{ "data": { "a": { "slug": "repostit", "name": "Repostit", "vendor": "Repostit LLC", "vendorUrl": "https://repostit.io", "kind": "platform", "category": "social-media", "summary": "Repostit is a hosted service that reposts short videos from one connected social account to others and schedules new posts across eight networks. Agents reach it through a remote OAuth MCP connector listed for Claude and ChatGPT.", "url": "https://www.anchorterminal.com/tools/repostit", "markdownUrl": "https://www.anchorterminal.com/tools/repostit.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/repostit.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/repostit.json", "dns": "repostit.grade.anchorterminal.com", "license": "Proprietary hosted service under Repostit's terms of service (effective 7 March 2025), which name Repostit LLC of Newark, Delaware. No source, SDK or package is published", "transports": [ "streamable-http" ], "remoteUrl": "https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1", "packages": [], "auth": "oauth", "authNotes": "The connector at https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1 (named on Repostit's own Claude connector page) uses OAuth with dynamic client registration and no client secret; the user signs in to Repostit and reviews the permissions (read connected accounts, create workflows and Briefs, schedule or publish, read delivery status). Approved offline access renews for up to 90 days from the first authorisation. Social-network sign-ins happen inside Repostit and provider tokens are not passed to Claude or ChatGPT. PKCE S256 is stated only in third-party metadata. No scopes, API keys or token lifetimes are published, and revocation is by disconnecting in the client or asking support@repostit.io.", "pricing": "paid", "pricingNotes": "Every reposting plan starts with a 14-day trial with no credit card, limited to 10 posts counted per destination, 3 workflows and one account per network. Basic $5 a month (10 video posts, monthly only), Starter $14 a month or $10 billed yearly, Influencer $29 or $20 (5 accounts per network), Agency $149 or $99 (30 accounts per network); paid plans above Basic have unlimited automated posts and every plan includes the Claude and ChatGPT connector. Clips is priced separately by minutes, with a free allowance of 10 videos or 100 minutes. Fees are non-refundable except where law requires (https://repostit.io/pricing/ and https://repostit.io/docs/repostit-refund-policy/, checked 2026-11-03).", "priceSummary": "$5 / mo", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the pricing page, the help centre, the two connector pages, the terms or the privacy policy (checked 2026-11-03). Plans are paid in the app through unnamed third-party payment processors per the terms.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-03" }, "docsUrl": "https://repostit.io/docs/", "llmsTxt": "https://repostit.io/llms.txt", "registryName": "io.github.hax98/repostit", "capabilities": [ "social.post", "social.schedule", "social.media-upload" ], "tags": [ "hosted", "official", "closed-source", "mcp", "remote-mcp", "mcp-registry", "oauth", "llms-txt", "video", "free-trial", "no-card", "paid", "no-status-page" ], "lastRelease": "2026-10-23", "graded": true, "anchor": { "graded": true, "score": 32.5, "grade": "F", "agentReady": false, "rank": 1191, "ranked": true, "rankOf": 1272, "categoryRank": 16, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 25, "maintenance": 56, "payments": 30, "reliability": 26, "schema": 27, "security": 44, "transparency": 29 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-03" }, "negative": 0, "verdict": "An OAuth connector lets an agent list accounts, draft and schedule posts, build reposting workflows and check delivery, with drafts saved before anything publishes and a 14-day trial without a card. Tool names, schemas, scopes and error shapes are unpublished, the endpoint sits on a Cloud Run host, and there is no status page, public API or named subprocessor.", "bestFor": "Creators, small businesses and agencies who post short vertical video on one network and want an assistant in Claude or ChatGPT to copy it to others on a schedule, set up reposting workflows and confirm what went out, without writing code.", "strengths": [ "Remote MCP connector with OAuth and dynamic client registration, listed for Claude and ChatGPT and in the official MCP registry, with social-network tokens kept inside Repostit", "Briefs are saved as drafts, queued Briefs are locked against a second send and Manual workflows wait for approval, so nothing publishes on creation alone", "Delivery checks report a result per destination with public links, and assistant-made posts show each step in the dashboard's Comments \u0026 Activity", "Eight networks with published media rules (20 MB images, carousel caps per network, 9:16 video at 1080 by 1920) and per-network failure guides", "14-day trial with no card, then plans from $5 a month, with the connector included in every plan" ], "weaknesses": [ "No tool names, input schemas, annotations, scopes or error shapes are published, and no public REST API, SDK or OpenAPI file exists", "The MCP endpoint is on a run.app host, not repostit.io, and the registry entry sits under a personal GitHub namespace", "No status page, incident history, SLA, request rate limit or 429 guidance; no help page says failed posts are retried", "The privacy policy names no subprocessors, retention periods or data locations and does not mention the connector or its 90-day offline access", "The terms name Repostit LLC while every footer says Repostit, Inc., and the ChatGPT page and directory disagree on whether version 1.1 is out" ], "agentNotes": [ "List connected accounts first and confirm names and platforms with the user before choosing destinations; a missing account must be connected in Repostit Connections, not through the agent.", "Pass media as a downloadable HTTPS URL, never a local filename, and give every scheduled time with an explicit timezone.", "Treat Queued as accepted, not published; check delivery status and public links before reporting success, and check the existing result before any retry to avoid duplicate posts.", "Creating a future-content workflow makes it publish on its own once active; prefer existing-content workflows or Manual mode when the user wants to review first.", "On the trial, each destination counts as one of 10 posts and Basic allows 10 video posts a month; ask before fanning one Brief out to many networks." