# Misar.Blog MCP Server (npm · @misarblog/mcp) Publish and manage articles, series, comments, reactions, newsletters and blog analytics. - Trust score: 84/100 (high trust) - Change this week: 0 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-21 ## Components - remote · `api.misar.io`: 52/100, [markdown](https://verifymcp.io/servers/misar-ai-misarblog-mcp/blog-mcp.md), [page](https://verifymcp.io/servers/misar-ai-misarblog-mcp/blog-mcp) - npm · `@misarblog/mcp`: 84/100 (this document), [markdown](https://verifymcp.io/servers/misar-ai-misarblog-mcp/misarblog-mcp.md), [page](https://verifymcp.io/servers/misar-ai-misarblog-mcp/misarblog-mcp) ## Channel facts - Registry: `npm` - Package: `@misarblog/mcp` - Version: `5.1.2` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-09-21. - **Supply Chain Security**: 98/100 - No malware found by supply-chain analysis. - No known CVEs affecting this package version or its production dependencies. - No install/post-install scripts declared. - 31 of 96 dependencies flagged as unhealthy. - **Provenance & Transparency**: 45/100 - Source repository is publicly reachable at the declared URL. - Provenance check failed: no build-provenance attestation is published. - Clear OSI-approved license (MIT). - Actively maintained (last published 32 days ago). - Disclosure check failed: no security disclosure policy was found in the source repository. - **Schema Quality & AI Usability**: 85/100 - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name). - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 4833 tokens (~155/item across 31 items; 26 tools + 5 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 87/100 - Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. - An AI judge read all 27 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the Misar.Blog MCP Server server? Misar.Blog MCP Server runs locally as an npm package, launched with npx -y @misarblog/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add misar-ai-misarblog-mcp -- npx -y @misarblog/mcp ``` ### Cursor ```json { "mcpServers": { "misar-ai-misarblog-mcp": { "command": "npx", "args": [ "-y", "@misarblog/mcp" ] } } } ``` ### VS Code ```json { "servers": { "misar-ai-misarblog-mcp": { "command": "npx", "args": [ "-y", "@misarblog/mcp" ] } } } ``` ### Codex ```bash codex mcp add misar-ai-misarblog-mcp -- npx -y @misarblog/mcp ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "misar-ai-misarblog-mcp": { "type": "local", "command": [ "npx", "-y", "@misarblog/mcp" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add misar-ai-misarblog-mcp --command npx --arg -y --arg @misarblog/mcp ``` ### Hermes ```yaml mcp_servers: misar-ai-misarblog-mcp: command: "npx" args: ["-y", "@misarblog/mcp"] ``` ### Netclaw ```json { "McpServers": { "misar-ai-misarblog-mcp": { "Transport": "stdio", "Command": "npx", "Arguments": [ "-y", "@misarblog/mcp" ] } } } ``` ### Vellum ```bash assistant mcp add misar-ai-misarblog-mcp -t stdio -c npx -a -y @misarblog/mcp ``` ### Other ```json { "mcpServers": { "misar-ai-misarblog-mcp": { "command": "npx", "args": [ "-y", "@misarblog/mcp" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-09-21 (score 84, +1) No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-19 (score 83, −3) - [functional] Stability: pass → 0.80 ### 2026-09-17 (score 86, +1) - [security] Stability: 0.97 → pass ### 2026-09-15 (score 85, +1) No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-13 (score 84, +1) No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-11 (score 83, +1) No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-08 (score 82, +1) No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-06 (score 81, +1) No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes. ## MCP tools (26) ### `login` (~273 tokens) Log in via browser Connect a Misar.Blog account by browser consent, with no API key to copy and paste. Use it when `status` reports no key, or when a tool fails as unauthenticated. It opens the authorisation page in the user's browser, waits for them to review the permissions and click Authorize, then stores the returned key in `~/.misarblog/config.json`. Two things to know before calling it. It BLOCKS until a human acts in the browser, so it can hang for as long as they take — never call it speculatively or in a retry loop. And `force=true` ROTATES the key, invalidating the existing one everywhere else it is used; without force, an already-valid session returns immediately and changes nothing. It listens on a short-lived local port to receive the callback. Input parameters: - `base_url` (string): Base URL of a self-hosted Misar.Blog. Omit for the hosted service. - `force` (boolean): Re-authenticate even when already logged in. This ROTATES the API key and breaks any other client using the old one — only on explicit request. - `port` (integer): Local