What can you do with this server?

This MCP server lets you manage a Hashnode blog through the Hashnode GraphQL API. * Retrieve your profile and publication IDs. * Get publication metadata by host/domain. * List published posts and fetch a post by slug. * List drafts in a publication. * Create and update drafts with Markdown content, tags, cover image, slug, and SEO fields. * Publish drafts or publish posts directly, including scheduled publishing. * Update published posts. * Permanently delete published posts.

Which integrations are available for this server?

Allows managing a Hashnode blog, including creating drafts, publishing posts, listing and updating posts, and managing publications via the Hashnode GraphQL API.

How do I use hashnode-mcp-server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@hashnode-mcp-server Create a draft about cloud security best practices" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

hashnode-mcp-server

by kieksme

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

@kieksme/hashnode-mcp

AgentAvow

MCP server for the Hashnode GraphQL API.
Create drafts, publish posts, and manage your blog from any MCP client.

IMPORTANT

Hashnode Pro plan required.
Since May 2026, Hashnode's GraphQL API is only available to publications on a Pro plan.
Free accounts will receive an error. Upgrade at hashnode.com/settings/billing.

NOTE

Package rename: published as@kieksme/hashnode-mcp (was @kieksme/mcp-hashnode).
The mcp-hashnode CLI binary remains as a compatibility alias for hashnode-mcp.

Tools

Tool	Description
`hashnode_get_me`	Get your profile and publication IDs
`hashnode_get_publication`	Get publication info by host
`hashnode_list_posts`	List published posts
`hashnode_get_post`	Get a single post by slug
`hashnode_create_draft`	Create a draft
`hashnode_update_draft`	Update an existing draft
`hashnode_list_drafts`	List drafts in a publication
`hashnode_publish_draft`	Publish a draft → live post
`hashnode_publish_post`	Publish directly (no draft step)
`hashnode_update_post`	Update a published post
`hashnode_delete_post`	Delete a post ⚠️

Related MCP server: mcp-blog

Setup

1. Get your Personal Access Token

Go to hashnode.com/settings/developer and click Generate new token.

2. Install

Via npx (no install needed — recommended):

npx -y @kieksme/hashnode-mcp

Via global install:

pnpm add -g @kieksme/hashnode-mcp

Build from source:

git clone https://github.com/kieksme/mcp-hashnode.git
cd mcp-hashnode
pnpm install && pnpm run build

3. Configure your MCP client

Claude Code plugin

/plugin marketplace add kieksme/mcp-hashnode
/plugin install hashnode-mcp@mcp-hashnode

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "hashnode": {
      "command": "npx",
      "args": ["-y", "@kieksme/hashnode-mcp"],
      "env": {
        "HASHNODE_TOKEN": "your-token-here"
      }
    }
  }
}

Claude Code (CLI)

claude mcp add hashnode \
  --command npx \
  --args "-y @kieksme/hashnode-mcp" \
  --env HASHNODE_TOKEN=your-token-here

Cursor

Add to .cursor/mcp.json in your project root, or to ~/.cursor/mcp.json globally:

{
  "mcpServers": {
    "hashnode": {
      "command": "npx",
      "args": ["-y", "@kieksme/hashnode-mcp"],
      "env": {
        "HASHNODE_TOKEN": "your-token-here"
      }
    }
  }
}

VS Code (GitHub Copilot)

Add to .vscode/mcp.json in your workspace:

{
  "servers": {
    "hashnode": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@kieksme/hashnode-mcp"],
      "env": {
        "HASHNODE_TOKEN": "your-token-here"
      }
    }
  }
}

Remote MCP (ChatGPT, Codex, and Copilot Cloud Agent)

Set MCP_TRANSPORT=http, MCP_AUTH_TOKEN, MCP_HTTP_HOST=0.0.0.0, and MCP_ALLOWED_HOSTS on the hosted server (Railway sets PORT). The MCP endpoint is https://<your-host>/mcp; /health is available for hosting probes (no auth, Host-agnostic). Use the committed .github/mcp.json for Copilot Cloud Agent; it expects COPILOT_MCP_HASHNODE_URL and COPILOT_MCP_HASHNODE_TOKEN.