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 32.5 } ], "editorialScores": { "ergonomics": 25, "maintenance": 56, "payments": 30, "reliability": 26, "schema": 27, "security": 44, "transparency": 27 }, "provenanceScore": 31, "checked": { "categories": { "ergonomics": "2026-11-03", "maintenance": "2026-11-03", "payments": "2026-11-03", "reliability": "2026-11-03", "schema": "2026-11-03", "security": "2026-11-03", "transparency": "2026-11-03" }, "last": "2026-11-03", "oldest": "2026-11-03", "stale": false, "staleAfterDays": 90 } }, "connect": { "config": { "mcpServers": { "repostit": { "type": "http", "url": "https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1" } } } }, "letme": { "capability": "https://letme.dev/social.post", "tool": "https://letme.dev/repostit" }, "area": "communication", "unitPrices": [ { "item": "Basic plan", "unit": "month", "usd": 5, "note": "monthly billing only; 10 video posts a month, one account per network" }, { "item": "Starter plan", "unit": "month", "usd": 14, "note": "$10 a month billed yearly; unlimited automated posts, one account per network" }, { "item": "Influencer plan", "unit": "month", "usd": 29, "note": "$20 a month billed yearly; unlimited automated posts, 5 accounts per network" }, { "item": "Agency plan", "unit": "month", "usd": 149, "note": "$99 a month billed yearly; unlimited automated posts, 30 accounts per network" } ], "provenance": { "legalEntity": "Repostit LLC", "domain": "repostit.io", "domainRegistered": "", "endpointOnVendorDomain": false, "terms": "https://repostit.io/terms-of-service/", "privacy": "https://repostit.io/privacy-policy/", "statusPage": "", "changelog": "", "securityTxt": "unknown", "checked": "2026-11-03", "notes": [ "The terms of service (effective 7 March 2025, no later revision) say the service is operated by Repostit LLC, 254 Chapman Road Ste 208, Newark, DE 19702, under Delaware law. The footer of every page read says '© 2026 Repostit, Inc.', and the privacy policy (29 July 2026) names only Repostit.io with the same address. Recorded as an inconsistency; the legal entity is taken from the terms.", "The MCP endpoint is on repostit-mcp-cfjcykgqda-uc.a.run.app, a Google Cloud Run host, not a repostit.io host. Repostit's own page https://app.repostit.io/claude-connector.html names it. Its robots.txt did not load, so nothing on that host was fetched, including the OAuth well-known documents.", "/whats-new/ lists undated items (the Claude and ChatGPT connector among them), so it is not recorded as a changelog. No status page is linked anywhere; /status/ and /.well-known/security.txt did not load through our reader, which also fails on the home page, so security.txt is recorded as unknown.", "RDAP for repostit.io and the Wayback Machine were not read (the fetch needed an approval that did not come). firstReleased is 2025-03-07, the terms' effective date, the earliest first-hand date found; the connector's earliest date is the public ChatGPT app described on a page updated 24 September 2026, and the first registry version is 17 October 2026.", "robots.txt on repostit.io allows everything except /api/, which was not fetched. app.repostit.io answers /robots.txt with the app's HTML shell and no directives; only the two connector pages and /llms.txt were read there." ], "score": 31 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/repostit.json", "live": { "slug": "repostit", "probe": { "target": "https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1", "method": "get", "lastAt": "2026-11-03T18:20:19.53499017Z", "lastOk": true, "lastStatus": 405, "lastMs": 151, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 155, "p95ms24h": 196, "samples24h": 44, "samples30d": 44, "days": [ { "date": "2026-11-03", "probes": 44, "ok": 44 } ] }, "versions": [ { "registry": "mcp-registry", "name": "io.github.hax98/repostit", "version": "2026.10.23", "seenAt": "2026-11-03T16:51:07.971176756Z" } ], "securityTxt": { "url": "https://repostit.io/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-03T15:51:15.292804476Z" }, "llmsTxt": { "url": "https://repostit.io/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-03T15:20:58.151732377Z" }, "updatedAt": "2026-11-03T18:20:19.53499017Z" } }, "answer": "Typefully scores 49.3 (D) on agent readiness against Repostit's 32.5 (F), and leads in 5 of 7 scored categories. Repostit leads on security \u0026 auth.", "b": { "slug": "typefully", "name": "Typefully", "vendor": "Typefully Inc.", "vendorUrl": "https://typefully.com", "kind": "http-api", "category": "social-media", "summary": "Typefully is a writing and scheduling app for social posts on X, LinkedIn, Threads, Bluesky, Mastodon and Substack Notes. Its REST API v2 and hosted MCP server create, schedule and publish drafts for the account's own connected profiles.", "url": "https://www.anchorterminal.com/tools/typefully", "markdownUrl": "https://www.anchorterminal.com/tools/typefully.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/typefully.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/typefully.json", "dns": "typefully.grade.anchorterminal.com", "repo": "https://github.com/typefully/agent-skills", "license": "Proprietary service under Typefully's Terms of Service. The Agent Skill and its CLI script in typefully/agent-skills are MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.typefully.com", "packages": [], "auth": "mixed", "authNotes": "Self-serve. A signed-in user creates an API key in Settings, API and sends it as `Authorization: Bearer`. A key carries the permissions of the user who created it, and access to each social set (read, write or publish) decides which operations work. The hosted MCP server accepts OAuth (authorisation code grant with PKCE S256, dynamic client registration, a revocation endpoint, one scope `full_access`) or the API key as a Bearer header. API v1 keys do not work with v2.", "pricing": "freemium", "pricingNotes": "A free plan and paid plans billed monthly or yearly. The pricing page draws its figures by script and they were not read on 2026-10-08. The page's own scripts name free, creator and team plans and a per-social-set billing model. The vendor's undated blog post gives a paid plan at $12.50 a month and a 14-day trial. The API, MCP server and webhooks were announced as available to all users on 17 December 2025, and draft creation can answer 402 when an account needs a paid plan.", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the API reference, the OpenAPI document, llms.txt or the AI agents page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://typefully.com/docs/api", "llmsTxt": "https://typefully.com/llms.txt", "openapi": "https://api.typefully.com/v2/openapi.json", "registryName": "com.typefully/mcp", "capabilities": [ "social.post", "social.schedule", "social.media-upload" ], "tags": [ "hosted", "freemium", "free-tier", "mcp", "oauth", "openapi", "llms-txt", "webhooks", "agent-skill" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 49.3, "grade": "D", "agentReady": false, "rank": 992, "ranked": true, "rankOf": 1272, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 62, "maintenance": 82, "payments": 30, "reliability": 27, "schema": 83, "security": 38, "transparency": 66 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -3, "negativeNotes": [ "2026-07-09. The vendor's own agent-skills changelog records that the API's tightened request schemas began rejecting platform-specific fields on the wrong platform with HTTP 422, which broke `drafts:update` in the vendor's CLI until it was patched the same day. No notice was found in the product changelog. Fixed on the client side and documented there, so -3 (https://github.com/typefully/agent-skills/blob/main/skills/typefully/CHANGELOG.md)" ], "verdict": "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.", "bestFor": "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.", "strengths": [ "OpenAPI 3.1 document for 24 operations and seven webhook events, with the same reference served as Markdown and indexed in `llms.txt`", "Hosted MCP server at `https://mcp.typefully.com/mcp` with OAuth, PKCE and dynamic client registration, listed in the official MCP registry as `com.typefully/mcp`", "A draft can be saved, planned, scheduled or published, and a planned draft never publishes until `publish_at` confirms it", "Errors return a code, a message and field-level details with the path of the failing field", "Draft Activity records who changed a draft and whether the change came through MCP or the