
Misarblog Mcp
io.github.mrgulshanyadavPublished by GitHub account mrgulshanyadavv1.0.6Updated Oct 13, 2026
Publish blog posts, manage drafts, generate AI cover images, and pull analytics from Misar.Blog.
Overview
Lets an assistant publish, draft, and manage Misar.Blog articles, series, newsletters, and analytics through the Misar.Blog API.
- What you can do
- Connects an assistant to a Misar.Blog account so it can publish or schedule articles, save drafts, update titles, bodies, and tags, and organize posts into series. It also reads analytics summaries, comments, reactions, follower status, and newsletter subscribers and issues, and can generate AI cover images, SEO titles, and topic research. Read-only resources expose the profile, recent articles, drafts, series, and a 30-day analytics summary.
- When to use it
- Useful for bloggers and creators on Misar.Blog who want an assistant to write, draft, publish, and promote posts, plan multi-part series, draft newsletters, or report on views, revenue, and subscribers without switching to the web dashboard.
- Requirements
- Runs locally over stdio via the npm package @misarblog/mcp (Node.js with npx), or as a remote Streamable HTTP endpoint. Requires a Misar.Blog account and either an API key in MISARBLOG_API_KEY or the browser login tool, which saves credentials to a local config file. Self-hosted instances need MISARBLOG_BASE_URL.
Installation
In SourceWeft
- Open Misarblog Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Misar.Blog MCP Server
Publish and manage articles, series, comments, reactions, newsletters, and analytics — from any AI assistant.
23 tools · 8 prompts · 5 resources · 6 agent skills
Works with Claude (Desktop, Code, and web), Cursor, VS Code, Windsurf, Cline, Zed, Gemini CLI, ChatGPT, and any other MCP-compatible client — over stdio or Streamable HTTP.
Install
Smithery (recommended)
Claude Code
Manual (any client)
Ready-made configs for every client live in connectors/.
Remote (no install)
Authentication
Two options — no copy-paste needed for the first:
- Browser login. Start the server with no key and run the
logintool. It opens the Misar.Blog consent screen, you review the requested permissions, and the key is delivered straight back and saved to~/.misarblog/config.json. - API key. Create one at https://www.misar.blog/dashboard/settings/api-keys and set
MISARBLOG_API_KEY.
Self-hosted instances: set MISARBLOG_BASE_URL.
Tools
Prompts
Reusable workflows your client exposes as slash-commands.
Resources
Read-only context an agent can attach without spending a tool call.
Agent skills
Bundled in skills/ — guidance an agent loads when a task matches.
Safety
Destructive and irreversible actions are annotated (destructiveHint) so
clients can prompt before running them. The skills instruct agents to confirm
before anything that sends mail, publishes content, or is otherwise visible to
other people.
Discovery (initialize, tools/list, prompts/list, resources/list)
never requires credentials, so registries can index the server without one.
Every action does.
Links
- Website — https://www.misar.blog
- App — https://www.misar.blog
- Documentation — https://docs.misar.io/blog/mcp
- Smithery — https://smithery.ai/server/misar/misarblog-mcp
- npm — https://www.npmjs.com/package/@misarblog/mcp
- Source — https://github.com/Misar-AI/misarblog-mcp
MIT © Misar.AI
Source: README.md at commit 9dc83a3
Tools
0Version history
1- v1.0.6LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts