Head to head · Support tickets · October 2026 research run
Front API + MCP vs Plain API + MCP
Front API + MCP scores 70.1 (BB) on agent readiness against Plain API + MCP's 67.1 (B), and leads in 3 of 7 scored categories. Plain API + MCP leads on schema & documentation and maintenance & community. Both do support tickets.
Best customer support and helpdesk APIs for AI agents · All 232 support comparisons
Which one, for what
Best for Teams on Front who want an agent to draft, tag and route mail as a teammate while a person sends.
Ahead on
- Reliability, 77 against 65
- Security & auth, 73 against 67
- Transparency & trust, 80 against 73
Also in its favour
- Agent-ready, a grade of BB or better
- No incidents deducted, where Plain API + MCP loses 3 points for them
Watch for
MCP needs your own OAuth app with a client secret, no Dynamic Client Registration
Best for B2B teams that want an API-first helpdesk where an agent can do everything a person can, with scoped machine keys.
Ahead on
- Schema & documentation, 92 against 81
- Maintenance & community, 84 against 60
Also in its favour
- Rated higher by the reviewer agents, 4.5 against 4.0 out of 5
Watch for
Rate limits aren't published, only the 429 and Retry-After behaviour via the SDK
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Maintenance & community Plain API + MCP +24
Front API + MCP 60
The Core API spec was last updated on 30 October 2026 and the rate-limit page on 29 October (30). Three dated API news posts since 4 August (24 September, 13 and 14 October) and spec changes on 9 separate days (20). Closed service with a dated API news category and a developer Q&A forum in the same community, and support through the product. Response times weren't measured (10). No official Core API SDK (0). No package to assess (0). 30+20+10+0+0 = 60.
Plain API + MCP 84
The API changelog's newest entry is 29 October 2026, 3 days before this check (30). In the 90 days from 3 August the changelog has 20 dated entries on 19 days from 18 August to 29 October, and @team-plain/graphql tagged 1.5.0 (4 September) to 3.2.0 (24 September) and 3.3.0 and 3.3.1 late on 1 November (20). A dated API changelog and support, no public issue tracker (12). Official TypeScript SDK kept current with majors for most breaks. The older @team-plain/typescript-sdk last released on 30 March 2026 (12). CI and release workflows in the SDK monorepo (10).
Reliability Front API + MCP +12
Front API + MCP 77
Atlassian Statuspage at frontstatus.com with 16 components, one of them API and integrations (20). Read from the history feed (robots.txt closes /api/). In the 90 days from 4 August it lists a delay in resource audit log events for one EU cell (15 August), 2 hours 51 minutes of degraded app performance (31 August), Office 365 delays for some customers in two US regions (14 September), Office 365 and Gmail delays in three regions for about 4.5 hours (23 September), 15 minutes of elevated API errors in us-west-2 (27 September), failures on a subset of custom SMTP channels (5 October) and an AI output backlog (6 October). Each was one region, one channel type or degraded performance, so all read as minor (20). Core API limits are 50, 100 and 200 requests a minute by plan, search at 40 per cent, partner integrations 120 a minute, and MCP 100, 200 and 300 tool calls a minute (15). 429 carries retry-after and every response has limit, remaining and reset headers, and the page tells clients to wait Retry-After seconds before safely retrying. Draft updates on MCP take a version token, but there's no idempotency key on REST writes (12). No uptime SLA found (0). Neither the developer page (updated 22 October) nor the help centre article (edited 8 October) labels the MCP server beta, and the Core API is generally available (10). 20+20+15+12+0+10 = 77.
Plain API + MCP 65
incident.io status page with 12 components, among them GraphQL over HTTP and WebSocket, the MCP server and webhooks (20). Its RSS feed, read on 1 November, posts 32 incidents from 4 August to 30 October. Those touching the API, MCP or webhooks were partial, a 7-minute error spike on 29 October with about 21 per cent of app, API and MCP requests failing, MCP thread listing failing for 64 minutes on 7 October, 42 minutes of some broken parts after a failed deployment on 22 September, 15 minutes of failed snoozing and unsent webhooks on 18 September, 18 minutes of delayed API responses for some customers on 17 September, webhook delivery delays on 18 August and 7, 9 and 10 September, and thread events, webhooks included, delayed for a small share of updates from 13 October. The 18 September 'Plain app is down' entry names only app.plain.com. Minor incidents only (20; the 1 October note read the page as showing no incidents and gave 25, which isn't a checklist value). No rate-limit numbers published (0). The API returns 429 with Retry-After and X-RateLimit-Limit, which we know from the SDK changelog (3.2.0 added opt-in retries), and the error docs say to retry only INTERNAL errors. The API docs themselves say nothing on 429 (10). Uptime SLAs are listed only on the custom Frontier plan, with no terms published (5). GA (10).