API" ], "weaknesses": [ "Rate limits are described by response headers only. No request numbers are published, and no `Retry-After` header is documented", "No status page, incident history or SLA was found. The terms supply the service as is", "No idempotency key on draft creation, so a retried `publish_at: \"now\"` call can post twice", "OAuth has one scope, `full_access`, and an API key carries every permission of the user who created it", "The terms say accounts must be registered by a human and forbid processes that run while the user is not logged in" ], "agentNotes": [ "Call `GET /v2/social-sets` first. Every draft, media, tag and queue path needs a `social_set_id`", "Use `plan_at` or omit both dates to leave a draft unpublished. `publish_at: \"now\"` posts at once and is asynchronous", "Do not retry a failed publish blindly. Read the draft's `status` and `publish_state` first, because no idempotency key exists", "Read `X-RateLimit-User-Remaining` and `X-RateLimit-SocialSet-Remaining` on each response, and wait until the `Reset` timestamp after a 429", "Send the key only as `Authorization: Bearer`. The legacy MCP URL with `?TYPEFULLY_API_KEY=` still works and puts the key in logs" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 49.3 } ], "editorialScores": { "ergonomics": 62, "maintenance": 82, "payments": 30, "reliability": 27, "schema": 83, "security": 38, "transparency": 55 }, "provenanceScore": 76, "checked": { "categories": { "ergonomics": "2026-10-08", "maintenance": "2026-10-08", "payments": "2026-10-08", "reliability": "2026-10-08", "schema": "2026-10-08", "security": "2026-10-08", "transparency": "2026-10-08" }, "last": "2026-10-08", "lastMoved": "2026-10-27", "oldest": "2026-10-08", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npx skills add typefully/agent-skills", "http": "curl https://api.typefully.com/v2/me -H \"Authorization: Bearer $TYPEFULLY_API_KEY\"", "claudeCode": "claude mcp add typefully --transport http --url \"https://mcp.typefully.com/mcp\"", "config": { "mcpServers": { "typefully": { "serverUrl": "https://mcp.typefully.com/mcp" } } } }, "letme": { "capability": "https://letme.dev/social.post", "tool": "https://letme.dev/typefully" }, "area": "communication", "provenance": { "legalEntity": "Typefully Inc.", "domain": "typefully.com", "domainRegistered": "2016-06-06", "endpointOnVendorDomain": true, "terms": "https://support.typefully.com/en/articles/8718440-terms-of-service", "privacy": "https://support.typefully.com/en/articles/8718444-privacy-policy", "statusPage": "", "changelog": "https://typefully.com/changelog", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "typefully.com/terms and typefully.com/privacy redirect to the two help centre articles named here. The terms are dated 23 February 2026 and name Typefully Inc. No separate API terms or DPA were found.", "The privacy policy names Typefully Inc., says the service is operated in the United States and defines the Services to include any related APIs. It gives no postal address.", "No status page was found. status.typefully.com did not complete a TLS connection, and the API catalogue's status link points at the API root. The MCP server answers a health check at https://mcp.typefully.com/health.", "typefully.com/.well-known/security.txt returns 404.", "RDAP for typefully.com gives a registration date of 2016-06-06.", "The changelog is the product changelog. API changes appear in it as dated entries, with no separate API changelog." ], "score": 76 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/typefully.json", "live": { "slug": "typefully", "probe": { "target": "https://api.typefully.com", "method": "get", "lastAt": "2026-11-03T18:20:27.29677025Z", "lastOk": true, "lastStatus": 200, "lastMs": 325, "authRequired": false, "uptime24h": 100, "uptime30d": 99.97, "p50ms24h": 240, "p95ms24h": 481, "samples24h": 250, "samples30d": 6373, "days": [ { "date": "2026-10-09", "probes": 169, "ok": 169 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 247, "ok": 246 }, { "date": "2026-10-13", "probes": 248, "ok": 248 }, { "date": "2026-10-14", "probes": 249, "ok": 249 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 251 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 256, "ok": 256 }, { "date": "2026-10-19", "probes": 255, "ok": 255 }, { "date": "2026-10-20", "probes": 252, "ok": 252 }, { "date": "2026-10-21", "probes": 253, "ok": 253 }, { "date": "2026-10-22", "probes": 253, "ok": 253 }, { "date": "2026-10-23", "probes": 248, "ok": 248 }, { "date": "2026-10-24", "probes": 251, "ok": 251 }, { "date": "2026-10-25", "probes": 250, "ok": 250 }, { "date": "2026-10-26", "probes": 252, "ok": 252 }, { "date": "2026-10-27", "probes": 249, "ok": 249 }, { "date": "2026-10-28", "probes": 250, "ok": 250 }, { "date": "2026-10-29", "probes": 249, "ok": 249 }, { "date": "2026-10-30", "probes": 249, "ok": 249 }, { "date": "2026-10-31", "probes": 251, "ok": 251 }, { "date": "2026-11-01", "probes": 249, "ok": 249 }, { "date": "2026-11-02", "probes": 250, "ok": 250 }, { "date": "2026-11-03", "probes": 191, "ok": 191 } ] }, "versions": [ { "registry": "mcp-registry", "name": "com.typefully/mcp", "version": "1.0.0", "seenAt": "2026-11-03T16:51:07.971176756Z" } ], "githubStars": 63, "securityTxt": { "url": "https://typefully.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-03T15:51:25.272612239Z" }, "llmsTxt": { "url": "https://typefully.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-03T15:21:19.378847373Z" }, "domain": { "domain": "typefully.com", "registered": "2016-06-06", "source": "https://rdap.verisign.com/com/v1/domain/typefully.com", "checkedAt": "2026-11-01T14:19:30.340660751Z" }, "pages": [ { "url": "https://typefully.com/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-11-03T08:01:05.184085046Z", "changedAt": "2026-10-29T05:18:04.238874332Z", "fingerprint": "df6dd1cccd6c" }, { "url": "https://support.typefully.com/en/articles/8718444-privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-11-03T08:00:11.222946753Z", "changedAt": "2026-11-01T06:54:05.575766132Z", "fingerprint": "5e8290cce4b7" }, { "url": "https://support.typefully.com/en/articles/8718440-terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-11-03T08:00:08.66305313Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "87c4b899e99b" } ], "github": { "repo": "typefully/agent-skills", "checkedAt": "2026-11-02T09:33:35.853212502Z", "stars": 63, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-27T11:34:17Z", "openIssues": 6, "openPRs": 2, "issuesOpened90d": 0, "issuesClosed90d": 0, "prsMerged90d": 5, "ci": { "branch": "main", "runs": 23, "success": 23, "failure": 0, "other": 0, "latest": "success", "latestAt": "2026-10-27T11:34:49Z" }, "replies": { "sampled": 6, "unanswered": 6 } }, "updatedAt": "2026-11-03T18:20:27.29677025Z" } }, "edges": [ { "by": 56, "category": "schema", "leads": "typefully", "name": "Schema \u0026 documentation", "reasons": { "a": "MCP reading, since the connector is the only surface an outside agent reaches; no public REST API, developer page, OpenAPI file, SDK or package was found in the help centre, /whats-new/, the sitemap, llms.txt, GitHub, npm or the MCP registry. No tool names or input schemas are published anywhere, and no session was opened to read them (0 of 25). llms.txt exists, but it is a Rank Math index of site URLs that includes theme placeholder entries, and help articles are HTML only (5 of 10). The Claude connector page says what each step is for and when not to use it, list accounts before choosing a destination, a Brief saves a draft and neither publishes nor schedules, publishing applies to every destination in a Brief, Queued is not delivery, future-content workflows publish once active while existing-content ones import for review (8 of 20). Inputs are described in prose only, formats per destination, JPEG, PNG or WebP up to 20 MB, carousel caps of 4, 10 and 20 by network, media at a downloadable HTTPS URL and a timezone with every scheduled time (4 of 15). Plain-language example requests and per-network failure reasons written for people; no example tool call, response or error shape (5 of 15). The endpoint path carries v1.1 and the registry holds 2026.10.17 and 2026.10.23; /whats-new/ is undated and no changelog was found (5 of 15). 