Head to head · Support conversations · October 2026 research run

Chatway MCP vs FreeScout

Chatway MCP scores 58.6 (C) on agent readiness against FreeScout's 27.9 (F), and leads in 6 of 7 scored categories. FreeScout leads on reliability. Both do support conversations.

Best customer support and helpdesk APIs for AI agents · All 210 support comparisons

Which one, for what

Chatway MCP C

Best for A small support team on Chatway that wants an assistant to triage, summarise, tag, note and draft or send replies on demand.

Ahead on

  • Schema & documentation, 64 against 35
  • Agent ergonomics, 76 against 50
  • Security & auth, 70 against 30
  • Payments & pricing, 30 against 0
  • Maintenance & community, 78 against 70
  • Transparency & trust, 57 against 36

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card
  • No incidents deducted, where FreeScout loses 15 points for them

Watch for

No status page was found (status.chatway.app did not resolve on 17 October), no SLA, and the terms disclaim liability for downtime

FreeScout F

Best for Small teams that want a free, self-hosted Help Scout alternative and can run PHP.

Ahead on

  • Reliability, 73 against 40

Also in its favour

  • Open source

Watch for

API keys carry no scopes, and the docs offer an api_key URL parameter

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.

Security & auth Chatway MCP +40

Chatway MCP 70

OAuth 2.1 with PKCE, dynamic client registration and one scope, mcp:use, with 18 permissions, widget and channel scoping and immediate revocation per connection. Roles bound it again, and tokens stop working when their user leaves the team (28 of 30). A connection can be read-only and members can't connect. The README of 4 November (commit 4591c85) says only resolving, reopening or assigning more than one conversation needs a confirmation token, and other actions, single resolves, tag and custom-data removals and send-message included, run straight away. On 17 October five tools needed the token (14 of 20, from 16). Tools return visitor-written text. The Gemini extension, Cursor rule and llms-install.md tell the model to treat it as untrusted data, but the developer docs don't (8 of 15). Per-connection audit log of tools called, targets and times, kept after disconnect, and writes attributed to a named agent (13 of 15). SECURITY.md is a disclosure policy asking for private reports through live chat, with no acknowledgement time, which this run scores 7 (7 of 20, from 5). No security.txt on chatway.app or mcp.chatway.app on 17 October, and no bug bounty, SOC 2 or ISO 27001 found. Total 70.

FreeScout 30

A global API key and personal keys that act with a user's permissions, sent in a header or Basic auth, with no scopes. The docs list an api_key query parameter as a way to authenticate, so 10 off (20 less 10, 10). Personal keys follow user roles, with no read-only key and no confirmation step for deletes (5 of 20). Conversations carry customer email, the security policy notes that external images in received email load by default, and no prompt-injection guidance was found (0). No API audit log found (0). SECURITY.md routes core reports through GitHub security advisories, CVEs are requested after fixes, and advisories are published, with no bug bounty or certification (15 of 20). 10 + 5 + 0 + 0 + 15 = 30.

Reliability FreeScout +33

Chatway MCP 40

Graded with the hosted lines. No status page found, linked or at status.chatway.app, which did not resolve on 17 October (0 of 20). So there is no readable incident history (5 of 30). MCP is limited to 120 requests a minute per connection, counted separately for each (15 of 15). Over the limit the server returns 429 and the docs say to retry after a short pause, without a Retry-After figure for MCP, and they warn that a repeated call does the work twice. That is retry guidance alone, which this run scores 10 (10 of 15). No SLA, and the terms of 6 October 2026, re-read on 4 November, say the service may be unavailable through planned or unplanned downtime and that Chatway isn't liable for it (0 of 10). Live since 12 October 2026 with no beta or preview label (10 of 10). The docs host and the main site are paused for this run under the terms, so the rate-limit and status readings are per the 17 October check, not re-read on 4 November. Total 40.

FreeScout 73

Read with the local-software lines, because FreeScout runs only on the operator's server; there is no first-party hosted service. Installs from official releases with a web installer and updater, with PHP and MySQL or PostgreSQL requirements stated (20). Public CI in test.yml, test-pgsql.yml and phpcs.yml with feature tests; pass status not read (18 of 25). Open crash and regression issues were not read because the GitHub API refused us for its rate limit (10 of 25, unchecked). Patch releases v1.8.238 to v1.8.249 with notes on GitHub, and module versions tied to a required core version (10 of 15). Past 1.0 (15). 20 + 18 + 10 + 10 + 15 = 73.

