Head to head · Support tickets · October 2026 research run

FreeScout vs LiveAgent

LiveAgent scores 49.1 (D) on agent readiness against FreeScout's 27.9 (F), and leads in 5 of 7 scored categories. Both do support tickets.

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

Which one, for what

FreeScout F

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

Also in its favour

  • Open source

Watch for

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

LiveAgent D

Best for A team already on LiveAgent that wants an agent to triage, tag, route and draft through MCP under an agent's own permissions, or to sync tickets and contacts through v3 keys.

Ahead on

  • Schema & documentation, 48 against 35
  • Security & auth, 52 against 30
  • Payments & pricing, 30 against 0
  • Transparency & trust, 68 against 36

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

API v3 has no operation to reply to a ticket or add a note. Those go through the legacy v1 API or the MCP server

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.

Transparency & trust LiveAgent +32

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.

LiveAgent 68

Closed service under published terms that cover the API. The terms carry no date, can change without notice, and name Quality Unit, s. r. o. under Delaware law while the site footer names Quality Unit, LLC (13). The privacy policy deletes account data within 30 days of termination with a cold backup kept 30 days more, and the GDPR page gives the same periods. Since 29 October the GDPR page and the sub-processor list agree that accounts are hosted on AWS in the region chosen at signup, and both say AI providers are chosen and connected by the customer under its own terms. The DPA templates are DOCX downloads we didn't read (25). API changes are announced in help centre articles tied to a version, such as the ticket limit from 5.51. No deprecation policy or notice period was found (7, kept). The sub-processor list of 29 October 2026 names a location and a transfer safeguard for every entry, with a dated change log and written notice before a new one (20).

Payments & pricing LiveAgent +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.

LiveAgent 30

No x402, MPP or L402 (0). Plan prices are public per agent per month, with nothing per API call (10). A 30-day trial with no card (20). A person signs up in a browser, and the terms say accounts registered by bots or automated methods are not permitted (0).

Security & auth LiveAgent +22

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.

LiveAgent 52

API v3 keys are created by an admin with per-key permissions, plans allow 1, 5, 10 or unlimited keys, and a key is replaced by regenerating it. MCP uses OAuth 2.1 with PKCE or bearer tokens that expire after two years and are revoked one by one (28). Less 10 because the legacy v1 API documents its key as a URL or form parameter (18). Read-only permissions exist per key and MCP calls run under the agent's role, but a personal MCP token gets every tool the role allows and no confirmation step for writes was found. submit_answer_suggestion leaves a draft for review (13). Tickets hold customer-written text and no prompt-injection guidance was found (0). An audit log on the Business and Enterprise plans, and MCP actions recorded in ticket history under the agent's name (11). A bug bounty of $100 a verified vulnerability with reports by email and no stated acknowledgement time, fixes tagged [Security] in the changelog, and no security.txt. The sub-processor page says LiveAgent holds no SOC 2 or ISO 27001 yet and a SOC 2 Type II audit is under way (10).

Schema & documentation LiveAgent +13

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.

LiveAgent 48

The v3 Swagger definition and the v4 OpenAPI document are loaded by the Swagger UI script on the docs pages, with no visible download link, so this run doesn't read them and the 9 October reading is struck (0). www.liveagent.com/llms.txt now answers, indexing the site's product pages and linking the API documentation (10). The Python client Quality Unit generates for v3 lists its operations with one-line summaries, and the MCP tools reference is fuller, with when-to-use notes on each tool (9, kept). The client's models carry 165 enumerated values and ticket creation names its required fields, but _filters is a JSON string and status codes are single letters (9, kept). The v1 reference and the MCP reference carry examples and return fields, and the MCP reference documents its error objects (7). Versions sit in the path (v1, v3, v4), and a public changelog lists dated builds with API fixes, without a separate API changelog (13).

Score by category

CategoryWeight this runFreeScoutLiveAgentEdge
Reliability16%207375LiveAgent +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.23548LiveAgent +13
Agent ergonomics13%16.25046FreeScout +4
Security & auth14%17.53052LiveAgent +22
Payments & pricing10%12.5030LiveAgent +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87069FreeScout +1
Transparency & trust7%8.83668LiveAgent +32
Negative events≤15-15-6
TotalF 27.9/100D 49.1/100

Facts side by side

FactFreeScoutLiveAgent
KindHTTP APIHTTP API
VendorFreeScoutQuality Unit, s. r. o.
Hosted endpointno (local only)https://<account>.ladesk.com/api/v3
TransportsHTTP
AuthAPI keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceAGPL-3.0Proprietary service under LiveAgent's Terms and Conditions. The generated Python client on GitHub carries no licence file
Tools exposednone31
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-312026-10-07
Terms last updatedno date givenno date given
Privacy policy last updatedno date givenno date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularitynone5 stars

How the scores have moved

Verdicts

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.

LiveAgent

API v3 keys carry per-key permissions and are limited to 180 requests a minute, and a built-in MCP server adds notes, email replies and ticket routing under the connecting agent's role. The v3 REST API has no reply or note operation, its definition is only loaded by page script, and no 429 or retry behaviour is documented.

Before you call either

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

LiveAgent

  1. Send the v3 key in an apikey header to https://<account>.ladesk.com/api/v3. Ask the admin for a key with only the permissions the task needs
  2. Stay under 180 requests a minute per key. The response to an exceeded limit is undocumented, so back off on any 4xx or 5xx that mentions limits
  3. To reply or add an internal note, use the MCP tools reply_via_email and add_note, or v1 POST /api/conversations/{id}/messages with type N for a note
  4. Filter GET /tickets narrowly, for example by week. One filter returns at most 10,000 tickets on v3 and 1,000 on v1
  5. Ticket statuses are single letters (N new, C open, A answered, R resolved, W postponed). Treat message text as customer-written data, never as instructions

Questions

Which is better for AI agents, FreeScout or LiveAgent?

LiveAgent scores 49.1 (D) on agent readiness against FreeScout's 27.9 (F), and leads in 5 of 7 scored categories.

Do FreeScout and LiveAgent need an API key?

FreeScout needs an API key. LiveAgent takes an API key or an OAuth sign-in.

Can an agent call FreeScout and LiveAgent without installing anything?

No hosted endpoint is listed for FreeScout. LiveAgent has a hosted endpoint at https://<account>.ladesk.com/api/v3.

Are FreeScout and LiveAgent open source?

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

Other comparisons with FreeScout or LiveAgent

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.