"An article or written content" matching MCP tools:

• word_create

  local-mcp

  Creates a new Word (.docx) document at `path` with the given text content (and an optional title rendered as the heading). Requires confirm=true — called without it, returns a preview of what will be written instead of creating the file. The path must be somewhere Local MCP can write; Desktop/Documents/Downloads may need a one-time Files-and-Folders grant (System Settings → Privacy & Security → Files and Folders). Returns {created, path}. For a OneDrive or Google Drive path use onedrive_write_file / gdrive_write_file; to append to an existing doc use word_append, to read one word_read.

  Connector

• detect_ai_text

  Stipple — Document Verification & Extraction

  Estimate the PROBABILITY that a document's text was AI-GENERATED (LLM-written prose). USE THIS WHEN someone shares prose — an essay, cover letter, article, review, application, or report (or a link to one) — and asks: did an AI / ChatGPT write this? is this human-written? detect AI text. Provide the document ONE way: `text` (pasted markdown/plain prose), `url` (a public http(s) link to a page or PDF — fetched server-side, the cheapest call), OR `bytes_b64` (a base64 PDF/file, plus `filename` for routing). Returns `{probability, lean, tells, reasoning, applicable}`. HONEST SCOPE: the probability is the model's CONFIDENCE, not a calibrated truth — it can false-flag templated/coached or non-native-English writing. It works on PROSE only: for a form/table/numeric document (payslip, statement) it returns `applicable: false` and abstains, because AI-text detection false-positives badly there — use `verify_document` (the authenticity engine) for those, and `verify_references` to check a doc's citations/claims. Costs 1 credit(s) per call.

  Connector

• detect_ai_text

  Stipple — AI Text Detection

  Estimate the PROBABILITY that a document's text was AI-GENERATED (LLM-written prose). USE THIS WHEN someone shares prose — an essay, cover letter, article, review, application, or report (or a link to one) — and asks: did an AI / ChatGPT write this? is this human-written? detect AI text. Provide the document ONE way: `text` (pasted markdown/plain prose), `url` (a public http(s) link to a page or PDF — fetched server-side, the cheapest call), OR `bytes_b64` (a base64 PDF/file, plus `filename` for routing). Returns `{probability, lean, tells, reasoning, applicable}`. HONEST SCOPE: the probability is the model's CONFIDENCE, not a calibrated truth — it can false-flag templated/coached or non-native-English writing. It works on PROSE only: for a form/table/numeric document (payslip, statement) it returns `applicable: false` and abstains, because AI-text detection false-positives badly there — use `verify_document` (the authenticity engine) for those, and `verify_references` to check a doc's citations/claims.

  Connector

• register_derived_asset

  VarynForge

  Register a derived asset (LinkedIn carousel PDF, social post, video, image) produced from an article suggestion. Appends a distribution-ledger row so the suggestion shows everything it produced — the article plus its derivatives — for content-ROI reporting (get_article_suggestion returns them as derivedAssets). Pass `channel` (reels | youtube | x | linkedin) so the app can show per-channel distribution status; register again with a new URL for repeat posts on the same channel — every registration is kept. `scheduledFor` records a future post date from an external scheduler (Buffer etc.) for display only — VarynForge never posts on your behalf. Derivative rows never affect publish status or Search Console attribution; use mark_article_published for the article itself.

  Connector

• update_article

  Misar.Blog MCP Server

  Change the title, body, or tags of an article or draft that already exists. Only the fields you pass are touched; omitted fields keep their current values. Passing `tags` REPLACES the whole tag list rather than adding to it, so send the full set you want. Editing a published article changes what readers see immediately; it does not unpublish or re-date it. Safe to repeat: the same call twice leaves the same result. Requires an API key, and the account must own the article. Errors if no updatable field is supplied. Returns the updated article.

  Connector

• publish_article

  Misar.Blog MCP Server

  Create a new article and make it live immediately, or schedule it for a future time. This PUBLISHES: without schedule_at the article is world-readable the moment this returns, at the visibility you choose. If the piece is not ready, use create_draft instead and publish later. Each call creates a NEW article — it is not idempotent, so calling twice publishes twice; use update_article to change one that exists. Requires an API key and consumes one publish from the account's plan quota; the response warns when the allowance is nearly spent. Returns the created article with its public url and editor_url.

  Connector

• search_kb

  WindowsForum MCP Server

  Search official Microsoft Knowledge Base articles on support.microsoft.com by topic or keyword — use for Windows update, patch, and known-issue lookups when you lack a KB number. Returns matching KB article titles and URLs. Use get_kb_article to fetch the full content of a specific article. Returns: Dictionary with 'results' key containing list of matching KB articles with title and url.

  Connector

• draft_news

  mcp

  Draft and publish a news article. Open to anyone with a Datronis account — the personal access token is for rate-limiting and audit, not permission-gating. Always drafted in English first; an automated safety classifier must return "green" (not political, not likely to be seen as controversial or divisive) before the article goes live. A "flagged" result creates the article unpublished and returns the reasons — use resubmit_news with revised content to try again; there is no way to force-publish a flagged article. Publishes English-only unless target_locales is given.

  Connector

• sftp_write

  termalin-web

  Create or overwrite a text file on one of your servers over SFTP. 'content' is written as UTF-8. Capped at 512 KB; for binary uploads use a terminal/scp instead.

  Connector

• web_url_reader

  Inferventis MCP Server

  Fetches any public web page and returns clean, readable plain text stripped of HTML, navigation, scripts, advertisements, and boilerplate. Returns the page title, meta description, word count, and main body text ready for analysis or summarisation. Use this tool when an agent needs to read the content of a specific web page or article URL — for example to summarise an article, extract facts from a page, verify a claim by reading the source, or convert a web page into plain text to pass to another tool. Pass article URLs returned by web_news_headlines to this tool to read full article content. Do not use this tool to discover current news headlines — use web_news_headlines instead. Does not execute JavaScript — best suited for standard HTML content pages. Will not work with paywalled, login-protected, or JavaScript-rendered single-page applications.