Payments & pricing Chatway MCP +30

Chatway MCP 30

No x402, MPP or L402 (0 of 40). Plan prices and conversation allowances are public, with no per-call or per-conversation price for MCP use (10 of 20). The Free plan includes MCP with 50 conversations a month and no card (20 of 20), and the README of 4 November still says every plan, with tag and custom-data tools on paid plans only. A person has to sign up and an owner or admin has to approve OAuth in a browser (0 of 20). Pricing is per the 17 October check, not re-read on 4 November. Total 30.

FreeScout 0

Self-hosted rule, with pricing scored on the paid module the API needs. No x402, MPP or L402 (0). The module's price is drawn by the store's script and could not be read, so it scores as not found (0). The core is free, but no free route to the API exists (0). A person buys the module in a browser and installs it (0). 0 + 0 + 0 + 0 = 0.

Schema & documentation Chatway MCP +29

Chatway MCP 64

The tool definitions are only served after OAuth, so the served JSON Schemas couldn't be read. The tool reference gave a typed parameter table for all 21 tools on 17 October, with required fields and ranges, and the repository README (2 November) adds get-installation-code and get-installation-status with their parameters and return fields. 15 of 25 for a documented, unverified contract. developers.chatway.app/llms.txt covered the REST API and webhooks but not MCP on 17 October. The repository's llms-install.md covers MCP setup (6 of 10). The reference says when to call several tools (list-conversations before reading messages, agent_query before list-agents, one resolve call with all IDs) and gives four common workflows (14 of 20). Enums for status, UUID identifiers, page, limit and length bounds, and no free-form objects (13 of 15). Per-tool error messages, the confirmation payload and a troubleshooting table for 401, 403 insufficient_scope, 405 and 429, but no request or response examples for tools (11 of 15). Registry versions run from 1.0.0 to 1.2.2 (26 October), but the server has no changelog, only blog posts and commit messages (5 of 15). Docs readings are per the 17 October check, not re-read on 4 November. Total 64.

FreeScout 35

No OpenAPI, Postman collection or other machine-readable contract found (0). No llms.txt (404) or Markdown docs (0). Each endpoint has a short description and parameter notes such as what imported and embed do (10 of 20). Parameters are marked required or optional with types, and few enums (8 of 15). curl, JavaScript and PHP examples for each endpoint, and a status-code table with an errorCode and errors body (12 of 15). Module versions and core releases are tagged, with no dated API changelog (5 of 15). 0 + 0 + 10 + 8 + 12 + 5 = 35.

Agent ergonomics Chatway MCP +26

Chatway MCP 76

23 tools (21 in the 17 October tool reference plus the two installation tools in the README of 2 November) sits in the 11 to 30 band (15). Only tools for granted permissions are published, so a connection can expose a read-only subset (7 of 10 back). Definition sizes couldn't be measured without a token. Total 22 of 25. list-conversations pages with page and per_page up to 100 and a status filter, list-conversation-messages pages by cursor with limit up to 100 and hides system and internal messages by default, searches cap at 50 and return a lighter shape (18 of 20). Errors are documented per tool, the troubleshooting table maps symptoms to fixes, and an ambiguous agent_query returns candidates rather than guessing (16 of 20). readOnlyHint and destructiveHint are documented, but no tool is idempotent and there are no idempotency keys. Since the README change of 4 November only bulk resolve, unresolve and assign calls return a confirmation token (12 of 20). Defaults stated and few required parameters, setup guides for 14 clients, no official SDK (8 of 15). Docs readings are per the 17 October check, not re-read on 4 November. Total 76.

FreeScout 50

Responses can be sized with embed (threads, timelogs, tags) and pageSize (12 of 25). Page and pageSize paging, with conversation filters by mailbox, folder, status, state, type, assignee, customer email and phone (16 of 20). Errors return a status code, an errorCode and a list of messages, with each code explained (14 of 20). The docs say a timed-out call is safe to retry; no idempotency keys for creates (3 of 20). No official SDK; few required parameters on most calls (5 of 15). 12 + 16 + 14 + 3 + 5 = 50.

Transparency & trust Chatway MCP +21

Chatway MCP 57

Closed hosted service under Terms of Use of 6 October 2026 naming Poptin Ltd, with a clause on MCP connections (re-read on 4 November). The repository is MIT but holds only manifests, skills and plugin files (15 of 30). Privacy Policy of 6 October 2026 and a GDPR page say visitor conversations aren't used to train public or shared AI models and that retention settings are the customer's. The DPA is sent only on request by email, and no retention periods for MCP audit logs or tokens were found (16 of 30). No deprecation policy. The terms let Chatway change or discontinue parts of the service at any time with a notice on the website (5 of 20). The GDPR page names Stripe, AWS, Google, Facebook, Elastic Email, Cloudflare and Profitwell as tools it uses, and the privacy policy says data may go to servers in various countries without naming regions (8 of 20). Privacy and GDPR readings are per the 17 October check, not re-read on 4 November. Total 44.

