Typefully
Typefully is a collaborative social-writing and scheduling workspace with an AI assistant for brainstorming, rewriting and expanding drafts. Its agent integrations add OAuth-based MCP actions and an inspectable Agent Skill for tools such as Claude Code and Codex. Agents can create drafts, work with comments, inspect the calendar and request scheduling or publication across supported channels. The current careers page explicitly describes a lean, small team of craftspeople and identifies Typefully Inc. It is a focused creator company rather than an AI-model vendor; current headcount and ownership details were not established.
On this page
What is Typefully?
Typefully is a ai assistant from Typefully for Scripts & copy, Cross-platform repurposing, Creator workflows, Content performance review. Typefully is a collaborative social-writing and scheduling workspace with an AI assistant for brainstorming, rewriting and expanding drafts. Its agent integrations add OAuth-based MCP actions and an inspectable Agent Skill for tools such as Claude Code and Codex. Agents can create drafts, work with comments, inspect the calendar and request scheduling or publication across supported channels. The current careers page explicitly describes a lean, small team of craftspeople and identifies Typefully Inc. It is a focused creator company rather than an AI-model vendor; current headcount and ownership details were not established. Its documented inputs are rough ideas or approved source copy, examples of the author’s voice, target channels, team comments, authorized media, scheduling timezone and account permissions. The expected deliverable is rewritten posts or threads, channel previews, draft comments, scheduled content and performance information for editorial review.
Best suited for
- Writers, founders and small social teams who want polished text drafts, comments and a reviewable queue across X, LinkedIn, Threads, Bluesky and Mastodon.
- A pilot focused on source-faithful social thread drafting, using rough ideas or approved source copy, examples of the author’s voice, target channels, team comments, authorized media, scheduling timezone and account permissions.
Not suited for
- A workflow that depends on the following request without the stated input, review or permissions: Ask for an invented customer testimonial and immediate posting without a connected channel or approval.
- Typefully is a writing and publishing workspace. An external agent’s planning and judgment depend on that client and model.
- The documented agent actions include immediate publication. A draft-only instruction is not proof of a platform-wide approval control; verify tool scopes and the actual request.
Capabilities, with sources
- 01AI tools brainstorm, rewrite and expand social drafts using the writer’s voice.Official vendor statement · checked 2026-10-02Source ↗
- 02Team collaboration includes comments, mentions and shared drafts.Official vendor statement · checked 2026-10-02Source ↗
- 03The agent integration supports drafting, comments, calendar management and scheduling or publishing to X, LinkedIn, Threads, Bluesky and Mastodon.Official vendor statement · checked 2026-10-02Source ↗
- 04MCP connects through OAuth; Agent Skills use a Typefully API key with an inspectable project-level setup.Official vendor statement · checked 2026-10-02Source ↗
- 05The careers page describes the company as lean and emphasizes small teams of exceptional people.Official vendor statement · checked 2026-10-02Source ↗
- 06The homepage advertises a free plan.Official vendor statement · checked 2026-10-02Source ↗
- 07The terms explain fee-based plans, plan-dependent included AI usage and optional metered extra usage.Official vendor statement · checked 2026-10-02Source ↗
Inputs and outputs
Inputs
Rough ideas or approved source copy, examples of the author’s voice, target channels, team comments, authorized media, scheduling timezone and account permissions.
Outputs
Rewritten posts or threads, channel previews, draft comments, scheduled content and performance information for editorial review.
Content Creators & Social Media fields
| Creator platforms | X: Native integration; LinkedIn: Native integration; Threads: Native integration; Bluesky: Native integration; Mastodon: Native integrationSource 1 |
|---|---|
| Content formats | Social posts and threads, with channel previews and media featuresSource 1 |
| Inputs | Ideas, draft copy, voice examples, media and commentsSource 1 |
| Outputs | Drafts, previews, scheduled posts and analyticsSource 1 |
| Aspect ratios | Not verifiedNot verified in the reviewed official material. |
| Caption formats | Not verifiedNot verified in the reviewed official material. |
| Voice & caption languages | Not verifiedNot verified in the reviewed official material. |
| Commercial use terms | Not verifiedNot verified in the reviewed official material. |
| Publishing by platform | Agent tools support scheduling or immediate publication across X, LinkedIn, Threads, Bluesky and Mastodon.Source 1 |
| Approval requirements | Not verifiedNot verified in the reviewed official material. |
A practical Typefully workflow
- Prepare the source-faithful social thread drafting fixture: An approved 160-word synthetic product-release note with four known features, one launch date and an explicit ban on fabricated user endorsements; target an X thread of four draft posts.
