Category · Work & business apps
Headless CMS and website publishing for AI agents
Content management systems an agent can write to. Entries, assets, locales and the publish step, through an API or an MCP server. Compared on write access, content modelling, drafts and versions, and how a change is reviewed before it goes live.
Capability keys cms.content · cms.publish · cms.assets · cms.localisation · cms.schema · All tools
letme.dev/cms.content picks the top-graded tool in this list and says how to call it direct; calling through letme comes later.
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/searchFilters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 65 | SanitySanity US Inc. and Sanity AS · HTTP API | CMS | BB | 73.7 | none | n/a | n/a | $15 / seat-mo | OAuth or key | Hosted | ||
|
Sanity is a hosted headless CMS. Content is stored as JSON documents in the Content Lake, queried with GROQ and edited in the open-source Sanity Studio. Agents reach it through the HTTP API or the hosted MCP server at mcp.sanity.io. Top strength 26 public OpenAPI specs covering 225 operations at www.sanity.io/docs/api/openapi, plus llms.txt and a Markdown copy of every documentation page Top weakness Schema validation rules run only in Sanity Studio. The HTTP mutation API accepts a document without checking them |
||||||||||||
| 168 | StoryblokStoryblok GmbH · HTTP API | CMS | B | 67.7 | none | n/a | n/a | $99 / mo | OAuth or key | Hosted | ||
|
Storyblok is a hosted headless CMS with a visual editor. Agents write to it through the Management API (stories, components, assets, releases, workflows) or the official hosted MCP server, which wraps that API in seven tools. Top strength Official hosted MCP server at mcp.storyblok.com/mcp with seven tools (search, describe, three execute tools, two for asset upload) and a Top weakness The Management API's OpenAPI spec sits in a private repository. Only the Content Delivery API has a public spec (OpenAPI 3.1, 14 operations) |
||||||||||||
| 206 | StrapiStrapi, Inc. · HTTP API | CMS | B | 65.7 | none | n/a | n/a | $45 / mo | API key | Local | ||
|
Strapi is an open-source headless CMS for Node.js that its owner hosts, with a paid cloud. Agents create, localise and publish entries through generated REST and GraphQL APIs or a built-in MCP server. Top strength Admin tokens carry a chosen subset of the owner's permissions, down to content type, action, field and locale, with 7, 30 or 90 day expiry Top weakness Content History keeps no version for REST, GraphQL or MCP writes, and exists only on Growth and Enterprise plans |
||||||||||||
| 237 | ContentstackContentstack Inc. · HTTP API | CMS | B | 64 | none | n/a | n/a | $29 / mo | OAuth or key | Hosted + local | ||
|
Contentstack is a hosted headless CMS. Its Content Management API reads and writes entries, assets, content types, locales, releases and publishing across seven regional endpoints, and an official local MCP server wraps the same API for agents. Top strength OAuth 2.0 scopes separate read, write, publish and unpublish for entries and assets, with 60-minute tokens and a refresh grant Top weakness The MCP server's default group loads 78 tools, including nine deletes, with no readOnlyHint or destructiveHint annotations and no read-only switch |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
How we test this category
The same article created as a draft with one image and two locales, revised, published and then rolled back through each listing's management API. We check schema validation, the draft and publish states, asset upload and version history. In this run listings are graded from public evidence against the published checklist. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.
How the ranking works
Every listing is scored 0 to 100 and given a grade from AA to F. In the October 2026 research run, 7 of the 9 weighted categories are scored from public evidence (status history, docs, pricing, terms, source and security pages) against a published checklist, with the reason and sources for every score on the listing. Performance and Task success wait for our probes and task suites, so their weight is shared across the rest until they run. Negative events deduct up to 15 points. Read the methodology.
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.