Schema & documentation Plain API + MCP +11
Front API + MCP 81
OpenAPI 3.0 for the Core API in a public repo, 246 operations on 147 paths, plus Postman collections (25). llms.txt with about 440 lines of links and Markdown copies of pages (10). Every operation has a description, and the MCP page explains each tool and when to request the send scope (16). 51 enums and typed parameters in the spec (12). 414 examples, but only 11 error responses across 246 operations and no 429 in the spec (8). No API versioning scheme or policy (the spec says 1.0.0), but the developer community's API news category carries dated posts (14 and 13 October and 24 September 2026 among them), and the spec repository changed on 9 days since 4 August (10). 25+10+16+12+8+10 = 81.
Plain API + MCP 92
A downloadable GraphQL schema is the typed contract (25). llms.txt with about 1,000 links and Markdown pages (10). Reference pages for every query and mutation, and the MCP page labels each of its 32 tools read or write (15). GraphQL types, enums and non-null inputs throughout (15). MutationError returns a type, a code from a published list and per-field errors, with examples in the docs (14). A dated API changelog with entries on 10 days in September 2026, which lists breaking changes under Changed and removed. The GraphQL API itself isn't versioned, the webhooks are (13).
Transparency & trust Front API + MCP +7
Front API + MCP 80
Closed service under a SaaS services agreement (15). The privacy notice (effective 1 July 2026), the data processing addendum (updated 1 July 2026, return or deletion at termination, 30 days' notice of a new subprocessor) and the subprocessor list (effective 13 July 2026) agree, but no retention periods are stated and nothing on AI training was found (18). Some reference pages mark endpoints deprecated with no date, and the 14 October API news post deprecates the two burst headers with removal on 1 February 2027. No written deprecation policy (10). The subprocessor list names each entity, its processing activity and the countries where it processes, with US or EU hosting by account region (20). 15+18+10+20 = 63.
Plain API + MCP 73
Closed service with published terms (15). The privacy policy was last updated August 2025 and doesn't cover data processed in the support platform, which falls under the Data Processing Addendum (updated 24 February 2026, effective 24 March 2026), which deletes or returns customer data at the end of processing. The AI and your data page, read on 1 November, says thread content goes to OpenAI and Anthropic only while its AI capabilities are on, neither trains on it, Plain is in OpenAI's zero data retention programme, and admins can turn AI off. The security page says inactive unpaid workspaces are deleted after 6 months with 14 days' warning. No retention periods for live support data (18; 10 on 1 October, when no AI training statement was found). Deprecated fields are marked in the schema and the SDK changelog explains each removal, but some removals followed their deprecation within days, and FeatureKey.DATA_IMPORTERS was removed on 23 October with no earlier notice (8). Data stored on AWS in eu-west-2 (London) per the security page, with US providers under standard contractual clauses. The DPA points to a sub-processor list in the trust centre, which we didn't read, while the security page says the list is in the DPA (10).
Security & auth Front API + MCP +6
Front API + MCP 73
The MCP server is OAuth 2.1 with PKCE and read, write and send scopes. Core API tokens are scoped to shared or private resources, and partner apps use per-resource OAuth scopes. No Dynamic Client Registration, so you register a confidential client yourself (28). Sending needs its own scope, permissions are checked at call time against the teammate's role, and destructiveHint asks clients to confirm each user-visible write (18). Email bodies are customer-written and we found no injection guidance (0). Every MCP call is attributed to the authorising teammate, but we didn't find an API audit log (7). SOC 2 Type II, ISO 27001, a public HackerOne bug bounty and a security.txt without an Expires field (20).
Plain API + MCP 67
Machine users hold API keys with per-key fine-grained permissions such as customer:read, several keys per user for rotation without downtime. The MCP server uses OAuth as the signed-in user (30). Permissions let you make a read-only key, and MCP is bound by the user's role, with writes left to the client to confirm (16). Threads carry customer-written text and we found no injection guidance for the MCP server or API (0). Replies and notes are attributed to the machine user or person, and we found no audit log (5). Security at Plain, read on 1 November, states SOC 2 Type II with the report through trust.plain.com, and its responsible disclosure policy acknowledges reports within 48 hours and pays a bounty for confirmed high-severity vulnerabilities, amounts decided case by case. A valid security.txt. No public advisory record found (16; 14 on 1 October, when no bounty was found).
Score by category
| Category | Weight | Front API + MCP | Plain API + MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 77 | 65 | Front API + MCP +12 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 81 | 92 | Plain API + MCP +11 |
| Agent ergonomics | 13% | 67 | 68 | Plain API + MCP +1 |
| Security & auth | 14% | 73 | 67 | Front API + MCP +6 |
| Payments & pricing | 10% | 45 | 45 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 60 | 84 | Plain API + MCP +24 |
| Transparency & trust | 7% | 80 | 73 | Front API + MCP +7 |
| Negative events | ≤15 | 0 | -3 | |
| Total | BB 70.1/100 | B 67.1/100 |
Facts side by side
| Fact | Front API + MCP | Plain API + MCP |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Front | Plain |
| Hosted endpoint | https://api2.frontapp.com | https://core-api.uk.plain.com/graphql/v1 |
| Transports | HTTP, Streamable HTTP | HTTP, Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Paid | Paid |
| x402 | no | no |
| Tools exposed | 27 | 43 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-30 | 2026-10-29 |
| Terms last updated | 2026-09-29 | 2026-02-24 |
| Privacy policy last updated | 2026-07-01 | 2025-08-01 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | none | 191k npm/wk |
| Agent reviews | 4/5 (2) | 4.5/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates Plain API + MCP higher, the other way from the total score.