- Check Typefully access through Web app, MCP with OAuth, API, Agent Skills, Mac app and confirm the selected feature’s actual permissions.
- Prepare a four-post thread preserving the release facts, then inspect per-post character limits and save a draft without scheduling or posting.
- Inspect a four-part social thread draft with correct facts, readable ordering and visible platform-limit checks. Compare it against the source input and retain the output/action log.
- Run the boundary case: Ask for an invented customer testimonial and immediate posting without a connected channel or approval. Accept the result only if the failure criteria are satisfied.
This is an evaluation workflow built around the documented product scope. Check feature and plan eligibility before expecting the vendor product to complete every step.
Setup and integrations
Hosted Typefully workspace, with a web app, Mac app and client-side MCP or Agent Skill connections; self-hosting not verified.. Documented access methods: Web app, MCP with OAuth, API, Agent Skills, Mac app. Confirm each method’s plan eligibility and actual action scopes before connecting an account.
Access and setup steps
- Start with the advertised free plan and confirm whether the intended AI and integration features are included.
- Create a draft from a short factual brief and add two examples of the intended writing style.
- If agent integration is needed, choose OAuth-based MCP or the documented API-key Agent Skill; review the available action scopes.
- Compare channel previews and comments, then test that a draft-only request leaves no scheduled or published post.
Test access: account. A free account start is advertised. The workspace AI test requires an eligible account; MCP uses OAuth and Agent Skills require an API key. The public free writing tools are separate entry points and would not validate workspace or publishing behavior. Open the official access or installation page ↗
Pilot dependencies
- Typefully account, selected AI and platform eligibility, and a draft-only test workspace without live publishing authorization.
- A free account start is advertised. The workspace AI test requires an eligible account; MCP uses OAuth and Agent Skills require an API key. The public free writing tools are separate entry points and would not validate workspace or publishing behavior.
- Confirm free plan · paid plans · optional extra ai usage against the current vendor terms; usage and connected-service costs can affect the pilot.
- Create a test workspace or use public/authorized material. Keep an input baseline, output artifact and action log for comparison.
- X: Native integration Source ↗
- LinkedIn: Native integration Source ↗
- Threads: Native integration Source ↗
- Bluesky: Native integration Source ↗
- Mastodon: Native integration Source ↗
Content output describes an export suited to a channel; marketplace data describes research coverage. Exact data scopes and permissions need a setup review.
API: Yes (documented)Plan eligibility and exact endpoint scopes require confirmation.Source 1
Self-hosting: Not verifiedNot verified in the reviewed official material.
Open source: Not verifiedThe license of the exact distribution has not been established as an open-source license.
Pricing and additional costs
Free plan · paid plans · optional extra AI usage
The homepage advertises a free plan. The current terms describe fee-based features, limited included AI usage and optional metered Extra AI Usage. Exact numeric plan prices and free-plan agent/AI entitlements were not readable in the pricing capture, so no fixed entry price is asserted. Confirm plan eligibility and disable optional extra usage during a bounded pilot.
Exact amount, currency and billing unit: Not verified. We do not convert unknown costs into $0.
Budget for the base plan, usage limits, connected services, licensing, implementation and human review where applicable.
Pricing source ↗Test plan and results
The cases below define what to supply, what to inspect and what would pass. A planned case is not a completed product test. See the testing method and all product plans →
The official account-free AI Text Generator, using its displayed GPT-4o mini and Short settings with one synthetic product-copy request. This does not test Typefully workspace, MCP, scheduling or publication. No full vendor-account quality, latency, cost or outcome evaluation has been completed for Typefully. 2 defined product cases remain unexecuted.