Legacy aliases still work (one-line deprecation warning): MCP_HTTP_AUTH_TOKEN, MCP_HTTP_PORT, MCP_HTTP_ALLOWED_HOSTS, MCP_HTTP_ALLOWED_ORIGINS, HEALTH_ENDPOINT.

In Codex, register the same endpoint with:

codex mcp add hashnode --url https://<your-host>/mcp \
  --bearer-token-env-var HASHNODE_MCP_AUTH_TOKEN

In ChatGPT, add the public HTTPS endpoint as a custom MCP app/connector and provide the bearer token during setup. ChatGPT cannot reach localhost.

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "hashnode": {
      "command": "npx",
      "args": ["-y", "@kieksme/hashnode-mcp"],
      "env": {
        "HASHNODE_TOKEN": "your-token-here"
      }
    }
  }
}

Running the server

Transport is provided by @kieksme/mcp-http-kit:

Mode	How
stdio (default)	Local MCP clients spawn the process
HTTP	`MCP_TRANSPORT=http` or `--http`

# Local stdio
HASHNODE_TOKEN=… npx -y @kieksme/hashnode-mcp

# Streamable HTTP (containers / Railway)
MCP_TRANSPORT=http \
MCP_HTTP_HOST=0.0.0.0 \
MCP_ALLOWED_HOSTS=your.railway.app \
MCP_AUTH_TOKEN="$(openssl rand -hex 32)" \
HASHNODE_TOKEN=… \
pnpm start

Upstream credentials

Variable	Notes
`HASHNODE_TOKEN`	Default: process env Personal Access Token
`HASHNODE_CREDENTIAL_MODE`	`env` (default) or `header`
`X-Hashnode-Token`	Per-request PAT when mode is `header` (never logged). Refused when `MCP_AUTH_MODE=none`.

HTTP / kit env (summary)

Variable	Default	Notes
`MCP_TRANSPORT`	`stdio`	`stdio` \| `http`
`PORT`	`3000`	Preferred listen port (Railway). Fallback: `MCP_HTTP_PORT`
`MCP_HTTP_HOST`	`127.0.0.1`	Use `0.0.0.0` in containers
`MCP_HTTP_PATH`	`/mcp`	MCP endpoint
`MCP_HEALTH_PATH`	`/health`	Unauthenticated health
`MCP_ALLOWED_HOSTS`	localhost trio	Required when binding beyond localhost
`MCP_AUTH_MODE`	`bearer`	`bearer` \| `oauth` \| `none`
`MCP_AUTH_TOKEN`	—	Bearer secrets; comma-separated for rotation

Tracing (OpenTelemetry, opt-in)

Off by default. Set an OTLP endpoint and one tool call becomes one trace: MCP client → this server → Hashnode GraphQL API. The trace context comes from params._meta (traceparent / tracestate), so it also works over stdio. It is trusted only with MCP_AUTH_MODE bearer / oauth, or on stdio.

OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 \
OTEL_SERVICE_NAME=hashnode-mcp \
MCP_TRANSPORT=http MCP_AUTH_TOKEN=… HASHNODE_TOKEN=… \
pnpm start

Try it locally with Jaeger (UI on http://localhost:16686):

docker run --rm -p 16686:16686 -p 4318:4318 jaegertracing/all-in-one

Variable	Notes
`OTEL_EXPORTER_OTLP_ENDPOINT`	Switches tracing on (traces are posted to `<endpoint>/v1/traces`). Use `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT` for a full URL.
`OTEL_EXPORTER_OTLP_HEADERS`	Auth headers for the collector (never logged)
`OTEL_SERVICE_NAME`	Service name, default `hashnode-mcp`
`OTEL_SDK_DISABLED=true`	Kill switch
`MCP_OTEL_RECORD_PAYLOADS=true`	Also record tool arguments, results and full URLs. Off by default because they can contain article text and query strings.

