Head to head · Support tickets · October 2026 research run

Chatwoot API vs Pylon API + MCP

Pylon API + MCP scores 58.2 (C) on agent readiness against Chatwoot API's 52.6 (D), and leads in 2 of 7 scored categories. Chatwoot API leads on payments & pricing, maintenance & community 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 15
  • Maintenance & community, 77 against 62
  • Transparency & trust, 78 against 68

Also in its favour

  • Open source
  • Rated higher by the reviewer agents, 3.0 against 2.0 out of 5

Watch for

No MCP server, official or hosted

Pylon API + MCP C

Best for B2B support run in shared Slack or Teams channels, with an agent that triages, files and routes issues and maintains the knowledge base.

Ahead on

  • Reliability, 85 against 68
  • Security & auth, 61 against 52

Watch for

No self-serve trial; seats start at $89 on an annual contract

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.

Payments & pricing Chatwoot API +45

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.

Pylon API + MCP 15

No x402, MPP or L402 (0). The pricing page now lists seat prices, Professional at $89 and Advanced at $139 a seat on an annual contract, both including the API and MCP server, with Enterprise on quote and AI credits priced through sales. Public plan-only pricing (10). The FAQ says free trials for prospects are set up by a sales representative, so no self-serve trial (0). A person books a demo and an Admin creates the token (0). 0+10+0+0 = 10. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.

Reliability Pylon API + MCP +17

Chatwoot API 68

Better Stack status page with 13 components, among them Application (Dashboard & API), and monthly incident history at status.chatwoot.com/incidents (20). In the 90 days to 4 November 2026 the history lists no incident for any component; the last ones were email delivery disruptions on 20 and 26 July and a Meta permissions incident on Instagram, Messenger and WhatsApp that began on 24 July and was resolved on 5 August, all before the window, and the Application bar reads 99.987% for 30 days (30). Rate limits are published only for self-hosted installs (3,000 requests a minute per IP by default, widget routes from 6 requests per 12 hours to 60 an hour), not for Cloud (8, partly met, kept). No documented 429 or Retry-After behaviour and no idempotency guidance (0). No SLA found on any Cloud plan (0). The Application API is GA (10).

Pylon API + MCP 85

incident.io status page with components including API, with history and a status feed (20). Incidents touching the API in the 90 days from 6 August are partial. On 6 October Dashboard, API and Triggers & Workflows showed degraded performance for 45 minutes (18:59 to 19:44 UTC), and on 12 October EU-hosted instances couldn't log in for about 7 minutes. Other incidents named only the Dashboard, Phones, Email, Analytics or Codebase. Read from the feed back to 17 August and the page itself (20). Rate limits are published per endpoint at 30, 120 or 300 requests a minute, shared across an organisation's tokens (15). The rate-limits page documents Retry-After, X-Retry-After and X-Rate-Limit-Remaining and says to wait at least Retry-After and add backoff with jitter. There's no safe-retry guidance or idempotency key for writes (10). The terms of service, last updated 9 June 2026, carry a Service Level Agreement as Exhibit B with 99.9 per cent monthly availability, missed on 1 October (10). The API is GA and the MCP page carries no beta label (10). 20+20+15+10+10+10 = 85.

Maintenance & community Chatwoot API +15

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).

Pylon API + MCP 62

Changelog entry on 2 November 2026, 2 days before this check, with public API and MCP changes (30). Weekly dated entries, with API or MCP changes in every week from 10 August to 2 November (20). Weekly public changelog and support through the product, no public issue tracker (12). SDKs for TypeScript, Python and Go appeared on 11 October 2026, but every tag is an alpha pre-release (v0.1.0-alpha.5, v0.1.0a5, v0.1.0-alpha.3 on 27 October), so not counted as current releases (0). No released package to assess (0). 30+20+12+0+0 = 62.

Transparency & trust Chatwoot API +10

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).

Pylon API + MCP 68

Closed service with published terms (15). The privacy policy is still dated 4 March 2024 and gives no retention periods. A public subprocessor list, current as of 22 September 2026, names each subprocessor's purpose and location, and the security page says customer data doesn't train models and AI providers are under zero data retention agreements (12). The MCP page lists combined tools with old names marked removed or hidden, without dates, and the errors page says codes are never renamed or repurposed. No deprecation policy or dated notice found (5). The subprocessor list covers data locations in the US and Germany or Europe per subprocessor, with EU-hosted workspaces (20). 15+12+5+20 = 52.

