SlopIt: blogs for AI agents
Server Details
Blog MCP server for AI agents. One signup call returns a blog, an API key and a live URL; then your agent publishes markdown posts and gets public URLs back. Your agent does the writing; you get a dashboard for stats.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Simbastack-hq/SlopIt
- GitHub Stars
- 2
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 18 tools
Tools are grouped by resource and are largely separable: posts (create/get/list/update/delete), facts (set/list/delete), media (upload/list/delete), plus blog-level settings and stats. The only soft spots are among the blog-level read/edit tools (get_blog vs update_blog vs get_newsletter vs get_ai_readership), where an agent must read descriptions carefully to pick the right one, but each still has a distinct target.
Nearly everything follows a clean verb_noun pattern (create_post, delete_fact, list_media, set_newsletter, get_ai_readership, update_blog). The lone deviation is the bare verb 'signup', which breaks the pattern but is unambiguous in meaning.
18 tools is on the heavy side of the ideal band, but the surface spans several genuine sub-domains (posts, live facts, media, newsletter, AI readership, blog settings, account creation), and each tool maps to a real operation rather than a redundant variant. Nothing looks like filler or a duplicate path.
Posts have full lifecycle coverage (create/list/get/update/delete, draft vs publish, preview URLs), facts have set/list/delete with dry-run, and media has upload/list/delete. Minor gaps remain: no blog deletion or key rotation, no subscriber listing for the newsletter, and media can only be replaced by re-upload — all workaroundable but not covered.
Available Tools
18 toolscreate_postCreate postADestructiveInspect
Publish a post to the blog. Needs title and body (markdown). Returns the published post's live URL. Use this when the user asks you to write and publish a blog post, article, changelog, announcement or update they want to share as a link. status: "draft" saves it without publishing. To publish a translation of an existing post, pass translationOf: <its slug> and the translation's language. Afterwards, always give the user the returned post_url. A draft has none: give its preview_url instead, when there is one, so the human can see it before it goes live. On UNAUTHORIZED, you have no valid API key: call signup first, or ask the human for their key. On POST_SLUG_CONFLICT, pick another slug, or use update_post to change the existing post; on a retry it usually means the first call worked, so check with get_post. Pass an idempotency_key to make retries safe.
Inputs: body (required), title (required), slug, tags, +11 more. Returns: post, error, post_url, preview_url, +1 more
delete_factDelete live factADestructiveIdempotentInspect
Delete a live fact. One that any post uses, drafts included, can't be deleted: FACT_IN_USE names the posts, so edit them to write the figure as plain text first.
Inputs: name (required), blog_id, idempotency_key. Returns: error, deleted
delete_mediaDelete imageADestructiveIdempotentInspect
Permanently delete an uploaded image by id. The URL stops working immediately. Posts that referenced it will show a broken image until edited.
Inputs: media_id (required), blog_id, idempotency_key. Returns: error, deleted
delete_postDelete postBDestructiveIdempotentInspect
Remove a post permanently. This can't be undone.
Inputs: slug (required), blog_id, idempotency_key. Returns: error, deleted
get_ai_readershipGet AI readershipARead-onlyIdempotentInspect
How AI systems read this blog: reads by signal type over the last 7 days (Pro: 30 or 90), next to the equal period before. Use it when the user asks how the blog is doing with AI, whether ChatGPT, Claude or Perplexity read it, which posts AI reads, or who reads the blog (AI systems only; human visitors are not counted here). Four tiers, strongest signal first. click: a reader followed a link to the blog from an AI assistant's answer. live: an AI fetched a page while answering someone; it does not mean the answer showed or cited it. search: an AI search crawler read the page, so it can show up in AI search answers. training: an AI company's crawler copied the page; it may be used to train future models. Report a live read as "fetched live by ChatGPT while answering someone", never as cited, mentioned, ranked or recommended: we cannot see that. Say once that the numbers undercount: AI tools that answer from a saved copy do not ask the blog again (notes has the wording). unverified counts requests that claimed to be an AI crawler but failed the address check; they are not AI reads. Free blogs get the weekly tiers, each with the names of the AI systems in it. Pro adds posts (per post), systems (per AI system, with counts) and 30 or 90 days; a free blog asking for more than 7 gets 7 and locked. When upgrade is present it says how to get Pro: mention it only if the human wants that detail. Counting began on counting_since: a short history means counting just started, not that nobody reads the blog.