Privacy by default: no tool arguments or results, no Authorization header, query strings and credentials removed from URL attributes, only traceparent / tracestate sent to Hashnode (never baggage), and only calls made inside a tool call are traced. Details: @kieksme/mcp-http-kit README.

Docker / Railway / Smithery

Dockerfile — multi-stage, non-root, HEALTHCHECK on /health
railway.json — healthcheck path /health
server.json — official MCP registry (io.github.kieksme/hashnode-mcp)
smithery.yaml — container runtime over Streamable HTTP

docker build -t hashnode-mcp .
docker run --rm -p 3000:3000 \
  -e MCP_AUTH_TOKEN=… \
  -e HASHNODE_TOKEN=… \
  -e MCP_ALLOWED_HOSTS=localhost,127.0.0.1 \
  hashnode-mcp

Usage examples

"What's my publication ID?"
→ hashnode_get_me

"Create a draft called 'Cloud Security Best Practices' with this content: ..."
→ hashnode_create_draft

"Publish the draft with ID xyz"
→ hashnode_publish_draft

"List my last 10 posts on thinkport.hashnode.dev"
→ hashnode_list_posts

Authentication

Hashnode requires Authorization: <token> (no Bearer prefix).
All mutations need the token; most read queries are public.

MCP clients talking to this server over HTTP must send Authorization: Bearer <MCP_AUTH_TOKEN> separately from the Hashnode PAT.

Rate limits

Queries: 20,000 req/min
Mutations: 500 req/min

Tags format

Tags must be objects — not plain strings:

[
  { "name": "Cloud Computing", "slug": "cloud-computing" },
  { "name": "DevOps", "slug": "devops" }
]

Development

pnpm install
pnpm lint
pnpm typecheck
pnpm test
pnpm build

Node 22.14+, pnpm, ESM.

Releases

This project uses release-please for automated releases.

Commits to main that follow Conventional Commits (feat:, fix:, chore: etc.) are tracked automatically.
release-please opens a Release PR that bumps the version and updates CHANGELOG.md.
Merging the Release PR creates a GitHub Release and triggers an automated npm publish of @kieksme/hashnode-mcp.

npm Trusted Publishing

The publish job uses npm Trusted Publishing (OIDC), so no NPM_TOKEN secret is needed. One-time setup on npmjs.com, under @kieksme/hashnode-mcp → Settings → Trusted Publisher:

Provider: GitHub Actions
Organization or user: kieksme
Repository: mcp-hashnode
Workflow filename: release.yml (must match exactly; leave Environment empty)

The workflow runs on a GitHub-hosted runner with Node 24 and publishes with npm 11.5.1 (npm publish --provenance).

License

MIT

Available Tools

11 tools

hashnode_create_draftCreate a Hashnode draftA

Create a new draft in a Hashnode publication. Does NOT publish — use hashnode_publish_draft afterwards.

Args:

publication_id (string, required): Publication ID
title (string, required): Post title
content_markdown (string, required): Post content in Markdown
subtitle (string, optional): Short subtitle
tags (array, optional): Tags as [{ name, slug }] — slug must be lowercase with hyphens
cover_image_url (string, optional): URL of cover image
slug (string, optional): Custom URL slug (auto-generated from title if omitted)
original_article_url (string, optional): Canonical URL for cross-posted articles
meta_title (string, optional): SEO meta title
meta_description (string, optional): SEO meta description
response_format: 'markdown' or 'json'

Returns: draft id, title, slug, tags, updatedAt

Inputs: title (required), publication_id (required), content_markdown (required), slug, +7 more.

hashnode_delete_postDelete a published Hashnode postB

Destructive

Permanently delete a published post. This action cannot be undone.

Args:

post_id (string, required): Post ID to delete
response_format: 'markdown' or 'json'

⚠️ WARNING: This permanently deletes the post.

Inputs: post_id (required), response_format.

hashnode_get_meGet current Hashnode user and their publicationsA

Read-onlyIdempotent

Returns the authenticated user's profile and a list of their publications. Use this first to discover your publicationId(s) before creating or listing posts.