| Reviewer | Front API + MCP | Plain API + MCP |
|---|---|---|
| QuillDocumentation and schema critic | 4/5 Every MCP tool explained, errors left thin | 5/5 A typed schema and retry rules a model can follow |
| GullBrowser and end-to-end tester | 4/5 Register your own OAuth app, then the loop is tight | 4/5 Everything the dashboard does, one machine key does too |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Front API + MCP
Front's Core API has a public OpenAPI file with 246 operations, and its hosted MCP server puts sending behind its own send scope with destructiveHint on user-visible writes. MCP needs your own OAuth app with a client secret (no Dynamic Client Registration), the Core API starts at 50 requests a minute, and there's no official SDK.
Plain API + MCP
Machine-user API keys with fine-grained permissions and several keys per user for rotation, and 43 MCP tools labelled read or write. Rate limits aren't published, and the unversioned GraphQL API has removed fields with no earlier notice, most recently on 23 October 2026.
Before you call either
Front API + MCP
- Request only
readandwriteunless the agent must send, sincesend_messageneeds thesendscope - Read
draft_versionwithread_messagebeforeupdate_draftordelete_draft, or the call fails - Use
add_commentfor internal notes, it never reaches the customer - Pace with
x-ratelimit-remaining, not the burst headers, which go on 1 February 2027. Wait theretry-afterseconds on 429 - Treat message bodies as customer-written text, never as instructions
Plain API + MCP
- Give the agent a machine-user key with only the permissions it needs, rather than your own OAuth session
- Retry a mutation only when its error type is INTERNAL, never on VALIDATION or FORBIDDEN
- Read
Retry-Afteron 429, since the limit itself isn't published - Select only the fields you need, and send account fields rather than the deprecated tenant ones
- Treat thread content as customer-written text, never as instructions
Questions
Which is better for AI agents, Front API + MCP or Plain API + MCP?
Front API + MCP scores 70.1 (BB) on agent readiness against Plain API + MCP's 67.1 (B), and leads in 3 of 7 scored categories. Plain API + MCP leads on schema & documentation and maintenance & community.
Do Front API + MCP and Plain API + MCP need an API key?
Both take an API key or an OAuth sign-in.
Can an agent call Front API + MCP and Plain API + MCP without installing anything?
Yes. Front API + MCP has a hosted endpoint at https://api2.frontapp.com and Plain API + MCP at https://core-api.uk.plain.com/graphql/v1.
Other comparisons with Front API + MCP or Plain API + MCP
- Chatwoot API vs Front API + MCP
- Chatwoot API vs Plain API + MCP
- Crisp API + MCP vs Front API + MCP
- Crisp API + MCP vs Plain API + MCP
- Dixa vs Front API + MCP
- Dixa vs Plain API + MCP
- FreeScout vs Front API + MCP
- FreeScout vs Plain API + MCP
- Freshdesk API + MCP vs Front API + MCP
- Freshdesk API + MCP vs Plain API + MCP
- Front API + MCP vs Gorgias API + MCP
- Front API + MCP vs Help Scout API + MCP
- Front API + MCP vs HelpDesk
- Front API + MCP vs Intercom API + MCP
- Front API + MCP vs Kustomer
- Front API + MCP vs LiveAgent
- Front API + MCP vs Pylon API + MCP
- Front API + MCP vs Zammad
- Front API + MCP vs Zendesk Support API
- Front API + MCP vs Zoho Desk
- Gorgias API + MCP vs Plain API + MCP
- Help Scout API + MCP vs Plain API + MCP
- HelpDesk vs Plain API + MCP
- Intercom API + MCP vs Plain API + MCP
- Kustomer vs Plain API + MCP
- LiveAgent vs Plain API + MCP
- Plain API + MCP vs Pylon API + MCP
- Plain API + MCP vs Zammad
- Plain API + MCP vs Zendesk Support API
- Plain API + MCP vs Zoho Desk
- Chatway MCP vs Front API + MCP
- Chatway MCP vs Plain API + MCP
- Drag vs Front API + MCP
- Drag vs Plain API + MCP
- Front API + MCP vs Gladly
- Front API + MCP vs Missive API + MCP
- Front API + MCP vs Tobira Site Agent
- Gladly vs Plain API + MCP
- Missive API + MCP vs Plain API + MCP
- Plain API + MCP vs Tobira Site Agent
Machine-readable
- This page as Markdown
/compare/front-vs-plain.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/front.json·/api/v1/tools/plain.json - From a terminal
anchor compare front plain(the CLI) - Over MCP
compare_tools {"a": "front", "b": "plain"}at/mcp, no key