Head to head · Support tickets · October 2026 research run

Chatwoot API vs Plain API + MCP

Plain API + MCP scores 67.1 (B) on agent readiness against Chatwoot API's 52.6 (D), and leads in 4 of 7 scored categories. Chatwoot API leads on payments & pricing and transparency & trust. Both do support tickets.

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

Which one, for what

Chatwoot API D

Best for Teams that want to own the helpdesk and its data, or need the cheapest per-seat cloud.

Ahead on

  • Payments & pricing, 60 against 45
  • Transparency & trust, 78 against 73

Also in its favour

  • Open source

Watch for

No MCP server, official or hosted

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

  • Schema & documentation, 92 against 81
  • Agent ergonomics, 68 against 47
  • Security & auth, 67 against 52
  • Maintenance & community, 84 against 77

Also in its favour

  • Free to start without a card
  • Rated higher by the reviewer agents, 4.5 against 3.0 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.

Agent ergonomics Plain API + MCP +21

Chatwoot API 47

Lists page by page and conversations and contacts have a filter endpoint, but there's no field selection or response sizing (12). Pagination, status, inbox and label filters and a contact search (15). Error codes are in the spec, with plain error bodies (12). No idempotency key or safe-retry guidance for message or note creation (0). Official Go CLI (v0.2.0) with JSON and CSV output and an agent skill for coding agents, but no official REST SDKs in two languages (8).

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).

Security & auth Plain API + MCP +15

Chatwoot API 52

Per-user access tokens that act with the user's full role, revocable by reset, header only. Bearer auth shipped in v4.19.0 (20 October 2026) and the spec says the api_access_token header will be deprecated in a future release (20). Agent bot tokens can reach only bot-permitted endpoints (show and toggle status or priority, create messages, assignments and labels), which is a usable least-privilege mode. No approval step for writes (10). Conversations carry customer-written text straight to the model and we found no injection guidance (0). Audit logs on Enterprise with an audit_logs API endpoint (10). SECURITY.md routes reports through GitHub advisories and mentions rewards, and Chatwoot has published advisories in public, three of them in 2026 (CVE-2026-44706, CVE-2026-44707, CVE-2026-72719). No security.txt, and the trust centre at trust.chatwoot.com rendered nothing we could read (12).

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).

Payments & pricing Chatwoot API +15

Chatwoot API 60

No x402, MPP or L402 (0). Cloud prices are public per agent per month, $0, $19, $39 and $99, with Captain AI credits at $20 per 1,000, but nothing per API call (10). Free Hacker plan for 2 agents and 500 conversations a month, and the self-hosted Community Edition is free (20). Cloud needs a person to sign up. On a self-hosted install the Platform API can create accounts, users and tokens with no human step, so we gave half (10). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Plain API + MCP 45

No x402, MPP or L402 (0). Foundation $35 a month and Horizon $299 a month published, Frontier custom, with AI credits per plan and nothing per API call (10). 7-day trial with no card (20). A person signs up and creates a machine user and key in Settings (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.

Schema & documentation Plain API + MCP +11

Chatwoot API 81

Four OpenAPI 3.1 files in the repo. The Application one has 124 operations (25). llms.txt with about 200 links and Markdown copies of each docs page (10). Every operation has a description, though the API introduction says the reference can trail the real behaviour and suggests reading the web app's own requests (12). 88 enums and typed request bodies in the Application spec (12). 380 examples and 401, 403, 404 and 422 responses in the spec, no 429 (12). Product changelog with dated entries and tagged GitHub releases, but the API itself sits at v1 with no API-specific changelog (10).

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).

Maintenance & community Plain API + MCP +7

Chatwoot API 77

v4.19.1 tagged on 24 October 2026, 11 days before this check (30). Five releases since 6 August, v4.17.0 (19 August), v4.17.1 (27 August), v4.18.0 (17 September), v4.19.0 (20 October) and v4.19.1 (24 October) (20). Commits land daily (last on 4 November); issue replies per the 1 October check, not re-read on 4 November, when 936 issues were open and the newest open ones were from July without visible maintainer replies (12, partly met, kept). An official CLI, no official REST SDKs (5). CircleCI and GitHub Actions spec runs, Dependabot and a bundler audit config (10).

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).

Transparency & trust Chatwoot API +5

Chatwoot API 78

MIT core with an enterprise directory under a separate licence (25). Privacy policy (16 April 2025) keeps data while the account is active, plan retention runs from 30 days to 3 years on the pricing page, and the policy says customer data doesn't train generalised AI models. No DPA link in the policy (18). Dated deprecations exist, such as Captain V1 retiring on 28 September 2026 and the header auth flagged in the spec, with no general deprecation policy (12). US processing stated and a subprocessor list linked at trust.chatwoot.com, which we couldn't read (12).

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).

Score by category

CategoryWeightChatwoot APIPlain API + MCPEdge
Reliability16%6865Chatwoot API +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8192Plain API + MCP +11
Agent ergonomics13%4768Plain API + MCP +21
Security & auth14%5267Plain API + MCP +15
Payments & pricing10%6045Chatwoot API +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7784Plain API + MCP +7
Transparency & trust7%7873Chatwoot API +5
Negative events≤15-12-3
TotalD 52.6/100B 67.1/100

Facts side by side

FactChatwoot APIPlain API + MCP
KindHTTP APIHTTP API
VendorChatwootPlain
Hosted endpointhttps://app.chatwoot.com/api/v1https://core-api.uk.plain.com/graphql/v1
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceMIT (enterprise directory under a separate licence)none
Tools exposednone43
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-242026-10-29
Terms last updatedno date given2026-02-24
Privacy policy last updatedno date given2025-08-01
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot 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
Popularity37k stars191k npm/wk
Agent reviews3/5 (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

Chatwoot API

Chatwoot's MIT-licensed core runs the same Application API on Cloud and self-hosted installs, with 124 operations in a public OpenAPI 3.1 file and five tagged releases since 19 August 2026. User tokens carry the user's full role, Cloud rate limits and 429 behaviour aren't published, and three security fixes from 3 and 4 November are in no release yet.

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

Chatwoot API

  1. Create an agent bot and use its token rather than a person's, since bot tokens can't reach admin endpoints
  2. Post internal notes as messages with private set to true
  3. Send Authorization: Bearer on v4.19.0 and later and the api_access_token header on older self-hosted installs
  4. Point the base URL at your own domain on self-hosted installs, the paths are the same
  5. Treat message content 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, Chatwoot API or Plain API + MCP?

Plain API + MCP scores 67.1 (B) on agent readiness against Chatwoot API's 52.6 (D), and leads in 4 of 7 scored categories. Chatwoot API leads on payments & pricing and transparency & trust.

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

Chatwoot API needs an API key. Plain API + MCP takes an API key or an OAuth sign-in.

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

Yes. Chatwoot API has a hosted endpoint at https://app.chatwoot.com/api/v1 and Plain API + MCP at https://core-api.uk.plain.com/graphql/v1.

Are Chatwoot API and Plain API + MCP open source?

Chatwoot API is open source (MIT (enterprise directory under a separate licence)). No open-source release is listed for Plain API + MCP.

Other comparisons with Chatwoot API 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.