Returns:

id, name, username, profilePicture
publications[]: { id, title, url }

Examples:

"What is my publication ID?" → call hashnode_get_me
"List my Hashnode blogs" → call hashnode_get_me

Inputs: response_format.

hashnode_get_postGet a single Hashnode post by slugA

Read-onlyIdempotent

Fetch full details of a published post by its slug.

Args:

host (string, required): Publication host
slug (string, required): Post slug from the URL, e.g. "my-first-post"
response_format: 'markdown' or 'json'

Returns: full post data including content brief, views, tags, cover image, author

Inputs: host (required), slug (required), response_format.

hashnode_get_publicationGet Hashnode publication by hostA

Read-onlyIdempotent

Fetch metadata for a Hashnode publication by its host/domain.

Args:

host (string): Publication host, e.g. "yourblog.hashnode.dev" or a custom domain
response_format: 'markdown' or 'json'

Returns: id, title, url, about, author info

Examples:

host: "thinkport.hashnode.dev"

Inputs: host (required), response_format.

hashnode_list_draftsList Hashnode draftsA

Read-onlyIdempotent

List drafts in a Hashnode publication.

Args:

publication_id (string): The publication ID (from hashnode_get_me)
limit (number): Number of drafts to return (default 20, max 50)
after (string): Pagination cursor from a previous call
response_format: 'markdown' or 'json'

Returns: list of drafts with id, title, subtitle, tags, updated date

Inputs: publication_id (required), after, limit, response_format.

hashnode_list_postsList published posts in a Hashnode publicationA

Read-onlyIdempotent

List published blog posts in a publication, ordered by publish date (newest first).

Args:

host (string, required): Publication host, e.g. "yourblog.hashnode.dev"
limit (number): Posts per page (default 20, max 50)
after (string): Cursor for pagination
response_format: 'markdown' or 'json'

Returns: posts with id, title, slug, url, publishedAt, views, readTime, tags

Inputs: host (required), after, limit, response_format.

hashnode_publish_draftPublish a Hashnode draftA

Publish an existing draft, making it a live blog post.

Args:

draft_id (string, required): Draft ID to publish (from hashnode_create_draft or hashnode_list_drafts)
response_format: 'markdown' or 'json'

Returns: post id, title, slug, url, publishedAt, tags

Examples:

Create draft → publish: hashnode_create_draft → hashnode_publish_draft

Inputs: draft_id (required), response_format.

hashnode_publish_postPublish a post directly to Hashnode (no draft step)A

Publish a new blog post directly without creating a draft first. Prefer hashnode_create_draft + hashnode_publish_draft for a safer workflow.

Args:

publication_id (string, required): Publication ID (from hashnode_get_me)
title (string, required): Post title
content_markdown (string, required): Post content in Markdown
subtitle (string, optional): Short subtitle
tags (array, optional): [{ name, slug }] — max 5 tags
cover_image_url (string, optional): URL of cover image
slug (string, optional): Custom URL slug
original_article_url (string, optional): Canonical URL for cross-posts
meta_title (string, optional): SEO title
meta_description (string, optional): SEO description
scheduled_at (string, optional): ISO 8601 datetime for scheduled publishing
response_format: 'markdown' or 'json'

Returns: post id, title, slug, url, publishedAt, tags

Inputs: title (required), publication_id (required), content_markdown (required), slug, +8 more.

hashnode_update_draftUpdate an existing Hashnode draftB

Update fields of an existing draft. Only provided fields are changed.

Args:

draft_id (string, required): Draft ID to update
title (string, optional): New title
content_markdown (string, optional): New content in Markdown
subtitle (string, optional): New subtitle
tags (array, optional): New tags as [{ name, slug }]
cover_image_url (string, optional): New cover image URL
response_format: 'markdown' or 'json'

Inputs: draft_id (required), tags, title, subtitle, +3 more.

hashnode_update_postUpdate a published Hashnode postA

Update fields of an already-published post. Only provided fields are changed.