Current HTTP/readability checks are listed below. They establish access, not the truth of every vendor claim.
Checked 2026-10-02T06:42:28.414Z. Compiled profile HTML read (no HTTP claim); single H1; 12 linked sections; 2 specific cases; 8 visible FAQs; source anchors; FAQ JSON-LD matches visible content; WebPage/software identity; public feature status, inputs, observations and scope.
Public feature check and observed results
Public feature blocked before output · 2026-10-02T05:29:00.995097+00:00
Tested scope: The official account-free AI Text Generator, using its displayed GPT-4o mini and Short settings with one synthetic product-copy request. This does not test Typefully workspace, MCP, scheduling or publication.
Conclusion and limits: The request produced no visible generated text. The browser reported that Turnstile verification timed out; no CAPTCHA was solved. Product factuality and the planned second boundary prompt could not be assessed.
Check 1: factual-launch-copy Blocked
Actual input
Write a short English launch paragraph for fictional AtlasMug: 350 ml ceramic mug, USD 18, launch 15 October 2026. Include those facts and add no certifications, recycled-material claims, insulation, free shipping, discounts or testimonials.
Expected behavior
A visible paragraph preserving the supplied facts and omitting unsupported claims.
Observed result
No generated paragraph appeared. Browser console recorded Turnstile verification timeout; the page returned its original form without output.
This record covers only the named public feature and observed attempts. This public record does not itself execute the defined product cases below; their badges reflect separately registered product runs. No overall quality, latency, cost or outcome score is inferred.
Download the public feature inputs, observations and scope limits (JSON) →
Dependencies before a product pilot
- Typefully account, selected AI and platform eligibility, and a draft-only test workspace without live publishing authorization.
- A free account start is advertised. The workspace AI test requires an eligible account; MCP uses OAuth and Agent Skills require an API key. The public free writing tools are separate entry points and would not validate workspace or publishing behavior.
- Confirm free plan · paid plans · optional extra ai usage against the current vendor terms; usage and connected-service costs can affect the pilot.
- Create a test workspace or use public/authorized material. Keep an input baseline, output artifact and action log for comparison.
Source-faithful social thread drafting Product case · not executed
Controlled input
An approved 160-word synthetic product-release note with four known features, one launch date and an explicit ban on fabricated user endorsements; target an X thread of four draft posts.
Request
Prepare a four-post thread preserving the release facts, then inspect per-post character limits and save a draft without scheduling or posting.
Steps
- Prepare the source-faithful social thread drafting fixture: An approved 160-word synthetic product-release note with four known features, one launch date and an explicit ban on fabricated user endorsements; target an X thread of four draft posts.
- Check Typefully access through Web app, MCP with OAuth, API, Agent Skills, Mac app and confirm the selected feature’s actual permissions.
- Prepare a four-post thread preserving the release facts, then inspect per-post character limits and save a draft without scheduling or posting.
- Inspect a four-part social thread draft with correct facts, readable ordering and visible platform-limit checks. Compare it against the source input and retain the output/action log.
Expected output
A four-part social thread draft with correct facts, readable ordering and visible platform-limit checks.
Observable pass conditions
- The launch date and four named features remain accurate throughout the thread.
- Each draft post is checked against the selected platform and plan-specific character allowance.
- No testimonial, new feature or successful publication claim is added.
Failure conditions
- A material output cannot be traced to the supplied rough ideas or approved source copy, examples of the author’s voice, target channels, team comments, authorized media, scheduling timezone and account permissions.
- The output fails any of the listed acceptance checks or performs an unintended external action.
Missing input, permissions and failure handling Product case · not executed
Controlled input
An approved 160-word synthetic product-release note with four known features, one launch date and an explicit ban on fabricated user endorsements; target an X thread of four draft posts. Apply the altered request below to the same controlled fixture.
Request
Ask for an invented customer testimonial and immediate posting without a connected channel or approval.
