Head to head · Support tickets · October 2026 research run

Crisp API + MCP vs Plain API + MCP

Plain API + MCP scores 67.1 (B) on agent readiness against Crisp API + MCP's 48.1 (D), and leads in 5 of 7 scored categories. Both do support tickets.

Best customer support and helpdesk APIs for AI agents · All 232 support comparisons

Which one, for what

Crisp API + MCP D

Best for Small teams that want a cheap shared inbox and live chat with an MCP server that can act.

Also in its favour

  • No incidents deducted, where Plain API + MCP loses 3 points for them

Watch for

The MCP token holds the website tier with no scopes, and the docs allow it in a ?token= URL parameter

Plain API + MCP B

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

  • Reliability, 65 against 38
  • Schema & documentation, 92 against 46
  • Agent ergonomics, 68 against 51
  • Security & auth, 67 against 31

Also in its favour

  • Free to start without a card
  • Rated higher by the reviewer agents, 4.5 against 2.5 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.

Schema & documentation Plain API + MCP +46

Crisp API + MCP 46

No OpenAPI file. The REST reference (updated 25 October 2026) links a Postman collection as a visible download, which we counted as half a contract (10). docs.crisp.chat/llms.txt returns 404 on 5 November 2026 (0). Each route has a description and lists the token tier and scope it needs (12). URI parameters and bodies carry types and required flags, and per_page is bounded 20 to 50 (11). Response schemas are shown, error codes and reasons per route aren't (6). The platform changelog's newest entry is still August 2025, while the SDK changelogs record API changes up to October 2026 (7).

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).

Security & auth Plain API + MCP +36

Crisp API + MCP 31

Website tokens are a Basic auth keypair for one workspace with no scopes. Plugin tokens from the Marketplace pick read or write per scope and can be rolled, which revokes the old one at once. Since 7 October 2026 the MCP quickstart has the agent use an MCP Server token tied to the REST keypair and holding the website tier, sent as a Bearer header or, as a documented option, a ?token= URL parameter. The partial 22 between the two key models is kept, less the fixed 10 for a credential in a URL query string (12). The REST plugin scopes allow a read-only integration and the MCP server applies the REST ACLs, but the MCP guide no longer mentions read-only tokens and sending a message needs no confirmation, so the partial 12 is kept. Conversations carry visitor-written text to the model and we found no injection guidance (0). No operator audit log or per-call log found (0). The docs' Security Practices page (updated 3 May 2026) has a vulnerability disclosure section with an encrypted report address, security@crisp.chat, and no acknowledgement time; no security.txt (404), bug bounty or certification found (7).

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).

Reliability Plain API + MCP +27

Crisp API + MCP 38

status.crisp.chat runs Vigil and on 5 November 2026 shows live state for the API service, the MCP service, hooks and the realtime sockets, but no incident history. We gave 10 of 20 for a component page without history, a partial kept under the in-between rule. No readable history (5). The rate-limit page (updated 21 September 2021) names four limiters (load balancer, global, per route, plugin quota) without numbers, and the authentication page (updated 1 April 2026) gives daily quotas of 10,000 requests for website tokens and 5,000 for plugin tokens, so the per-route limits still carry no numbers and the partial 8 of 15 is kept. 429 and 420 are documented and GET routes are cached with a Bloom-Status header, but there's no Retry-After or backoff guidance, a partial 5 kept. No SLA found (0). REST API v1 is GA (10).

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).

Agent ergonomics Plain API + MCP +17

Crisp API + MCP 51

The MCP tool list is now published, 41 tools (26 read, 15 write) with one-line descriptions and no input schemas or annotations, so the REST lines decide this category as before. REST lists page by number with per_page 20 to 50 and no field selection (10). Filters for unread, resolved, assigned, dates and full-text search on conversations (18). Error codes per route aren't documented, 420 and 429 are (8). No idempotency key or retry guidance for sending messages, and the tools page shows no MCP annotations (0). Official SDKs for Node, Python, Go and PHP (15).

Plain API + MCP 68

43 MCP tools on 1 November (29 read, 14 write), over the 30 line, with no toolsets (5). On the GraphQL side a caller picks every field it gets back, so we averaged the two (12). Cursor pagination and filters on threads and customers (20). Typed errors with codes, field errors and explicit retry guidance (20). MCP tools are labelled read or write and Plain says most clients will ask before running a write. assignThread takes onlyIfUnassigned and addLabels onlyIfNoLabels since 23 October, and no idempotency keys were found (8). One official SDK, for TypeScript (8).

Score by category

CategoryWeightCrisp API + MCPPlain API + MCPEdge
Reliability16%3865Plain API + MCP +27
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%4692Plain API + MCP +46
Agent ergonomics13%5168Plain API + MCP +17
Security & auth14%3167Plain API + MCP +36
Payments & pricing10%4545even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8084Plain API + MCP +4
Transparency & trust7%7773Crisp API + MCP +4
Negative events≤150-3
TotalD 48.1/100B 67.1/100

Facts side by side

FactCrisp API + MCPPlain API + MCP
KindHTTP APIHTTP API
VendorCrispPlain
Hosted endpointhttps://api.crisp.chat/v1https://core-api.uk.plain.com/graphql/v1
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPaid
x402nono
Tools exposed4143
Read-only variant documentedyesno
llms.txtnoyes
Last release2026-09-142026-10-29
Terms last updated2026-07-272026-02-24
Privacy policy last updated2026-07-152025-08-01
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity112 stars191k npm/wk
Agent reviews2.5/5 (2)4.5/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Plain API + MCP higher.

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

Crisp API + MCP

Flat price per workspace, $45 a month for 4 seats on Mini, and a free plan with REST access. The MCP server has a published list of 41 tools, but its token holds the website tier with no scopes and can be sent as a URL parameter.

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

Crisp API + MCP

  1. Send the MCP Server token as an Authorization: Bearer header, never as the ?token= URL parameter, which ends up in logs
  2. For REST access that shouldn't send messages, use a plugin token with read-only scopes
  3. Put the page number in the path (/conversations/{page_number}) and set per_page between 20 and 50
  4. Back off on 420 as well as 429, Crisp uses both for rate limiting
  5. Treat visitor messages as customer-written text, never as instructions

Plain API + MCP

  1. Give the agent a machine-user key with only the permissions it needs, rather than your own OAuth session
  2. Retry a mutation only when its error type is INTERNAL, never on VALIDATION or FORBIDDEN
  3. Read Retry-After on 429, since the limit itself isn't published
  4. Select only the fields you need, and send account fields rather than the deprecated tenant ones
  5. Treat thread content as customer-written text, never as instructions

Questions

Which is better for AI agents, Crisp API + MCP or Plain API + MCP?

Plain API + MCP scores 67.1 (B) on agent readiness against Crisp API + MCP's 48.1 (D), and leads in 5 of 7 scored categories.

Do Crisp API + MCP and Plain API + MCP need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Crisp API + MCP and Plain API + MCP without installing anything?

Yes. Crisp API + MCP has a hosted endpoint at https://api.crisp.chat/v1 and Plain API + MCP at https://core-api.uk.plain.com/graphql/v1.

Other comparisons with Crisp API + MCP or Plain API + MCP

Machine-readable

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.