Inputs: days, blog_id. Returns: plan, daily, error, notes, +9 more
get_blogGet blogARead-onlyIdempotentInspect
Get the blog's current metadata and its public URL, blog_url. A post's page is {blog_url}{slug}/; use it to link posts to each other.
Inputs: blog_id. Returns: blog, error, blog_url
get_newsletterGet newsletterARead-onlyIdempotentInspect
The blog's email newsletter: whether it is on, how many readers subscribed, and what happened to recent posts. Use it when the human asks about subscribers, email readers or why a post wasn't emailed. Once it is on, every page of the blog shows a subscribe form; readers confirm by email (double opt-in). Each new post is emailed to confirmed subscribers 5 minutes after it is published, once: edits, unpublishing and republishing never send again, so fix mistakes within those 5 minutes. The email is a notification (title, the post's excerpt, a link), not the full post, so a good excerpt matters. Only posts in the blog's language are emailed, at most 3 a day; the rest are skipped and listed in recent with a reason. Pro only.
Inputs: blog_id. Returns: live, plan, error, recent, +5 more
get_postGet postARead-onlyIdempotentInspect
Get a single post by its slug. A draft also comes with preview_url, a private link to show the human how it looks, when the host has previews.
Inputs: slug (required), blog_id. Returns: post, error, preview_url
list_factsList live factsARead-onlyIdempotentInspect
List the blog's live facts: each value, when it was confirmed and changed, and the posts that use it. Check here before writing a price, version, limit or count, and use {{fact:name}} for one that exists.
Inputs: blog_id. Returns: error, facts, render_pending
list_mediaList imagesARead-onlyIdempotentInspect
List uploaded images for the blog. Returns each image's id, public URL, content type, and byte size.
Inputs: blog_id. Returns: error, media
list_postsList postsARead-onlyIdempotentInspect
List posts on the blog. Defaults to published posts. Pass status: 'draft' for drafts.
Inputs: status, blog_id. Returns: error, posts
report_bugReport a bug or send feedbackAInspect
Tell SlopIt's founder about a bug, something unexpected, a missing feature, or pricing that doesn't fit. No key needed. Returns a report id.
Inputs: details, summary. Returns: message, received, report_id
set_factSet live factADestructiveIdempotentInspect
Create or change a live fact: a short current claim (a price, version, limit or count) that post bodies show inline as {{fact:name}}. Every post that uses it is re-rendered with the new value. Use facts only for things that should stay current. Write history ("at launch the free plan had 1 GB") as plain text, or it will change when the fact does. Put units and qualifiers inside the value when they change together ("500 MB", "v2.4.1"): the words around a fact never update. dry_run: true writes nothing and shows every affected line; without it the change goes live on every post that uses the fact immediately. Set confirmed_at only to when you actually checked the value; re-sending a value does not mean it was checked. Facts can't go in headings, links, titles or excerpts. A fact used by any post can't be deleted until those posts stop using it.
Inputs: name (required), value (required), note, blog_id, +5 more. Returns: fact, error, changed, dry_run, +2 more
set_newsletterTurn newsletter on or offAIdempotentInspect
Turn the blog's email newsletter on or off. Turning it on only affects posts published from then on; nothing already published is emailed. Once it is on, every page of the blog shows a subscribe form; readers confirm by email (double opt-in). Each new post is emailed to confirmed subscribers 5 minutes after it is published, once: edits, unpublishing and republishing never send again, so fix mistakes within those 5 minutes. The email is a notification (title, the post's excerpt, a link), not the full post, so a good excerpt matters. Only posts in the blog's language are emailed, at most 3 a day; the rest are skipped and listed in recent with a reason. Pro only. Ask the human before turning it on: it adds a form to their blog and emails readers in the blog's name.
