Head to head · Content management · October 2026 research run

Directus vs Kontent.ai

Kontent.ai scores 70.5 (BB) on agent readiness against Directus's 67.1 (B), and leads in 2 of 7 scored categories. Directus leads on schema & documentation and payments & pricing. Both do content management.

Best headless CMS and website publishing for AI agents · All 91 cms comparisons

Which one, for what

Directus B

Good for Teams that already keep content in an SQL database and want an agent to edit items, files and the data model under a named user's permissions.

Ahead on

  • Schema & documentation, 81 against 74
  • Payments & pricing, 55 against 20

Watch for

Version 12 (10 June 2026) added licence enforcement. The free Core tier allows 3 Studio seats, 25 collections and 5 flows, and an instance over its limits is locked after a grace period

Kontent.ai BB

Good for A company already on Kontent.ai, or evaluating it on a trial, that wants an agent to draft, localise, move through workflow and publish structured content with a permission-limited key and an audit trail.

Ahead on

  • Security & auth, 81 against 68
  • Transparency & trust, 75 against 61

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install
  • Runs on your own machine
  • Free to start without a card
  • No incidents deducted, where Directus loses 6 points for them

Watch for

No price is published. The pricing page shows sliders for seats, content types and items and a form that requests a quote

Score by category

CategoryWeight this runDirectusKontent.aiEdge
Reliability16%208282even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28174Directus +7
Agent ergonomics13%16.27371Directus +2
Security & auth14%17.56881Kontent.ai +13
Payments & pricing10%12.55520Directus +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88683Directus +3
Transparency & trust7%8.86175Kontent.ai +14
Negative events≤15-60
Total67.1 · B70.5 · BB

Facts side by side

FactDirectusKontent.ai
KindHTTP APIHTTP API
VendorMonospace Inc. (Directus)Kontent CZ s.r.o.
Hosted endpointno (local only)https://manage.kontent.ai/v2
TransportsHTTP, Streamable HTTPHTTP, stdio, Streamable HTTP
AuthOAuth or keyAPI key
PricingFreemiumPaid
x402nono
LicenceMSCL-1.0-GPL (Monospace Sustainable Core Licence 1.0), source-available with a licence key for paid tiers, each version converting to GPL-3.0 after four years. @directus/sdk is MITProprietary service under the Kontent.ai Terms of Service. The management SDKs for JavaScript and .NET and the MCP server on GitHub are MIT
Tools exposed1254
Read-only variant documentednoyes
llms.txtyesyes
MCP registrynot listedio.github.kontent-ai/mcp-server
Last release2026-10-072026-10-02
Terms last updatedno date given2026-09-11
Privacy policy last updated2026-06-092025-06-02
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesyes
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
Popularity38k stars, 23k npm/wk8.4k npm/wk

Verdicts

Directus

The built-in MCP server works under the connecting user's permissions, supports OAuth limited to the MCP endpoint and blocks deletes unless an administrator allows them. Since version 12 a licence check caps the free Core tier at 3 Studio seats, 25 collections and 5 flows, and the default tool list carries about 79 KB of instructions.

Kontent.ai

Management API keys take per-area permissions, environment limits and an expiry from one minute to two years, and changes made with a key are named in the audit log. Rate limits and Retry-After are documented. No price is published, and no OpenAPI file was found. Access starts with a 30-day trial that a person opens in a browser.

Before you call either

Directus

  1. Connect with OAuth or an Authorization: Bearer header. Don't put the token in the URL as ?access_token=, where it can be logged
  2. Use /mcp?tool_mode=registry when the client loads every tool definition. Default mode sends each tool's full instructions, about 79 KB in total
  3. Read the schema tool before writing. Item payloads are untyped objects, so field names and types come only from the data model
  4. Publish a version with POST /versions/{id}/promote over REST. The MCP items tool refuses system collections such as directus_versions
  5. Count translation and junction tables against the 25-collection Core limit before creating collections

Kontent.ai

  1. Send Authorization: Bearer <key> to https://manage.kontent.ai/v2/projects/{environment_id}/.... The Management API must be switched on under Environment settings, General, Enabled APIs first
  2. Ask for a Management API key with only the permissions the task needs. Read content alone gives a read-only key, and keys expire after six months by default
  3. Stay under 10 requests a second and 400 a minute per environment, send requests one at a time, and wait the seconds in Retry-After on a 429
  4. Page lists by passing the continuation_token from the response back in the x-continuation header
  5. Create items with an external_id and write with the upsert PUT at /items/external-id/{id} so a retry after a lost response does not create a duplicate
  6. With the MCP server, call get-patch-guide before any patch tool, and use a client that prompts on destructiveHint

Questions

Which is better for AI agents, Directus or Kontent.ai?

Kontent.ai scores 70.5 (BB) on agent readiness against Directus's 67.1 (B), and leads in 2 of 7 scored categories. Directus leads on schema & documentation and payments & pricing.

Do Directus and Kontent.ai need an API key?

Directus takes an API key or an OAuth sign-in. Kontent.ai needs an API key.

Can an agent call Directus and Kontent.ai without installing anything?

No hosted endpoint is listed for Directus. Kontent.ai has a hosted endpoint at https://manage.kontent.ai/v2.

Other comparisons with Directus or Kontent.ai

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.