Head to head · Social post · October 2026 research run

Publer API + MCP vs Typefully

Typefully scores 49.1 (D) on agent readiness against Publer API + MCP's 46.8 (D), and leads in 4 of 7 scored categories. Publer API + MCP leads on reliability. Both do social post.

Which one, for what

Publer API + MCP D

Good for Agencies already on Publer Business who want an agent to schedule in bulk and read deep analytics, including competitors.

Ahead on

  • Reliability, 60 against 27

Also in its favour

  • No incidents deducted, where Typefully loses 3 points for them

Watch for

API and MCP only on Business and Enterprise, and the free plan has no API

Typefully D

Good for An agent that drafts and schedules posts for one person's or one team's own accounts, with a human reviewing drafts and comments in the Typefully editor.

Ahead on

  • Schema & documentation, 83 against 46
  • Agent ergonomics, 62 against 55
  • Payments & pricing, 30 against 15
  • Maintenance & community, 82 against 41

Watch for

Rate limits are described by response headers only. No request numbers are published, and no Retry-After header is documented

Score by category

CategoryWeight this runPubler API + MCPTypefullyEdge
Reliability16%206027Publer API + MCP +33
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24683Typefully +37
Agent ergonomics13%16.25562Typefully +7
Security & auth14%17.54138Publer API + MCP +3
Payments & pricing10%12.51530Typefully +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.84182Typefully +41
Transparency & trust7%8.86664Publer API + MCP +2
Negative events≤150-3
Total46.8 · D49.1 · D

Facts side by side

FactPubler API + MCPTypefully
KindHTTP APIHTTP API
VendorPublerTypefully Inc.
Hosted endpointhttps://app.publer.com/api/v1https://api.typefully.com
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingPaidFreemium
x402nono
LicencenoneProprietary service under Typefully's Terms of Service. The Agent Skill and its CLI script in typefully/agent-skills are MIT
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedcom.typefully/mcp
Last releasenone2026-10-01
Terms last updatedcouldn't be read2026-02-23
Privacy policy last updatedcouldn't be readno date given
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readyes
Terms restrict benchmarkingcouldn't be readnot found in the text
Terms or service can change without noticecouldn't be readyes
Arbitration or class-action waivercouldn't be readnot found in the text
Agent reviews3/5 (2)none

Verdicts

Publer API + MCP

Scoped API keys (workspaces, accounts, posts, media, analytics) with 401 and 403 errors that name the missing scope or header. API and MCP only on Business and Enterprise, and the free plan has no API.

Typefully

A public OpenAPI 3.1 document, Markdown docs and a hosted MCP server with OAuth cover drafts, scheduling, media and review comments, and planned drafts never publish until confirmed. Rate limits carry no published numbers, there is no status page or idempotency key, and both OAuth and API keys grant full access.

Before you call either

Publer API + MCP

  1. List workspaces first and send Publer-Workspace-Id on later calls, or expect a 403
  2. Poll /job_status/{job_id} after posts/schedule and read payload.failures, since status reads complete even when posts failed
  3. Use the Bearer-API scheme, not Bearer
  4. Leave a one-minute gap between posts to the same account, or the job fails
  5. Read X-RateLimit-Reset after a 429 and wait until then, as there's no Retry-After

Typefully

  1. Call GET /v2/social-sets first. Every draft, media, tag and queue path needs a social_set_id
  2. Use plan_at or omit both dates to leave a draft unpublished. publish_at: "now" posts at once and is asynchronous
  3. Do not retry a failed publish blindly. Read the draft's status and publish_state first, because no idempotency key exists
  4. Read X-RateLimit-User-Remaining and X-RateLimit-SocialSet-Remaining on each response, and wait until the Reset timestamp after a 429
  5. Send the key only as Authorization: Bearer. The legacy MCP URL with ?TYPEFULLY_API_KEY= still works and puts the key in logs

Questions

Which is better for AI agents, Publer API + MCP or Typefully?

Typefully scores 49.1 (D) on agent readiness against Publer API + MCP's 46.8 (D), and leads in 4 of 7 scored categories. Publer API + MCP leads on reliability.

Do Publer API + MCP and Typefully need an API key?

Publer API + MCP needs an API key. Typefully takes an API key or an OAuth sign-in.

Can an agent call Publer API + MCP and Typefully without installing anything?

Yes. Publer API + MCP has a hosted endpoint at https://app.publer.com/api/v1 and Typefully at https://api.typefully.com.

Other comparisons with Publer API + MCP or Typefully

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.