructiveHint, and sends marked destructive Top weakness One API key with full workspace access; no scopes or read-only key |
||||||||||||
| 1340 | ZammadZammad GmbH · HTTP API | Support | E | 40.9 | 3.5 (4) | n/a | n/a | Freemium | OAuth or key | Hosted | ||
|
Zammad is an open-source helpdesk from Zammad GmbH in Berlin, sold hosted or run on the owner's servers. Its REST API under `/api/v1` covers tickets, articles, users, organisations, the knowledge base and webhooks. Top strength Access tokens are created with a chosen list of permissions and an optional expiry date, and the server records when each was last used Top weakness No OpenAPI or other machine-readable contract was found in the repository or the documentation, and no |
||||||||||||
| 1359 | Landbot MCP serverLandbot · MCP server | Support | E | 39.8 | none | n/a | n/a | Freemium | OAuth | Hosted | ||
|
Landbot's hosted MCP server lets an agent build, edit, test and publish Landbot chatbots, WhatsApp flows and AI agents, including their knowledge, integrations and web chat styling, over OAuth with published scopes. Top strength Builds, tests and publishes bots, WhatsApp flows and AI agents Top weakness No read-only mode; scripts:write allows custom JS on chat pages |
||||||||||||
| 1445 | FreeScoutFreeScout · HTTP API | Support | F | 27.9 | none | n/a | n/a | Freemium | API key | Local | ||
|
FreeScout is an open-source, self-hosted help desk and shared inbox in PHP under AGPL-3.0, modelled on Help Scout. A paid API & Webhooks module adds a REST API for conversations, customers, users, tags and time logs. Top strength AGPL-3.0 core, free to self-host, with releases every one to two weeks Top weakness API keys carry no scopes, and the docs offer an |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
Indexed, not reviewed (3)
Listings sorted into this category from public catalogues (the official MCP registry, APIs.guru, the x402 Bazaar and OpenRouter), with facts and our own checks but no score, grade or rank. How the index works.
| Listing | Kind | What it does | Why it's here |
|---|---|---|---|
| casemargin-mcp-server casemargin.com | MCP server | Turn a support ticket into a structured case brief, or score its L2 escalation readiness. | vendor's own |
| codmir.com MCP server codmir.com | MCP server | AI-powered task execution, tickets, sprints, error debugging, and desktop control. | vendor's own |
| NexTool MCP for GLPI nextoolsolutions.com | MCP server | MCP server for GLPI: tickets, ITIL, assets, knowledge base. GLPI 10/11. Not affiliated with Teclib'. | vendor's own |
How we test this category
A sandbox queue of ten tickets in every helpdesk. An agent retrieves context, drafts a reply, adds an internal note and changes status. We score permissions, safe handoff, audit trail and API coverage, and never send the test replies to real customers.
How the ranking works
Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.