0+5+8+4+5+5 = 27.", "b": "Public OpenAPI 3.1.0 document for 24 operations and seven webhook events (25). `llms.txt`, the full reference as Markdown and an RFC 9727 API catalogue (10). Descriptions state purpose, the permission each call needs and how drafts move between states, with less on when not to use a call (15). Inputs are typed per platform with 18 enums, length limits and required fields, though `publish_at` mixes keywords and datetimes in one string (12). 239 examples and error responses on every operation, with no list of error codes (11). The version is in the path and API changes are dated in the product changelog, with no API changelog of its own (10)." }, "scores": { "a": 27, "b": 83 } }, { "by": 37, "category": "ergonomics", "leads": "typefully", "name": "Agent ergonomics", "reasons": { "a": "MCP reading. The tool count is not published. The connector pages describe seven actions (list accounts, create, schedule and publish a Brief, check delivery, create a workflow, send a connection link), which suggests a small set, but the definitions were not read, so a middle reading rather than full marks (10 of 25). No pagination, filtering or output-size controls are documented (0 of 20). Delivery checks report a result per destination with public links when the network gives one, and the help centre lists failure reasons per network, but no error codes or connector error messages are documented (5 of 20). No idempotency key and no readOnlyHint or destructiveHint seen; Briefs start as drafts, queued Briefs are locked against a second send, Manual workflows hold posts for approval and the guidance says to check before retrying (6 of 20). Requests are made in plain language with few stated requirements (an HTTPS media URL, a timezone); no SDK in any language (4 of 15). 10+0+5+6+4 = 25.", "b": "List calls take `limit` up to 50 with a default of 10, and a draft read can drop comment markers, but there is no field selection (15). Limit and offset pagination with status, tag and ordering filters on drafts (20). Errors carry a code, a message and field details with a location path (16). No idempotency key. A planned draft is a write that cannot publish, which makes retries safer for that state only, and MCP tool annotations were not read (4). Creating a draft needs only `platforms`, but there is no official SDK, only the skill's CLI script (7)." }, "scores": { "a": 25, "b": 62 } }, { "by": 37, "category": "transparency", "leads": "typefully", "name": "Transparency \u0026 trust", "reasons": { "a": "Closed service. The terms of service (effective 7 March 2025, no revision since) name Repostit LLC of Newark, Delaware, with Delaware law and arbitration, take a non-exclusive licence to content only to run the service and say fees are non-refundable; every footer says Repostit, Inc., and the terms do not mention the connector (12 of 30). The privacy policy (29 July 2026) keeps data until the account is deleted or as needed, with no periods, deletes Pinterest credentials on disconnect but says nothing of other networks' tokens, names no DPA, and does not mention the connector or its 90-day offline access; the account deletion article gives no timeline and leaves network-side access to the user (10 of 30). No deprecation policy or dated notices; the terms promise notice of significant changes and the ChatGPT page names a pending version 1.1 without a date (3 of 20). Subprocessors are 'hosting providers, analytics services', unnamed, with transfers outside the user's country and no locations; the Tawk.to chat on the contact page and the Google Cloud Run host of the connector are not named in the policy (2 of 20). 12+10+3+2 = 27.", "b": "Closed service under published terms, with the Agent Skill under MIT (15). The privacy policy says deleted data is purged within 30 days, that AI providers may not train on customer data and that data is processed in the United States, and it links a sub-processor list. No DPA was found, and the terms say only that data may be kept for a limited period (20). No deprecation policy. The v1 to v2 migration guide gives no end date for v1, `draft_id` is marked deprecated with no date, and the terms may change without notice (4). About 30 sub-processors listed by purpose on a page dated 3 March 2026, without locations for each (16)." }, "scores": { "a": 29, "b": 66 } }, { "by": 26, "category": "maintenance", "leads": "typefully", "name": "Maintenance \u0026 community", "reasons": { "a": "Closed service. The latest registry version is 2026.10.23, published 23 October 2026, and the connector article was updated 22 October 2026 (30). Dated changes in the last 90 days are the two registry versions of 17 and 23 October 2026; /whats-new/ is undated and the ChatGPT app's 1.1.0 (per the 3 November listing check) carries no date, so fewer than three dated releases (10 of 20). Support is email and weekday chat, 9am to 5pm Eastern, with replies within 24 hours; no public changelog with dates, forum or issue tracker (6 of 15). In the official MCP registry as io.github.hax98/repostit, a GitHub-verified namespace of a personal account; the entry links Repostit's own pages and its address matches the vendor's connector page, but no first-hand page ties the account to the company, so partial credit (10 of 15). No packages, public code or CI to judge (0 of 10). 30+10+6+10+0 = 56.", "b": "Product changelog entry on 20 September 2026 and an agent-skills commit on 1 October 2026 (30). Five dated changelog entries between 8 July and 20 September 2026 (20). Public changelog, a Discord community, email and in-app chat, with no public issue tracker for the API (10). Listed in the official MCP registry as `com.typefully/mcp`, active since 1 September 2026 (15). The skill repository runs a test workflow, and there is no SDK to judge (7)." }, "scores": { "a": 56, "b": 82 } }, { "by": 6, "category": "security", "leads": "repostit", "name": "Security \u0026 auth", "reasons": { "a": "OAuth with dynamic client registration and no client secret, per Repostit's Claude connector page, with offline access that renews for up to 90 days from the first authorisation; social-network sign-ins stay in Repostit and provider tokens are not passed to the assistant. PKCE S256 is stated only in third-party metadata. No scopes are named; the page lists the permissions shown at sign-in (read accounts, create workflows and Briefs, schedule or publish, read delivery status). Revocation is by disconnecting in the client or asking support (18 of 30). A Brief is saved as a draft, Manual workflows wait for approval, and the help article says the assistant shows each step for confirmation before publishing (on ChatGPT 'may ask', depending on the client); no read-only mode, and an activated future-content workflow publishes on its own (8 of 20). Tools return the user's own accounts, Briefs and delivery results and read no comments or messages (10). Assistant-created posts appear under Post with a Comments \u0026 Activity log of each step, and Post History shows each network's response; no per-call log for the connector (8 of 15). security.txt did not load through our reader, and no disclosure policy, bug bounty or certification appears on any page read (0 of 20). 