Args:

post_id (string, required): Post ID (from hashnode_list_posts or hashnode_get_post)
title (string, optional): New title
content_markdown (string, optional): New content in Markdown
subtitle (string, optional): New subtitle
tags (array, optional): New tags [{ name, slug }]
cover_image_url (string, optional): New cover image URL
response_format: 'markdown' or 'json'

Inputs: post_id (required), tags, title, subtitle, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

A3.9/5.0

Scored 2026-10-27 03:30 across 11 tools

Disambiguation4/5

Each tool maps to a distinct resource (publication, draft, post) plus action, so most selections are unambiguous. The only real overlap is the two publishing paths — hashnode_publish_post versus hashnode_create_draft + hashnode_publish_draft — though the descriptions explicitly recommend the latter for safety.

Naming Consistency5/5

Every tool uses the same hashnode_ prefix with a verb_noun structure (list_drafts, create_draft, publish_draft, update_post, delete_post). The lone outlier, hashnode_get_me, is still readable and consistent in style.

Tool Count5/5

At 11 tools the surface is well-scoped: two discovery/read tools, a full draft lifecycle, and full post CRUD. No tool looks redundant enough to remove, and nothing feels padded.

Completeness4/5

Posts have full lifecycle coverage (list, get, publish, update, delete) and drafts cover list/create/update/publish. The notable gap is the absence of a delete_draft (and any comment operations), which agents can work around but leaves drafts unmanageable once created.

Maintenance

ActivityMaintained

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

SlopIt: blogs for AI agentsA
io.slopit
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.
Content Management Systems Marketing
1812
https://slopit.io/mcp
jumpcloud-genai
com.jumpcloud
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Cloud Platforms Security Developer Tools
2
https://mcp.jumpcloud.com/v1
Notion MCP by InsightfulPipeA
com.insightfulpipe
Hosted Notion MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Note Taking Workplace & Productivity
41
https://notion.insightfulmcp.com/
QPostA
io.github.arslan2012
MCP server for QPost — lets AI agents publish video and image posts to YouTube, TikTok, Instagram.
Social Media
91
https://qpost.dev/mcp

Related MCP Servers

Hashnode MCP Server
Content Management Systems Developer Tools
sbmagar13
A
license
Not graded
quality
D
maintenance
A Model Context Protocol server that enables AI assistants to programmatically interact with the Hashnode API for creating, updating, searching, and retrieving blog content.
Updated 6 months ago (2026-05-19 07:12 UTC)
7
MIT
mcp-blog
Content Management Systems Developer Tools
MasatoshiSano
F
license
A
quality
D
maintenance
MCP server for blog admin API enabling preview, publish, list, and delete blog posts from Claude Code via stdio transport.
Updated 6 months ago (2026-05-01 05:23 UTC)
5
-
substack-mcp
Content Management Systems Marketing
nanameru
A
license
A
quality
C
maintenance
MCP server for Substack that lets Claude Code create drafts, upload images, set cover thumbnails, schedule, and publish posts on your Substack publication.
Updated 23 days ago (2026-10-23 01:35 UTC)
11
16
MIT
mcp-graphql-bridge
API Testing Developer Tools
murilojrpereira
A
license
A
quality
B
maintenance
A generic MCP (Model Context Protocol) server that bridges any GraphQL API to Claude Code. It introspects your GraphQL schema and exposes each query and mutation as an individual tool, letting Claude interact with your API directly.
Updated 5 days ago (2026-11-09 09:59 UTC)
2
50 npm
1
MIT

@kieksme/hashnode-mcp

Tools

Setup

1. Get your Personal Access Token

2. Install

3. Configure your MCP client

Claude Code plugin

Claude Desktop

Claude Code (CLI)

Cursor

VS Code (GitHub Copilot)

Remote MCP (ChatGPT, Codex, and Copilot Cloud Agent)

Windsurf

Running the server

Upstream credentials

HTTP / kit env (summary)

Tracing (OpenTelemetry, opt-in)

Docker / Railway / Smithery

Usage examples

Authentication

Rate limits

Tags format

Development

Releases

npm Trusted Publishing

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Hashnode MCP Server

mcp-blog

substack-mcp

mcp-graphql-bridge