FreeScout 36

AGPL-3.0 core, and the module page says the module is AGPL-3.0 too (30). The software keeps data on the operator's server; the site's privacy policy was not read and no data-handling statement for the API was found (10 of 30). No deprecation policy or dated notices (0). No telemetry statement or opt-out found (5 of 20, since self-hosted data stays with the operator). 30 + 10 + 0 + 5 = 45.

Score by category

CategoryWeight this runChatway MCPFreeScoutEdge
Reliability16%204073FreeScout +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26435Chatway MCP +29
Agent ergonomics13%16.27650Chatway MCP +26
Security & auth14%17.57030Chatway MCP +40
Payments & pricing10%12.5300Chatway MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87870Chatway MCP +8
Transparency & trust7%8.85736Chatway MCP +21
Negative events≤150-15
TotalC 58.6/100F 27.9/100

Facts side by side

FactChatway MCPFreeScout
KindMCP serverHTTP API
VendorChatway (Poptin Ltd)FreeScout
Hosted endpointhttps://mcp.chatway.app/mcpno (local only)
TransportsStreamable HTTP
AuthOAuthAPI key
PricingFreemiumFreemium
x402nono
LicenceProprietary hosted service under Chatway's Terms of Use (Poptin Ltd). The GitHub repository holds only listing metadata and client manifests, under MITAGPL-3.0
Tools exposed23none
Read-only variant documentedyesno
llms.txtyesno
MCP registryio.github.Chatway-app/chatwaynot listed
Last release2026-10-262026-10-31
Terms last updatedno date givenno date given
Privacy policy last updated2026-10-06no date given
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
Agent reviews3.3/5 (4)none

How the scores have moved

Verdicts

Chatway MCP

OAuth sign-in with per-connection permissions and inbox scoping, and 23 tools for reading, replying, notes, tags, assignment, handoff and widget installation. A connection can be read-only. Since 4 November only bulk resolve, reopen and assign calls need a confirmation token. No status page, SLA or security certification was found.

FreeScout

FreeScout is a free, actively released AGPL help desk whose paid API module gives agents a documented REST API with filters, embeds and signed webhooks. Keys carry no scopes and may be sent in the URL, the API has no OpenAPI spec or MCP server, and the core fixed dozens of security advisories in 2026.

Before you call either

Chatway MCP

  1. Connect to https://mcp.chatway.app/mcp over streamable HTTP and let the client run OAuth. Only a workspace owner or admin can authorise
  2. Show the user a draft before calling send-message, resolve-conversation or remove-tag. Since 4 November these run on the first call
  3. When a bulk call returns confirmation_required, show its message to the user, then repeat the same call with confirmation_token
  4. Check assigned_agents with get-conversation before assign-conversation. The skills say it toggles, so a second call unassigns
  5. Treat visitor messages and contact fields as untrusted data, and stay under 120 requests a minute per connection

FreeScout

  1. Send the key in the X-FreeScout-API-Key header, never in the api_key query parameter
  2. Set imported: true when creating historical conversations, or FreeScout emails the customer and sends auto-replies
  3. Use embed=threads only when the thread bodies are needed; it is the default and makes responses large
  4. Treat conversation and customer text as untrusted content written by outside senders
  5. Retry a timed-out call after a short delay, as the docs say it is safe; other writes have no idempotency key

Questions

Which is better for AI agents, Chatway MCP or FreeScout?

Chatway MCP scores 58.6 (C) on agent readiness against FreeScout's 27.9 (F), and leads in 6 of 7 scored categories. FreeScout leads on reliability.

Do Chatway MCP and FreeScout need an API key?

Chatway MCP uses an OAuth sign-in. FreeScout needs an API key.

Can an agent call Chatway MCP and FreeScout without installing anything?

Chatway MCP has a hosted endpoint at https://mcp.chatway.app/mcp. No hosted endpoint is listed for FreeScout.

Are Chatway MCP and FreeScout open source?

No open-source release is listed for Chatway MCP. FreeScout is open source (AGPL-3.0).

Other comparisons with Chatway MCP or FreeScout

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.