port for the one-shot callback listener, 9001-9099. Random by default; set it only when a firewall requires a fixed port. ### `status` (~158 tokens) Check authentication status Report whether this client holds a working Misar.Blog API key, and which account it belongs to. Run it first when anything is failing with an auth error, and before a run of write operations, so you find out up front rather than midway. It distinguishes three states: no key stored, a key that is stored but rejected, and a valid key with its username. If it reports no key, run `login`. Reads only; it never creates or rotates a key — `login` does that. Takes no parameters. Unlike most tools here it does not fail when unauthenticated: 'not authenticated' is a normal successful answer, not an error. For plan and quota, use `upgrade`; for the full profile, get_profile. ### `upgrade` (~266 tokens) Show plan and quota, or upgrade Show the account's current plan, how much of each quota remains, and what a higher plan unlocks. Called with no arguments it only reads — useful any time, not just after hitting a limit, and the natural follow-up when a write tool reports a quota error. Two arguments make it act rather than report, so pass them only on explicit instruction from the user: `start_trial` ENROLS the account in the free trial immediately (a real account change, not a preview), and `open` LAUNCHES a checkout page in the user's browser. Neither charges a card by itself. Requires an API key. No billing state changes unless you pass start_trial; the returned quota snapshot already reflects a trial started in the same call. For whether you are authenticated at all, use `status`. Input parameters: - `open` (boolean): Open the checkout page in the user's default browser. Side effect on their desktop — only when they asked to upgrade. - `plan` (string): Plan slug to open, e.g. 'pro' or 'business'. Defaults to the recommended plan. Only meaningful with open=true. - `start_trial` (boolean): Enrol in the free no-card trial now, if eligible. This changes the account's plan — do not set it speculatively. ### `get_profile` (~132 tokens) Get my profile Fetch the authenticated account's own creator profile: id, username, display name, bio, public profile URL, and whether Stripe payouts are connected. Use it to confirm which account a key belongs to before acting on that account's behalf, to get your own profile id for tools that take a UUID, or to check stripe_connected before discussing paid posts. It only ever describes the caller — there is no tool here for looking up someone else's profile. Reads only; nothing is modified. Requires an API key, and takes no parameters. Errors if the key is missing or invalid, which is the quickest way to test authentication. ### `get_analytics_summary` (~174 tokens) Get analytics summary Summarise the account's performance over a trailing window: page views, gross and net revenue, and active subscriber count. Use it for 'how did I do this month' style questions. These are whole-account totals — it cannot break results down per article, and it covers a trailing window ending today rather than an arbitrary date range. Reads only. Requires an API key. Revenue is returned in cents (revenue_cents gross, revenue_net_cents after fees) with a formatted revenue_usd added for convenience — read the cents fields when doing arithmetic. Zero views is a real answer, not an error. Input parameters: - `days` (integer): Size of the trailing window in days, ending today. 1-365, defaults to 30. Use 7 for a week, 365 for a year. ### `list_my_articles` (~171 tokens) List my articles 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. Input parameters: - `limit` (integer): Maximum articles to return, 1-100. Defaults to 20. - `status` (string): Return only articles in this state. Omit to return every state the account owns. ### `get_article` (~153 tokens) Get one article 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. Input parameters: - `slug` (string, required): URL slug of the article, e.g. 'how-we-cut-build-times'. Not the numeric id, and not the full URL. ### `publish_article` (~293 tokens) Publish an article 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. Input parameters: - `body_markdown` (string, required): Complete article body as Markdown. Images may be referenced by URL. - `cover_image_url` (string): Absolute URL of the hero image. generate_cover_image returns a URL suitable here. - `schedule_at` (string): ISO 8601 timestamp to publish at, e.g. '2026-09-01T09:00:00Z'. Omit to publish immediately. A past timestamp publishes immediately. - `tags` (array): Up to 10 topic tags used for discovery and filtering. - `title` (string, required): Headline, 1-250 characters. - `visibility` (string): Audience: 'public' anyone, 'subscribers' newsletter subscribers, 'paid' paying