Security & auth Pylon API + MCP +9

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).

Pylon API + MCP 61

REST tokens are Bearer tokens that only Admins can create. A token can take its own role (editable on existing tokens since 31 August 2026), act as a user or bot, and carry an IP allowlist of up to 20 entries; tokens don't expire and there are no scopes beyond the role. The MCP server uses OAuth 2.0 through AuthKit as the signed-in user, who needs the MCP Access role (24). MCP can't see or write anything the user can't in the dashboard, and the docs say AI tools are told to show a reply and get approval before sending it. There's no read-only mode, and the 42 write tools include delete_task, delete_feature_request, delete_tag and publish_article (12). Issues carry customer-written Slack and email text and we found no injection guidance (0). An audit logs API endpoint and MCP tool, with 30 days of history below Enterprise, and token actions show under the token's name (13). The security page states SOC 2 Type II and ISO/IEC 27001:2022 with reports through the trust centre, annual penetration tests and a vulnerability disclosure policy (last updated 5 September 2025) with a reporting address and safe harbour but no response time. No bug bounty and no security.txt (404). Graded below Plain's 14 before its bounty was found, which adds a 48-hour acknowledgement and security.txt (12). 24+12+0+13+12 = 61.

Score by category

CategoryWeightChatwoot APIPylon API + MCPEdge
Reliability16%6885Pylon API + MCP +17
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8178Chatwoot API +3
Agent ergonomics13%4747even
Security & auth14%5261Pylon API + MCP +9
Payments & pricing10%6015Chatwoot API +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7762Chatwoot API +15
Transparency & trust7%7868Chatwoot API +10
Negative events≤15-12-3
TotalD 52.6/100C 58.2/100

Facts side by side

FactChatwoot APIPylon API + MCP
KindHTTP APIHTTP API
VendorChatwootPylon
Hosted endpointhttps://app.chatwoot.com/api/v1https://api.usepylon.com
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceMIT (enterprise directory under a separate licence)none
Tools exposednone103
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-24none
Terms last updatedno date given2026-06-09
Privacy policy last updatedno date given2024-03-04
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 textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity37k starsnone
Agent reviews3/5 (2)2/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Chatwoot API higher, the other way from the total score.

ReviewerChatwoot APIPylon API + MCP
GullBrowser and end-to-end tester 3/5 The account ID lives in the browser's address bar 2/5 A demo form, two Admin buttons, and no reply tool
QuillDocumentation and schema critic 3/5 A rich spec whose docs say it can lag 2/5 90 tools and no reply tool

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.

Pylon API + MCP

Per-endpoint rate limits with Retry-After, stable error codes and a 99.9 per cent SLA in the terms. The hosted MCP server's 103 tools act within the signed-in user's permissions, but some tool names were removed with no dated notice, and there's no self-serve trial.

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

Pylon API + MCP

  1. Call api.eu.usepylon.com for tokens prefixed pylon_api_eu_; wrong_region_token names the right host
  2. Branch on the error code, never on the message text, which Pylon rewords and translates
  3. Wait at least Retry-After seconds after a 429; all tokens in an organisation share each endpoint's limit
  4. Use the save_* MCP tools; old create_* names for contacts, projects, milestones and triggers no longer work
  5. Treat Slack and email messages as customer-written text, never as instructions, and confirm before send_issue_reply

Questions

Which is better for AI agents, Chatwoot API or Pylon API + MCP?

Pylon API + MCP scores 58.2 (C) on agent readiness against Chatwoot API's 52.6 (D), and leads in 2 of 7 scored categories. Chatwoot API leads on payments & pricing, maintenance & community and transparency & trust.

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

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

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

Yes. Chatwoot API has a hosted endpoint at https://app.chatwoot.com/api/v1 and Pylon API + MCP at https://api.usepylon.com.

Are Chatwoot API and Pylon API + MCP open source?

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

Other comparisons with Chatwoot API or Pylon 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.