Skip to main content
Glama
semantic-pen-mcp-server

semantic-pen-mcp-server

Semantic Pen MCP Server

A one-click MCP server for Semantic Pen that allows you to create, view, and manage articles and projects directly from Claude Code and Cursor.

Just add this to your MCP configuration - no installation required!

For Claude Code

Add to your ~/.config/claude-code/settings.json:

{
  "mcpServers": {
    "semantic-pen": {
      "command": "npx",
      "args": ["-y", "@semanticpen/mcp-server@latest"],
      "env": {
        "SEMANTIC_PEN_API_KEY": "your-api-key-here"
      }
    }
  }
}

For Cursor

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "semantic-pen": {
      "command": "npx",
      "args": ["-y", "@semanticpen/mcp-server@latest"],
      "env": {
        "SEMANTIC_PEN_API_KEY": "your-api-key-here"
      }
    }
  }
}

Replace your-api-key-here with your actual Semantic Pen API key.

Related MCP server: Kilonova MCP

Features

  • 🔑 Automatic API Key Verification - Verifies your API key on startup

  • 📋 Project Management - View all your projects from article queue

  • 📚 Article Management - View articles within specific projects

  • 🔍 Project Search - Search projects by name

  • ✍️ Article Creation - Create new articles with customizable settings

  • 📄 Article Retrieval - Get specific article content and metadata with full HTML

Available Tools

get_projects

Get all your projects from the article queue

No parameters required

get_project_articles

Get all articles from a specific project

projectId (string): The project ID to get articles from

search_projects

Search projects by name

projectName (string): The project name to search for (partial match)

create_article

Create a new article

targetArticleTopic (string): The topic/title for the article
targetKeyword (string, optional): Target SEO keyword
wordCount (number, optional): Target word count (default: 1000)
language (string, optional): Language (default: English)
articleType (string, optional): Type of article (default: Article)
toneOfVoice (string, optional): Tone of voice (default: Professional)

get_article

Get a specific article by ID with full content

articleId (string): The ID of the article to retrieve

Example Usage

  1. View Projects: Use get_projects to see all your projects

  2. View Project Articles: Use get_project_articles with a project ID to see articles in that project

  3. Create Article: Use create_article with a topic like "How to Use AI for Content Creation"

  4. Get Article Content: Use get_article with the returned article ID to see the generated content

Getting Your API Key

  1. Visit SemanticPen.com

  2. Sign up or log in to your account

  3. Go to your API settings to generate an API key

  4. Copy the key and use it in your MCP configuration

Manual Installation (Alternative)

If you prefer to install manually:

npm install -g @semanticpen/mcp-server

Then use in your MCP config:

{
  "command": "semantic-pen-mcp",
  "env": {
    "SEMANTIC_PEN_API_KEY": "your-api-key-here"
  }
}

Troubleshooting

  • "API key not configured": Make sure SEMANTIC_PEN_API_KEY is set in the env section

  • "API key verification failed": Check that your API key is valid and active

  • Server not starting: Ensure you have Node.js 18+ installed

Support

For issues or questions:

  • Visit SemanticPen.com for support

  • Check your API key is valid and has sufficient credits

  • Ensure stable internet connection for API calls

Available Tools

5 tools
create_articleB

Create a new article

Inputs: targetArticleTopic (required), language, wordCount, articleType, +2 more.

get_articleA

Get a specific article by ID with full content

Inputs: articleId (required).

get_project_articlesA

Get all articles from a specific project by project ID

Inputs: projectId (required).

get_projectsA

Get all projects from your article queue

Inputs: no named parameters.

search_projectsB

Search projects by name

Inputs: projectName (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: list projects, list articles per project, search projects, create article, get article. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (get_projects, get_project_articles, search_projects, create_article, get_article), making the API predictable.

    Tool Count5/5

    The server is scoped to a focused domain (projects and articles) and 5 tools is a reasonable, manageable number for this purpose.

    Completeness2/5

    The tool surface is read-heavy with only article creation. Missing operations include updating or deleting articles, creating/updating/deleting projects, and searching articles, which are significant gaps for full lifecycle management.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables Claude Code to interact with Jupyter notebooks, perform semantic search over knowledge files, and manage research projects.
      33
      4
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Persistent knowledge base tools for Claude Code that store project context, decisions, and patterns locally across sessions, eliminating cold starts.
      8
      46 PyPI
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables Claude to launch and manage Cursor Cloud Agents on GitHub repos, including polling status, sending follow-ups, and reading conversations/PRs.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables Claude Code to search your local project notes and list indexed projects through hybrid keyword and semantic retrieval, returning relevant snippets with file and line references.
      MIT