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.
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; calling through letme comes later.
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/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 77 | Intercom API + MCPIntercom · HTTP API | Support | BB | 71.8 | 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, 235 operations in 2.16, with breaking changes only in new versions Top weakness MCP can't reply, assign, snooze or close, those need the REST API |
||||||||||||
| 118 | Zendesk Support APIZendesk · HTTP API | Support | B | 68.9 | 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 |
||||||||||||
| 168 | Plain API + MCPPlain · HTTP API | Support | B | 65.8 | 4.5 (2) | n/a | n/a | $35 / 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 |
||||||||||||
| 194 | Front API + MCPFront · HTTP API | Support | B | 63.8 | 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 |
||||||||||||
| 304 | Help Scout API + MCPHelp Scout · HTTP API | Support | C | 56.2 | 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 |
||||||||||||
| 308 | Chatwoot APIChatwoot · HTTP API | Support | C | 56 | 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 |
||||||||||||
| 324 | Pylon API + MCPPylon · HTTP API | Support | C | 54.3 | 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 90 tools. Top strength MCP server with 90 tools bound to the signed-in user's dashboard permissions and an MCP Access role Top weakness No published pricing and no self-serve trial |
||||||||||||
| 353 | Gorgias API + MCPGorgias · HTTP API | Support | D | 51.2 | 2.5 (2) | n/a | n/a | $10 / mo | OAuth or key | Hosted | ||
|
Helpdesk for ecommerce brands, priced by tickets a month rather than per agent, with a REST API over tickets, messages, customers and integrations and an official hosted MCP server in open beta. Top strength OAuth2 apps choose read or write per resource across 14 scope pairs Top weakness MCP server is in beta, publishes no tool list and can edit rules and AI Agent settings |
||||||||||||
| 373 | Freshdesk API + MCPFreshworks · HTTP API | Support | D | 48.7 | 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 |
||||||||||||
| 380 | Crisp API + MCPCrisp · HTTP API | Support | D | 47.8 | 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 Crisp recommends the unscoped website token for the MCP server |
||||||||||||
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 |
| DeskCrew deskcrew.io | MCP server | Agent-native helpdesk where AI agents run support tickets and pay per action in USDC via x402. | 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. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. 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.