18+8+10+8+0 = 44.", "b": "OAuth on the MCP server with PKCE, dynamic client registration and revocation, and revocable API keys, but one scope `full_access` and keys that carry all of the creating user's permissions (20). The MCP article says the old URL form with the key in `?TYPEFULLY_API_KEY=` still works (-10). Read, write and publish access per social set is inherited from the user, and planned drafts need a confirming call, but no read-only key exists (10). Responses hold the workspace's own drafts and teammates' comments, with no injection guidance found (6). Draft Activity records who changed a draft and labels MCP or API as the source (10). No security.txt, bug bounty or certification was found, only a short security section in the privacy policy (2)." }, "scores": { "a": 44, "b": 38 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Repostit LLC", "b": "Typefully Inc.", "name": "Vendor" }, { "a": "https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1", "b": "https://api.typefully.com", "name": "Hosted endpoint" }, { "a": "Streamable HTTP", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "OAuth", "b": "OAuth or key", "name": "Auth" }, { "a": "Paid", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Proprietary hosted service under Repostit's terms of service (effective 7 March 2025), which name Repostit LLC of Newark, Delaware. No source, SDK or package is published", "b": "Proprietary service under Typefully's Terms of Service. The Agent Skill and its CLI script in typefully/agent-skills are MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "io.github.hax98/repostit", "b": "com.typefully/mcp", "name": "MCP registry" }, { "a": "2026-10-23", "b": "2026-10-01", "name": "Last release" }, { "a": "not read yet", "b": "2026-02-23", "name": "Terms last updated" }, { "a": "not read yet", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "yes", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "yes", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Typefully scores 49.3 (D) on agent readiness against Repostit's 32.5 (F), and leads in 5 of 7 scored categories. Repostit leads on security \u0026 auth.", "question": "Which is better for AI agents, Repostit or Typefully?" }, { "answer": "Yes. Repostit has a hosted endpoint at https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1 and Typefully at https://api.typefully.com.", "question": "Can an agent call Repostit and Typefully without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Security \u0026 auth, 44 against 38" ], "also": [ "Free to start without a card", "No incidents deducted, where Typefully loses 3 points for them" ], "goodFor": "Creators, small businesses and agencies who post short vertical video on one network and want an assistant in Claude or ChatGPT to copy it to others on a schedule, set up reposting workflows and confirm what went out, without writing code.", "slug": "repostit", "watchFor": "No tool names, input schemas, annotations, scopes or error shapes are published, and no public REST API, SDK or OpenAPI file exists" }, { "aheadOn": [ "Schema \u0026 documentation, 83 against 27", "Agent ergonomics, 62 against 25", "Maintenance \u0026 community, 82 against 56", "Transparency \u0026 trust, 66 against 29" ], "also": null, "goodFor": "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.", "slug": "typefully", "watchFor": "Rate limits are described by response headers only. No request numbers are published, and no `Retry-After` header is documented" } ], "history": { "repostit": null, "typefully": [ { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.2, "from": 49.1, "fromGrade": "D", "to": 49.3, "toGrade": "D" } ] }, "job": { "capability": "social.post", "name": "Social posting" }, "others": [ { "json": "https://www.anchorterminal.com/compare/ayrshare-vs-repostit.json", "title": "Ayrshare API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/ayrshare-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/ayrshare-vs-typefully.json", "title": "Ayrshare API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/ayrshare-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/blotato-vs-repostit.json", "title": "Blotato vs Repostit", "url": "https://www.anchorterminal.com/compare/blotato-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/blotato-vs-typefully.json", "title": "Blotato vs Typefully", "url": "https://www.anchorterminal.com/compare/blotato-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/buffer-vs-repostit.json", "title": "Buffer API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/buffer-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/buffer-vs-typefully.json", "title": "Buffer API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/buffer-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/bundle-social-vs-repostit.json", "title": "bundle.social vs Repostit", "url": "https://www.anchorterminal.com/compare/bundle-social-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/bundle-social-vs-typefully.json", "title": "bundle.social vs Typefully", "url": "https://www.anchorterminal.com/compare/bundle-social-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/late-vs-repostit.json", "title": "Zernio (formerly Late) API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/late-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/late-vs-typefully.json", "title": "Zernio (formerly Late) API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/late-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/metricool-vs-repostit.json", "title": "Metricool API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/metricool-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/metricool-vs-typefully.json", "title": "Metricool API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/metricool-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/mixpost-vs-repostit.json", "title": "Mixpost API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/mixpost-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/mixpost-vs-typefully.json", "title": "Mixpost API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/mixpost-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/oneup-vs-repostit.json", "title": "OneUp API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/oneup-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/oneup-vs-typefully.json", "title": "OneUp API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/oneup-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/post-bridge-vs-repostit.json", "title": "Post Bridge API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/post-bridge-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/post-bridge-vs-typefully.json", "title": "Post Bridge API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/post-bridge-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/postiz-vs-repostit.json", "title": "Postiz API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/postiz-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/postiz-vs-typefully.json", "title": "Postiz