  Connector

• get_article

  Nalegalu MCP

  Fetch the exact text of one article (or paragraph) of a Polish legal act. Use after search_law or another trusted source supplied the address and article key; never guess them. Deterministic lookup by act address (e.g. WDU19740240141) and article key (e.g. "133" or "Art. 133."). Optional paragraph_key (e.g. "1" or "§ 1.") narrows the result to a single paragraph.

  Connector

• update_article_media

  Clueso

  Update an article image/GIF (screenshot), or inspect its current state. - Provide one or more of `zoom_factor`, `crop`, `shapes` to change metadata. - Pass `render=true` (with no other updates) to fetch the current details without mutating. To DELETE an article image/GIF: call `update_article` with markdown that omits the `<SCREENSHOT id>` reference. Unreferenced media is pruned server-side on save. There is no separate delete tool — the markdown IS the source of truth for what's present.

  Connector

• update_article

  Misar.Blog MCP Server

  Change the title, body, or tags of an article or draft that already exists. Only the fields you pass are touched; omitted fields keep their current values. Passing `tags` REPLACES the whole tag list rather than adding to it, so send the full set you want. Editing a published article changes what readers see immediately; it does not unpublish or re-date it. Safe to repeat: the same call twice leaves the same result. Requires an API key, and the account must own the article. Errors if no updatable field is supplied. Returns the updated article.

  Connector

• generate_title_seo

  Misar.Blog MCP Server

  Generate 5 search-optimised article titles from a TOPIC OR KEYWORD, each with a keyword-strategy hint. Aims at high-volume, low-competition long-tail phrases and at AI answer engines (ChatGPT, Perplexity, Claude) as well as Google. Pick between the two title tools by what you have in hand: use this one when you have a topic or keywords and the article may not be written yet. Use suggest_titles when the draft already exists and you want titles drawn from its actual text. Passing `context` here does not make them equivalent — this one still optimises for the keywords you supply. Nothing is saved and no article is created or retitled; use update_article to apply a title. Requires an API key and consumes AI credits per call. Generative, so repeated calls return different titles.

  Connector

• rendex_extract

  Rendex: Rendering API for Images, PDFs & Content Extraction

  Use this when the user asks to read, extract, get the text/content/article of, or summarize a webpage/URL. Do NOT use for a visual screenshot (use rendex_screenshot). Extracts clean reader-mode content from any webpage as Markdown, JSON, or HTML. Runs the same Chromium render pass as a screenshot, so it captures content after JavaScript runs — handles SPAs that fetch-only readers miss. Strips nav, ads, and boilerplate, returning the article body plus title, byline, and excerpt. Great for feeding page content to an LLM, summarization, or RAG ingestion. Costs 1 render credit per call.

  Connector

• list_my_articles

  Misar.Blog MCP Server

  List articles owned by the authenticated account, newest first, including drafts and scheduled posts. Use this to find your own work — it is the only listing that sees unpublished content. To search across the whole site, including other creators, use search_articles instead. Reads only; nothing is created or modified. Requires an API key. Returns `{ articles, total }`, where each article carries id, slug, title, status, url, editor_url, tags and timestamps, but NOT the article body — call get_article for that. `total` counts all matches, not just the page returned.

  Connector

• get_article

  Misar.Blog MCP Server

  Fetch a single article by slug, including its full Markdown body. Use this after list_my_articles or search_articles has given you a slug and you need the actual content — for reading, editing, or repurposing it. Fetching one article at a time is deliberate: the listing tools omit bodies so they stay cheap. Reads only; nothing is created or modified. Requires an API key for unpublished articles; published ones are readable without. Returns the article object with content_markdown populated. Errors if the slug does not exist or the account cannot see it.

  Connector

• add_to_series

  Misar.Blog MCP Server

  Place an existing article into an existing series, optionally at a specific position. Both the series and the article must already exist — this creates neither. Identify them by SLUG, not id: get_series supplies the series slug and the article tools supply the article slug. Omit position to append at the end. Requires an API key. Adding an article does not change its publication status or URL; it only changes where it appears. Inserting at a position shifts the articles after it down. Errors if either slug is unknown.

  Connector

• research_topic

  Misar.Blog MCP Server

  Research a topic with AI and return insights, sources, and a suggested content outline. Use it at the START of a piece, before drafting — it produces raw material to write from, not a finished article and not a title. For titles use generate_title_seo; to see what already exists on Misar.Blog use search_articles. Nothing is saved: no draft, article, or file is created, and calling it has no effect on the blog. Requires an API key and consumes AI credits from the account's plan, so each call costs whether or not you use the output. Runs noticeably longer than a plain read, and being generative, two identical calls give different text. Returns prose to read, not structured JSON — verify any factual claims it makes.

  Connector

• generate_title_seo

  Misar.Blog MCP Server

  Generate 5 search-optimised article titles from a TOPIC OR KEYWORD, each with a keyword-strategy hint. Aims at high-volume, low-competition long-tail phrases and at AI answer engines (ChatGPT, Perplexity, Claude) as well as Google. Pick between the two title tools by what you have in hand: use this one when you have a topic or keywords and the article may not be written yet. Use suggest_titles when the draft already exists and you want titles drawn from its actual text. Passing `context` here does not make them equivalent — this one still optimises for the keywords you supply. Nothing is saved and no article is created or retitled; use update_article to apply a title. Requires an API key and consumes AI credits per call. Generative, so repeated calls return different titles.

  Connector