members, 'private' only you. Defaults to 'public'. ### `create_draft` (~135 tokens) Create a draft Save an article as an unpublished draft. Nothing becomes visible to readers: use this whenever the work still needs review, and publish_article only when it should go live. The draft can be edited afterwards with update_article. Each call creates a NEW draft — not idempotent, so calling twice leaves two drafts. Requires an API key. Returns the draft with an editor_url for finishing it in the browser. Input parameters: - `body_markdown` (string, required): Article body so far, as Markdown. - `tags` (array): Topic tags to carry through to publication. - `title` (string, required): Working headline. Can be changed before publishing. ### `update_article` (~203 tokens) Update an article 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. Input parameters: - `body_markdown` (string): Replacement body as Markdown. Replaces the whole body, not a patch. - `id` (string, required): Article or draft id from a listing tool. This is the id, not the slug. - `tags` (array): Replacement tag list, up to 10. Overwrites the existing tags entirely. - `title` (string): Replacement headline. ### `search_articles` (~194 tokens) Search published articles Search PUBLISHED articles across all of Misar.Blog, including other creators' work. Use this for discovery, research, and competitive reading. It never returns drafts, scheduled, or private posts — not even your own — so reach for list_my_articles when you want your unpublished work. Reads only. No API key required; unauthenticated callers are rate-limited by IP. Filters combine with AND. Returns an array of article summaries without bodies; pass a slug to get_article for the full text. An empty array means no matches, which is not an error. Input parameters: - `author` (string): Restrict to one author, by username. - `limit` (integer): Maximum results to return, 1-20. Defaults to 10. - `q` (string): Free-text query matched against title and body. Minimum 2 characters. - `tag` (string): Restrict to articles carrying this exact tag. ### `research_topic` (~201 tokens) Research a topic 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. Input parameters: - `query` (string, required): The topic or question to research, 5-500 characters. Specific beats broad: 'how small SaaS teams price annual plans' returns more than 'pricing'. ### `generate_title_seo` (~267 tokens) Generate SEO titles from keywords 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. Input parameters: - `context` (string): Optional draft text (plain or Markdown, up to 8000 chars) so the titles match what the article actually says. Titles still follow `prompt` for keywords. - `prompt` (string, required): Topic or target keywords, 3-500 characters. Include niche, audience and any long-tail phrase you want to rank for, e.g. 'best AI writing tools for beginner bloggers 2025'. ### `suggest_titles` (~176 tokens) Suggest titles from draft text Generate 5 title options FROM AN EXISTING DRAFT, derived from what the article actually says. Pick between the two title tools by what you have in hand: use this one when the text exists and should drive the headline. Use generate_title_seo when you are starting from a topic or keyword, or want titles aimed at specific search terms — this tool takes no keyword input at all. Nothing is saved and the article is not retitled; apply a choice with update_article. Requires an API key and consumes AI credits per call. Generative, so repeated calls return different titles. Needs at least 20 characters of text to work from. Input parameters: - `context` (string, required): The article text to draw titles from, plain or Markdown, 20-8000 characters. More of the real draft yields better-fitting titles than a summary. ### `upload_image` (~187 tokens) Upload a local image Upload an image file from the local filesystem to the Misar.Blog CDN and return its public URL. Use it for images the user already has on disk; use generate_cover_image when the image does not exist yet. Available only when the server runs locally over stdio — the hosted endpoint cannot see your disk, so it does not offer this tool at all. Reads the file and creates a NEW CDN object each call; uploading twice yields two URLs. Nothing on the filesystem is modified or deleted. Requires an API key. The resulting URL is public and undeletable through this server, so do not upload anything private. Accepts JPEG, PNG, WebP and GIF. Input parameters: - `file_path` (string, required): Absolute path to the image on this machine, e.g. '/Users/me/cover.png'. JPEG, PNG, WebP or GIF; the type is inferred from the extension. ### `generate_cover_image` (~211 tokens) Generate a cover image Generate an image from a text prompt with AI, upload it to the Misar.Blog CDN, and return its public URL for use as