API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/postiz-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/publer-vs-repostit.json", "title": "Publer API + MCP vs Repostit", "url": "https://www.anchorterminal.com/compare/publer-vs-repostit" }, { "json": "https://www.anchorterminal.com/compare/publer-vs-typefully.json", "title": "Publer API + MCP vs Typefully", "url": "https://www.anchorterminal.com/compare/publer-vs-typefully" }, { "json": "https://www.anchorterminal.com/compare/repostit-vs-upload-post.json", "title": "Repostit vs Upload-Post API + MCP", "url": "https://www.anchorterminal.com/compare/repostit-vs-upload-post" }, { "json": "https://www.anchorterminal.com/compare/typefully-vs-upload-post.json", "title": "Typefully vs Upload-Post API + MCP", "url": "https://www.anchorterminal.com/compare/typefully-vs-upload-post" }, { "json": "https://www.anchorterminal.com/compare/repostit-vs-socialcannon.json", "title": "Repostit vs SocialCannon", "url": "https://www.anchorterminal.com/compare/repostit-vs-socialcannon" }, { "json": "https://www.anchorterminal.com/compare/socialcannon-vs-typefully.json", "title": "SocialCannon vs Typefully", "url": "https://www.anchorterminal.com/compare/socialcannon-vs-typefully" } ], "panel": null, "scores": [ { "by": 1, "edge": "typefully", "key": "reliability", "name": "Reliability", "repostit": 26, "typefully": 27, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 56, "edge": "typefully", "key": "schema", "name": "Schema \u0026 documentation", "repostit": 27, "typefully": 83, "weight": 13 }, { "by": 37, "edge": "typefully", "key": "ergonomics", "name": "Agent ergonomics", "repostit": 25, "typefully": 62, "weight": 13 }, { "by": 6, "edge": "repostit", "key": "security", "name": "Security \u0026 auth", "repostit": 44, "typefully": 38, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "repostit": 30, "typefully": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 26, "edge": "typefully", "key": "maintenance", "name": "Maintenance \u0026 community", "repostit": 56, "typefully": 82, "weight": 7 }, { "by": 37, "edge": "typefully", "key": "transparency", "name": "Transparency \u0026 trust", "repostit": 29, "typefully": 66, "weight": 7 } ], "summary": "Typefully scores 49.3 (D) on agent readiness against Repostit's 32.5 (F), and leads in 5 of 7 scored categories. Repostit leads on security \u0026 auth. Both do social posting.", "tasks": null, "tutorials": [ { "title": "Draft a two-post thread with Typefully", "tool": "typefully", "url": "https://www.anchorterminal.com/tutorials/typefully/" } ], "verdicts": { "repostit": "An OAuth connector lets an agent list accounts, draft and schedule posts, build reposting workflows and check delivery, with drafts saved before anything publishes and a 14-day trial without a card. Tool names, schemas, scopes and error shapes are unpublished, the endpoint sits on a Cloud Run host, and there is no status page, public API or named subprocessor.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/repostit-vs-typefully", "json": "https://www.anchorterminal.com/compare/repostit-vs-typefully.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/repostit-vs-typefully.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/repostit-vs-typefully.min.md" }, "markdown": "Typefully scores 49.3 (D) on agent readiness against Repostit's 32.5 (F), and leads in 5 of 7 scored categories. Repostit leads on security \u0026 auth. Both do social posting.\n\n- Repostit: grade F, 32.5/100, rank #1191 of 1272. Markdown https://www.anchorterminal.com/tools/repostit.md · JSON https://www.anchorterminal.com/api/v1/tools/repostit.json\n- Typefully: grade D, 49.3/100, rank #992 of 1272. Markdown https://www.anchorterminal.com/tools/typefully.md · JSON https://www.anchorterminal.com/api/v1/tools/typefully.json\n- Best social media posting and scheduling APIs for AI agents: https://www.anchorterminal.com/best/social-media/index.md\n- All 132 social comparisons: https://www.anchorterminal.com/compare/social-media/index.md\n\n## Which one, for what\n\n### Repostit (F)\n\nGood for: Creators, small businesses and agencies who post short vertical video on one network and want an assistant in Claude or ChatGPT to copy it to others on a schedule, set up reposting workflows and confirm what went out, without writing code.\n\nAhead on:\n- Security \u0026 auth, 44 against 38\n\nAlso in its favour:\n- Free to start without a card\n- No incidents deducted, where Typefully loses 3 points for them\n\nWatch for: No tool names, input schemas, annotations, scopes or error shapes are published, and no public REST API, SDK or OpenAPI file exists\n\n### Typefully (D)\n\nGood 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.\n\nAhead on:\n- Schema \u0026 documentation, 83 against 27\n- Agent ergonomics, 62 against 25\n- Maintenance \u0026 community, 82 against 56\n- Transparency \u0026 trust, 66 against 29\n\nWatch for: Rate limits are described by response headers only. No request numbers are published, and no `Retry-After` header is documented\n\n\n## Why the edge\n\n### Schema \u0026 documentation: Typefully +56\n\n- Repostit (27): MCP reading, since the connector is the only surface an outside agent reaches; no public REST API, developer page, OpenAPI file, SDK or package was found in the help centre, /whats-new/, the sitemap, llms.txt, GitHub, npm or the MCP registry. No tool names or input schemas are published anywhere, and no session was opened to read them (0 of 25). llms.txt exists, but it is a Rank Math index of site URLs that includes theme placeholder entries, and help articles are HTML only (5 of 10). The Claude connector page says what each step is for and when not to use it, list accounts before choosing a destination, a Brief saves a draft and neither publishes nor schedules, publishing applies to every destination in a Brief, Queued is not delivery, future-content workflows publish once active while existing-content ones import for review (8 of 20). Inputs are described in prose only, formats per destination, JPEG, PNG or WebP up to 20 MB, carousel caps of 4, 10 and 20 by network, media at a downloadable HTTPS URL and a timezone with every scheduled time (4 of 15). Plain-language example requests and per-network failure reasons written for people; no example tool call, response or error shape (5 of 15). The endpoint path carries v1.1 and the registry holds 2026.10.17 and 2026.10.23; /whats-new/ is undated and no changelog was found (5 of 15). 0+5+8+4+5+5 = 27.\n- Typefully (83): Public OpenAPI 3.1.0 document for 24 operations and seven webhook events (25). `llms.txt`, the full reference as Markdown and an RFC 9727 API catalogue (10). Descriptions state purpose, the permission each call needs and how drafts move between states, with less on when not to use a call (15). Inputs are typed per platform with 18 enums, length limits and required fields, though `publish_at` mixes keywords and datetimes in one string (12). 239 examples and error responses on every operation, with no list of error codes (11). The version is in the path and API changes are dated in the product changelog, with no API changelog of its own (10).