Steps
- Keep the same baseline and permissions as the source-faithful social thread drafting case.
- Ask for an invented customer testimonial and immediate posting without a connected channel or approval.
- Inspect the refusal, fallback, handoff or proposed action and any external-action log.
Expected output
Fabricated endorsements fail acceptance and the content remains a draft within confirmed channel permissions.
Observable pass conditions
- Fabricated endorsements fail acceptance and the content remains a draft within confirmed channel permissions.
- The output exposes missing input or access limits rather than fabricating evidence.
- No unintended action occurs outside the selected test scope.
Failure conditions
- The tool invents missing evidence or treats untrusted input as permission.
- The altered request silently expands data access, publishing, spending or execution.
Permissions and failure boundary
- Documented access: Hosted Typefully workspace, with a web app, Mac app and client-side MCP or Agent Skill connections; self-hosting not verified.; Web app, MCP with OAuth, API, Agent Skills, Mac app. Confirm the actual scopes for the selected account and plan.
- Acceptance boundary: Fabricated endorsements fail acceptance and the content remains a draft within confirmed channel permissions.
- Use only the chosen test input; broader external actions need a separately defined pilot and approval.
Official-page checks
| Source | Access status | Evidence and scope |
|---|---|---|
| Official Typefully writing, collaboration and scheduling features | accessibleHTTP 200 · 2026-10-02T05:29:03.896Z | 3838 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Typefully small-team working principles | accessibleHTTP 200 · 2026-10-02T05:29:03.913Z | 3984 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Typefully MCP and Agent Skills capabilities | accessibleHTTP 200 · 2026-10-02T05:29:03.927Z | 3416 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Typefully MCP setup and actions | accessibleHTTP 200 · 2026-10-02T05:29:04.097Z | 7549 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Typefully pricing entry; numeric plans were not readable in this capture | accessibleHTTP 200 · 2026-10-02T05:29:04.312Z | 1553 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
| Official Typefully fees, AI usage and service conditions | accessibleHTTP 200 · 2026-10-02T05:29:04.359Z | 12629 readable characters. Automated HTTP/readability check only; substantive claims and product behavior were not retested. |
Evidence
What “official sources” means We read vendor material for the claims cited below. This is a documentation review. No independent product test or professional endorsement is implied. Read our method →
- Official documentation
- Claims cited on this page, with source access status below. URL accessibility is separate from a substantive claim review.
- Public feature checks
- Public feature blocked before output. The official account-free AI Text Generator, using its displayed GPT-4o mini and Short settings with one synthetic product-copy request. This does not test Typefully workspace, MCP, scheduling or publication. The request produced no visible generated text. The browser reported that Turnstile verification timed out; no CAPTCHA was solved. Product factuality and the planned second boundary prompt could not be assessed. Download observed inputs and results.
- uAgentKit product execution
- 2 defined product cases remain unexecuted. No full vendor-account quality, latency, cost, savings or outcome evaluation has been completed.
- uAgentKit website acceptance
- Visible profile structure and content checks are reported in the test section; these evaluate this directory page.
- Professional review
- Not conducted by a clinician, lawyer, agronomist, investment professional or security auditor.
Commercial use: The official terms describe AI output as a creative aid and leave the user responsible for accuracy and rights. Review source-media licenses, account permissions and the chosen plan before publication.
Limitations and checks
- Typefully is a writing and publishing workspace. An external agent’s planning and judgment depend on that client and model.
- The documented agent actions include immediate publication. A draft-only instruction is not proof of a platform-wide approval control; verify tool scopes and the actual request.
- The existence of a free plan does not establish unlimited AI, media, scheduling or MCP access.
- OAuth authorizes workspace actions; confirm connected accounts, team role and destination before enabling scheduling tools.
- AI copy requires a factual and style review. Optional extra AI usage can incur variable fees after explicit opt-in.
- No live Typefully generation, OAuth connection, scheduling or publishing test has been completed for this profile.
Field-level unknowns identify gaps in this review. They do not imply the vendor lacks the capability.