cover_image_url when publishing. Use it when no artwork exists yet; use upload_image for a file the user already has. Each call generates a NEW image and costs generation credits against the account's plan — it is not idempotent, so re-running to 'try again' bills again. Generation takes noticeably longer than other tools. Requires an API key. The resulting URL is public and cannot be deleted through this server. Results vary between runs for the same prompt. Input parameters: - `prompt` (string, required): What the image should show, in plain language, up to 1000 characters. Describe subject and style; avoid asking for text in the image. - `size` (string): Output dimensions: '1792x1024' landscape (the default, best for article covers), '1024x1024' square, '1024x1792' portrait. ### `get_series` (~133 tokens) List my series List every series the authenticated account owns. Despite the name this returns the whole collection, not one series — there is no single-series lookup. Use it to find a series slug before calling add_to_series, or to check whether a series already exists before create_series makes a duplicate. Reads only; nothing is created or modified. Requires an API key, and takes no parameters — it is unfiltered and unpaginated. Returns `{ series, total }` where each entry carries id, slug, title, description, url and article_count. An empty list means the account has no series yet, which is not an error. ### `create_series` (~146 tokens) Create a series Create a new, empty series — a named collection that related articles can be added to. Creating the series does not move any article into it; follow up with add_to_series for each one. Call get_series first to avoid making a second series with the same title, since each call creates a NEW series and nothing deduplicates them. Requires an API key. The series and its URL become publicly reachable, though it shows nothing until articles are added. Returns the series with the slug that add_to_series needs. Input parameters: - `description` (string): Short summary shown on the series page. Optional. - `title` (string, required): Display name of the series. The slug is derived from this. ### `add_to_series` (~193 tokens) Add an article to a series 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. Input parameters: - `article_slug` (string, required): Slug of the article to add, from list_my_articles. Not its title or id. - `position` (integer): 1-based position within the series. Omit to append at the end. Inserting shifts later articles down. - `series_slug` (string, required): Slug of the target series, from get_series. Not its title or id. ### `list_comments` (~173 tokens) List article comments Read the comment thread on one article, oldest first, paginated. Use it to review reader feedback or summarise a discussion. It reads comments only; there is no tool here for posting or moderating a reply. Reads only. Requires an API key and counts against the plan's request quota. Page through with limit and offset — the default returns the first 20. Returns the comments with their authors and timestamps; an empty list simply means no comments yet, which is not an error. Input parameters: - `article_id` (string, required): UUID of the article, as returned in the `id` field by article tools. Not the slug. - `limit` (integer): Comments per page, 1-100. Defaults to 20. - `offset` (integer): Comments to skip before this page. Defaults to 0. ### `get_follow_status` (~134 tokens) Get follow status Check whether the authenticated account follows a given profile, and how many followers that profile has. Use it before offering to follow someone, so you do not suggest an action that is already done. It answers about ONE profile identified by UUID — there is no tool here that lists everyone you follow. Reads only; following state is not changed. Requires an API key and counts against the plan's request quota. Returns the follow relationship and follower count. Errors if the UUID does not match a profile. Input parameters: - `user_id` (string, required): UUID of the profile to check, as returned in author fields by article tools. Not the username. ### `list_newsletter_subscribers` (~147 tokens) List newsletter subscribers List the people subscribed to the authenticated account's newsletter, paginated. Use it to size the audience or export the list. For what has been SENT to them, use list_newsletter_issues instead. Reads only — no email is sent and no subscriber is added or removed. Requires an API key. This returns personal data (email addresses), so treat the result as confidential and do not echo it into shared transcripts. Page with limit and offset; the default returns the first 20. Input parameters: - `limit` (integer): Subscribers per page, 1-100. Defaults to 20. - `offset` (integer): Subscribers to skip before this page. Defaults