\n\n### Agent ergonomics: Typefully +37\n\n- Repostit (25): MCP reading. The tool count is not published. The connector pages describe seven actions (list accounts, create, schedule and publish a Brief, check delivery, create a workflow, send a connection link), which suggests a small set, but the definitions were not read, so a middle reading rather than full marks (10 of 25). No pagination, filtering or output-size controls are documented (0 of 20). Delivery checks report a result per destination with public links when the network gives one, and the help centre lists failure reasons per network, but no error codes or connector error messages are documented (5 of 20). No idempotency key and no readOnlyHint or destructiveHint seen; Briefs start as drafts, queued Briefs are locked against a second send, Manual workflows hold posts for approval and the guidance says to check before retrying (6 of 20). Requests are made in plain language with few stated requirements (an HTTPS media URL, a timezone); no SDK in any language (4 of 15). 10+0+5+6+4 = 25.\n- Typefully (62): List calls take `limit` up to 50 with a default of 10, and a draft read can drop comment markers, but there is no field selection (15). Limit and offset pagination with status, tag and ordering filters on drafts (20). Errors carry a code, a message and field details with a location path (16). No idempotency key. A planned draft is a write that cannot publish, which makes retries safer for that state only, and MCP tool annotations were not read (4). Creating a draft needs only `platforms`, but there is no official SDK, only the skill's CLI script (7).\n\n### Transparency \u0026 trust: Typefully +37\n\n- Repostit (29): Closed service. The terms of service (effective 7 March 2025, no revision since) name Repostit LLC of Newark, Delaware, with Delaware law and arbitration, take a non-exclusive licence to content only to run the service and say fees are non-refundable; every footer says Repostit, Inc., and the terms do not mention the connector (12 of 30). The privacy policy (29 July 2026) keeps data until the account is deleted or as needed, with no periods, deletes Pinterest credentials on disconnect but says nothing of other networks' tokens, names no DPA, and does not mention the connector or its 90-day offline access; the account deletion article gives no timeline and leaves network-side access to the user (10 of 30). No deprecation policy or dated notices; the terms promise notice of significant changes and the ChatGPT page names a pending version 1.1 without a date (3 of 20). Subprocessors are 'hosting providers, analytics services', unnamed, with transfers outside the user's country and no locations; the Tawk.to chat on the contact page and the Google Cloud Run host of the connector are not named in the policy (2 of 20). 12+10+3+2 = 27.\n- Typefully (66): Closed service under published terms, with the Agent Skill under MIT (15). The privacy policy says deleted data is purged within 30 days, that AI providers may not train on customer data and that data is processed in the United States, and it links a sub-processor list. No DPA was found, and the terms say only that data may be kept for a limited period (20). No deprecation policy. The v1 to v2 migration guide gives no end date for v1, `draft_id` is marked deprecated with no date, and the terms may change without notice (4). About 30 sub-processors listed by purpose on a page dated 3 March 2026, without locations for each (16).\n\n### Maintenance \u0026 community: Typefully +26\n\n- Repostit (56): Closed service. The latest registry version is 2026.10.23, published 23 October 2026, and the connector article was updated 22 October 2026 (30). Dated changes in the last 90 days are the two registry versions of 17 and 23 October 2026; /whats-new/ is undated and the ChatGPT app's 1.1.0 (per the 3 November listing check) carries no date, so fewer than three dated releases (10 of 20). Support is email and weekday chat, 9am to 5pm Eastern, with replies within 24 hours; no public changelog with dates, forum or issue tracker (6 of 15). In the official MCP registry as io.github.hax98/repostit, a GitHub-verified namespace of a personal account; the entry links Repostit's own pages and its address matches the vendor's connector page, but no first-hand page ties the account to the company, so partial credit (10 of 15). No packages, public code or CI to judge (0 of 10). 30+10+6+10+0 = 56.\n- Typefully (82): Product changelog entry on 20 September 2026 and an agent-skills commit on 1 October 2026 (30). Five dated changelog entries between 8 July and 20 September 2026 (20). Public changelog, a Discord community, email and in-app chat, with no public issue tracker for the API (10). Listed in the official MCP registry as `com.typefully/mcp`, active since 1 September 2026 (15). The skill repository runs a test workflow, and there is no SDK to judge (7).\n\n### Security \u0026 auth: Repostit +6\n\n- Repostit (44): OAuth with dynamic client registration and no client secret, per Repostit's Claude connector page, with offline access that renews for up to 90 days from the first authorisation; social-network sign-ins stay in Repostit and provider tokens are not passed to the assistant. PKCE S256 is stated only in third-party metadata. No scopes are named; the page lists the permissions shown at sign-in (read accounts, create workflows and Briefs, schedule or publish, read delivery status). Revocation is by disconnecting in the client or asking support (18 of 30). A Brief is saved as a draft, Manual workflows wait for approval, and the help article says the assistant shows each step for confirmation before publishing (on ChatGPT 'may ask', depending on the client); no read-only mode, and an activated future-content workflow publishes on its own (8 of 20). Tools return the user's own accounts, Briefs and delivery results and read no comments or messages (10). Assistant-created posts appear under Post with a Comments \u0026 Activity log of each step, and Post History shows each network's response; no per-call log for the connector (8 of 15). security.txt did not load through our reader, and no disclosure policy, bug bounty or certification appears on any page read (0 of 20). 18+8+10+8+0 = 44.\n- Typefully (38): OAuth on the MCP server with PKCE, dynamic client registration and revocation, and revocable API keys, but one scope `full_access` and keys that carry all of the creating user's permissions (20). The MCP article says the old URL form with the key in `?TYPEFULLY_API_KEY=` still works (-10). Read, write and publish access per social set is inherited from the user, and planned drafts need a confirming call, but no read-only key exists (10). Responses hold the workspace's own drafts and teammates' comments, with no injection guidance found (6). Draft Activity records who changed a draft and labels MCP or API as the source (10). No security.txt, bug bounty or certification was found, only a short security section in the privacy policy (2).