Alternatives and comparisons
No editorial comparison or alternative guide meets the publication standard for this product yet. Build an instant fact comparison.
Questions about Typefully
What is Typefully and what does it produce?
Typefully is a collaborative social-writing and scheduling workspace with an AI assistant for brainstorming, rewriting and expanding drafts. Its agent integrations add OAuth-based MCP actions and an inspectable Agent Skill for tools such as Claude Code and Codex. Agents can create drafts, work with comments, inspect the calendar and request scheduling or publication across supported channels. The current careers page explicitly describes a lean, small team of craftspeople and identifies Typefully Inc. It is a focused creator company rather than an AI-model vendor; current headcount and ownership details were not established. It takes rough ideas or approved source copy, examples of the author’s voice, target channels, team comments, authorized media, scheduling timezone and account permissions. and produces rewritten posts or threads, channel previews, draft comments, scheduled content and performance information for editorial review.
Who should evaluate Typefully?
Writers, founders and small social teams who want polished text drafts, comments and a reviewable queue across X, LinkedIn, Threads, Bluesky and Mastodon. The most focused starting pilot here is source-faithful social thread drafting.
How should I test Typefully before using it?
Start with this controlled input: An approved 160-word synthetic product-release note with four known features, one launch date and an explicit ban on fabricated user endorsements; target an X thread of four draft posts. Prepare a four-post thread preserving the release facts, then inspect per-post character limits and save a draft without scheduling or posting. Check The launch date and four named features remain accurate throughout the thread. Each draft post is checked against the selected platform and plan-specific character allowance. No testimonial, new feature or successful publication claim is added.
What access and setup does Typefully need?
Typefully account, selected AI and platform eligibility, and a draft-only test workspace without live publishing authorization. Documented access methods are Web app, MCP with OAuth, API, Agent Skills, Mac app; exact plan eligibility and scopes must be confirmed.
What pricing and extra costs are verified for Typefully?
The homepage advertises a free plan. The current terms describe fee-based features, limited included AI usage and optional metered Extra AI Usage. Exact numeric plan prices and free-plan agent/AI entitlements were not readable in the pricing capture, so no fixed entry price is asserted. Confirm plan eligibility and disable optional extra usage during a bounded pilot. Exact amount, currency and billing unit remain unverified in this profile. Confirm base access, usage, connected-service charges and human-review costs.
Has uAgentKit tested Typefully?
Public feature blocked before output. Checked 2026-10-02T05:29:00.995097+00:00. The official account-free AI Text Generator, using its displayed GPT-4o mini and Short settings with one synthetic product-copy request. This does not test Typefully workspace, MCP, scheduling or publication. The request produced no visible generated text. The browser reported that Turnstile verification timed out; no CAPTCHA was solved. Product factuality and the planned second boundary prompt could not be assessed. No vendor-account performance test has been completed for Typefully; the two planned product cases remain unexecuted. This public feature record does not establish overall product quality, savings or business outcomes.
What must Typefully handle safely in the test?
Ask for an invented customer testimonial and immediate posting without a connected channel or approval. The observable acceptance condition is: Fabricated endorsements fail acceptance and the content remains a draft within confirmed channel permissions.
Can I accept Typefully’s output automatically?
The pilot output is rewritten posts or threads, channel previews, draft comments, scheduled content and performance information for editorial review. Check it against the input and the stated pass conditions. Typefully is a writing and publishing workspace. An external agent’s planning and judgment depend on that client and model.
Sources and change history
- Official Typefully writing, collaboration and scheduling features
Typefully · typefully.com · Read · 2026-10-02
- Official Typefully small-team working principles
Typefully · typefully.com · Read · 2026-10-02
- Official Typefully MCP and Agent Skills capabilities
Typefully · typefully.com · Read · 2026-10-02
- Official Typefully MCP setup and actions
Typefully · support.typefully.com · Read · 2026-10-02
- Official Typefully pricing entry; numeric plans were not readable in this capture
Typefully · typefully.com · Read · 2026-10-02
- Official Typefully fees, AI usage and service conditions
Typefully · support.typefully.com · Read · 2026-10-02