to 0. ### `list_newsletter_issues` (~126 tokens) List newsletter issues List newsletter issues the account has sent or scheduled, newest first. Use it to check what went out and when, or to confirm a scheduled send exists before queueing another. For WHO receives them, use list_newsletter_subscribers. Reads only — this neither sends nor cancels an issue. Requires an API key. Returns each issue with its subject, status and send time. An empty list means nothing has been sent yet, which is not an error. Input parameters: - `limit` (integer): Issues to return, 1-50, newest first. Defaults to 10. ### `get_reactions` (~134 tokens) Get article reactions Read the reaction totals on one article, plus which reactions the authenticated account has left on it. Use it before add_reaction or remove_reaction so you know the current state — it is how you tell 'not yet liked' from 'already liked'. Covers one article at a time. Reads only; no reaction is added or removed. Requires an API key. Returns counts per type (like, clap, bookmark) alongside the caller's own reactions. Zero counts are a real answer, not an error. Input parameters: - `article_id` (string, required): UUID of the article, from the `id` field returned by article tools. ### `add_reaction` (~172 tokens) Add a reaction Record one reaction — like, clap, or bookmark — from the authenticated account on an article. This acts publicly as the account holder, so only call it when the user has actually asked to react; do not react on their behalf to be helpful. Adds a single type per call — react twice for two types. Safe to repeat: if the reaction already exists the call succeeds and changes nothing, so it will not double-count. Requires an API key. Use remove_reaction to undo, and get_reactions to see the resulting totals. Input parameters: - `article_id` (string, required): UUID of the article to react to, from the `id` field of article tools. - `type` (string, required): Which reaction to add: 'like' approval, 'clap' stronger approval, 'bookmark' save for later. ### `remove_reaction` (~148 tokens) Remove a reaction Withdraw one reaction the authenticated account previously left on an article. Removes exactly the type you name and leaves the account's other reactions on that article intact — removing 'like' does not remove a 'bookmark'. Nothing else is deleted: the article and its comments are untouched. Safe to repeat: removing a reaction that is not there succeeds and changes nothing. Requires an API key. Call get_reactions first if you need to know what is currently set. Input parameters: - `article_id` (string, required): UUID of the article to un-react to, from the `id` field of article tools. - `type` (string, required): Which reaction to withdraw: 'like', 'clap', or 'bookmark'. ## Diagnostics Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/misar-ai-misarblog-mcp/misarblog-mcp#diagnostics ## Score history - 2026-09-21: 84 - 2026-09-20: 83 - 2026-09-19: 83 - 2026-09-18: 86 - 2026-09-17: 86 - 2026-09-16: 85 - 2026-09-15: 85 - 2026-09-14: 84 - 2026-09-13: 84 - 2026-09-12: 83 - 2026-09-11: 83 - 2026-09-10: 82 - 2026-09-09: 82 - 2026-09-08: 82 - 2026-09-07: 81 - 2026-09-06: 81 - 2026-09-05: 80 - 2026-09-04: 80 - 2026-09-03: 79 - 2026-09-02: 79 - 2026-09-01: 78 - 2026-08-31: 78 - 2026-08-30: 77 - 2026-08-29: 77 - 2026-08-28: 76 - 2026-08-27: 76 - 2026-08-26: 75 - 2026-08-25: 74 - 2026-08-24: 73 - 2026-08-23: 73 ## Common questions ### What is the Misar.Blog MCP Server server? Misar.Blog MCP Server is listed in the public MCP registry as io.github.Misar-AI/misarblog-mcp. Publish and manage articles, series, comments, reactions, newsletters and blog analytics. This page covers its npm package (@misarblog/mcp). ### Is the Misar.Blog MCP Server server safe to use? Misar.Blog MCP Server scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the Misar.Blog MCP Server server expose? Misar.Blog MCP Server exposes 26 tools: login, status, upgrade, get_profile, get_analytics_summary, and 21 more. Their descriptions and schemas cost roughly 4,700 tokens of context every time the server is loaded. ### Is the Misar.Blog MCP Server server still maintained? Misar.Blog MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ### What licence is the Misar.Blog MCP Server server under? Misar.Blog MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls. ## Links - npm package: https://www.npmjs.com/package/@misarblog/mcp - Socket report: https://socket.dev/npm/package/@misarblog/mcp - Repository: https://github.com/Misar-AI/misarblog-mcp - Website: https://www.misar.blog/ - Changelog RSS feed: https://verifymcp.io/servers/misar-ai-misarblog-mcp/misarblog-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/misar-ai-misarblog-mcp/misarblog-mcp.json - HTML version of this page: https://verifymcp.io/servers/misar-ai-misarblog-mcp/misarblog-mcp