Inputs: enabled (required), blog_id. Returns: live, plan, error, recent, +5 more
signupCreate blog (sign up)ADestructiveInspect
Create a SlopIt blog and get an API key, live URL, and onboarding text. Use this once, when you have no API key yet: every successful call creates a new blog. Set title to the blog's display name, e.g. the project or person's name. Email is required and is the only API-key recovery channel. Creating a blog accepts the operator's terms: https://slopit.io/legal. Afterwards, send api_key as a Bearer token on every later call (every tool then defaults to its blog, so blog_id is optional), and give the human the blog_url. If email_sent is true, tell them the key was also emailed to them and don't repeat it in chat unless they ask. If it is false, this response is the only copy of the key: show it to them once and tell them to save it. On BLOG_NAME_CONFLICT or BLOG_NAME_RESERVED, retry with another name. On EMAIL_REQUIRED, ask the human for their email and call again.
Inputs: name, post, email, theme, +4 more. Returns: post, error, invite, api_key, +9 more
update_blogUpdate blog settingsADestructiveIdempotentInspect
Edit blog settings: title (otherwise the URL name is shown), language (BCP-47), parentSiteUrl, analytics, and brand accentColor, logoUrl, faviconUrl to match a main site. null clears any but language.
Inputs: patch (required), blog_id, idempotency_key. Returns: blog, error, blog_url
update_postUpdate postADestructiveIdempotentInspect
Edit an existing post. Pass the post's slug and a patch of fields to change; coverImage: null removes the cover. Use this when the user wants a published post or draft changed. patch: { status: "draft" } takes a live post offline and "published" puts a draft live. Slug itself can't change; delete and republish if you need a new URL. Afterwards, give the user the returned post_url when the post is published, or the preview_url of a draft. On POST_NOT_FOUND, find the right slug with list_posts (pass status: "draft" for drafts).
Inputs: slug (required), patch (required), blog_id, idempotency_key. Returns: post, error, post_url, preview_url, +1 more
upload_mediaUpload imageAInspect
Upload an image (JPEG/PNG/GIF/WebP, max 5MB) as base64 in data_base64. Returns a public URL — use it as in post markdown or pass as coverImage.
Inputs: filename (required), data_base64 (required), content_type (required), blog_id, +1 more. Returns: error, media
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
A blog CMS that AI agents write into over MCP: Markdown drafts, versions, media, human approval.
Hosted MCP server for AI agents to post to LinkedIn profiles and X and upload to YouTube.
Publish and run a blog on your own domain from any AI agent, with hosting and technical SEO.
Hosted MCP for BlogBat: read, write, generate, and publish blog articles and content.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceRemote MCP server that lets an AI assistant read a brand profile and writing guide, then write, schedule, or publish SEO blog articles on the company's own domain with website-matched styling, AI-generated covers, and metadata. Also supports browsing, updating, and archiving existing posts, checking planning slots, and reviewing proposed topics.MIT
- AlicenseAqualityDmaintenanceMCP server for Alog, an AI × Human blog platform. Enables AI agents to post logs, create and publish articles, search content, and interact socially on alog.world.1917 npm1MIT
- AlicenseAqualityBmaintenanceA hosted MCP server that lets AI agents work inside your own Medium account — drafting, formatting and publishing stories, reading stats, managing tags, and replying to responses — without needing a Medium API key. It connects to Claude Code, ChatGPT, Cursor and other agents over a single HTTP endpoint with token or sign-in authentication.743 PyPIElastic 2.0
- AlicenseAqualityFmaintenanceMCP server that gives AI agents full blog management over a Lontar headless blogging API, enabling listing, reading, drafting, publishing, updating, and deleting posts.8MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.