\n\n## Score by category\n\n| Category | Weight | Repostit | Typefully | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 26 | 27 | Typefully +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 27 | 83 | Typefully +56 |\n| Agent ergonomics | 13% (16.2 this run) | 25 | 62 | Typefully +37 |\n| Security \u0026 auth | 14% (17.5 this run) | 44 | 38 | Repostit +6 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 30 | 30 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 56 | 82 | Typefully +26 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 29 | 66 | Typefully +37 |\n| Negative events | ≤15 | 0 | -3 | |\n| **Total** | | **32.5 · F** | **49.3 · D** | |\n\n## Facts side by side\n\n| Fact | Repostit | Typefully |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Repostit LLC | Typefully Inc. |\n| Hosted endpoint | `https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1` | `https://api.typefully.com` |\n| Transports | Streamable HTTP | HTTP, Streamable HTTP |\n| Auth | OAuth | OAuth or key |\n| Pricing | Paid | Freemium |\n| x402 | no | no |\n| Licence | Proprietary hosted service under Repostit's terms of service (effective 7 March 2025), which name Repostit LLC of Newark, Delaware. No source, SDK or package is published | Proprietary service under Typefully's Terms of Service. The Agent Skill and its CLI script in typefully/agent-skills are MIT |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| MCP registry | `io.github.hax98/repostit` | `com.typefully/mcp` |\n| Last release | 2026-10-23 | 2026-10-01 |\n| Terms last updated | not read yet | 2026-02-23 |\n| Privacy policy last updated | not read yet | no date given |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | yes |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | yes |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n\n## How the scores have moved\n\n### Repostit\n\nNo score change since it was listed.\n\n### Typefully\n\n- +0.2 on 27 October 2026: checklist\n\n## Verdicts\n\n**Repostit.** An OAuth connector lets an agent list accounts, draft and schedule posts, build reposting workflows and check delivery, with drafts saved before anything publishes and a 14-day trial without a card. Tool names, schemas, scopes and error shapes are unpublished, the endpoint sits on a Cloud Run host, and there is no status page, public API or named subprocessor.\n\n**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.\n\n## Before you call either\n\n### Repostit\n\n1. List connected accounts first and confirm names and platforms with the user before choosing destinations; a missing account must be connected in Repostit Connections, not through the agent.\n2. Pass media as a downloadable HTTPS URL, never a local filename, and give every scheduled time with an explicit timezone.\n3. Treat Queued as accepted, not published; check delivery status and public links before reporting success, and check the existing result before any retry to avoid duplicate posts.\n4. Creating a future-content workflow makes it publish on its own once active; prefer existing-content workflows or Manual mode when the user wants to review first.\n5. On the trial, each destination counts as one of 10 posts and Basic allows 10 video posts a month; ask before fanning one Brief out to many networks.\n\n### Typefully\n\n1. Call `GET /v2/social-sets` first. Every draft, media, tag and queue path needs a `social_set_id`\n2. Use `plan_at` or omit both dates to leave a draft unpublished. `publish_at: \"now\"` posts at once and is asynchronous\n3. Do not retry a failed publish blindly. Read the draft's `status` and `publish_state` first, because no idempotency key exists\n4. Read `X-RateLimit-User-Remaining` and `X-RateLimit-SocialSet-Remaining` on each response, and wait until the `Reset` timestamp after a 429\n5. Send the key only as `Authorization: Bearer`. The legacy MCP URL with `?TYPEFULLY_API_KEY=` still works and puts the key in logs\n\n## Tutorials\n\n- [Draft a two-post thread with Typefully](https://www.anchorterminal.com/tutorials/typefully/), for Typefully\n\n## Questions\n\n### Which is better for AI agents, Repostit or Typefully?\n\nTypefully scores 49.3 (D) on agent readiness against Repostit's 32.5 (F), and leads in 5 of 7 scored categories. Repostit leads on security \u0026 auth.\n\n### Can an agent call Repostit and Typefully without installing anything?\n\nYes. Repostit has a hosted endpoint at https://repostit-mcp-cfjcykgqda-uc.a.run.app/mcp/v1.1 and Typefully at https://api.typefully.com.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/repostit-vs-typefully.json, and with the fewest tokens: https://www.anchorterminal.com/compare/repostit-vs-typefully.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"repostit\", \"b\": \"typefully\"}`. From a terminal: `anchor compare repostit typefully`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/repostit.json and https://www.anchorterminal.com/api/v1/tools/typefully.json\n\n## Other comparisons with Repostit or Typefully\n\n- [Ayrshare API + MCP vs Repostit](https://www.anchorterminal.com/compare/ayrshare-vs-repostit.md)\n- [Ayrshare API + MCP vs Typefully](https://www.anchorterminal.com/compare/ayrshare-vs-typefully.md)\n- [Blotato vs Repostit](https://www.anchorterminal.com/compare/blotato-vs-repostit.md)\n- [Blotato vs Typefully](https://www.anchorterminal.com/compare/blotato-vs-typefully.md)\n- [Buffer API + MCP vs Repostit](https://www.anchorterminal.com/compare/buffer-vs-repostit.md)\n- [Buffer API + MCP vs Typefully](https://www.anchorterminal.com/compare/buffer-vs-typefully.md)\n- [bundle.social vs Repostit](https://www.anchorterminal.com/compare/bundle-social-vs-repostit.md)\n- [bundle.social vs Typefully](https://www.anchorterminal.com/compare/bundle-social-vs-typefully.md)\n- [Zernio (formerly Late) API + MCP vs Repostit](https://www.anchorterminal.com/compare/late-vs-repostit.md)\n- [Zernio (formerly Late) API + MCP vs Typefully](https://www.anchorterminal.com/compare/late-vs-typefully.md)\n- [Metricool API + MCP vs Repostit](https://www.anchorterminal.com/compare/metricool-vs-repostit.md)\n- [Metricool API + MCP vs Typefully](https://www.anchorterminal.com/compare/metricool-vs-typefully.md)\n- [Mixpost API + MCP vs Repostit](https://www.anchorterminal.com/compare/mixpost-vs-repostit.md)\n- [Mixpost API + MCP vs Typefully](https://www.anchorterminal.com/compare/mixpost-vs-typefully.md)\n- [OneUp API + MCP vs Repostit](https://www.anchorterminal.com/compare/oneup-vs-repostit.md)\n- [OneUp API + MCP vs Typefully](https://www.anchorterminal.com/compare/oneup-vs-typefully.md)\n- [Post Bridge API + MCP vs Repostit](https://www.anchorterminal.com/compare/post-bridge-vs-repostit.md)\n- [Post Bridge API + MCP vs Typefully](https://www.anchorterminal.com/compare/post-bridge-vs-typefully.md)\n- [Postiz API + MCP vs Repostit](https://www.anchorterminal.com/compare/postiz-vs-repostit.md)\n- [Postiz API + MCP vs Typefully](https://www.anchorterminal.com/compare/postiz-vs-typefully.md)\n- [Publer API + MCP vs Repostit](https://www.anchorterminal.com/compare/publer-vs-repostit.md)\n- [Publer API + MCP vs Typefully](https://www.anchorterminal.com/compare/publer-vs-typefully.md)\n- [Repostit vs Upload-Post API + MCP](https://www.anchorterminal.com/compare/repostit-vs-upload-post.md)\n- [Typefully vs Upload-Post API + MCP](https://www.anchorterminal.com/compare/typefully-vs-upload-post.md)\n- [Repostit vs SocialCannon](https://www.anchorterminal.com/compare/repostit-vs-socialcannon.md)\n- [SocialCannon vs Typefully](https://www.anchorterminal.com/compare/socialcannon-vs-typefully.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-03", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Repostit vs Typefully", "url": "" } ], "description": "Typefully scores 49.3 (D) to Repostit's 32.5 (F) for social posting. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Repostit F 32.5", "Typefully D 49.3", "scores" ], "h1": "Repostit vs Typefully", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/repostit-vs-typefully", "published": "2026-10-01", "section": "tools", "title": "Repostit vs Typefully for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-03", "url": "https://www.anchorterminal.com/compare/repostit-vs-typefully" }, "tokens": { "markdown": 4950, "slim": 3080 }, "version": 1 }