Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@semantic-pen-mcp-server create an article on sustainable living"
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.
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!
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"
}
}
}
}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: XLMCP
🔑 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
get_projectsGet all your projects from the article queue
No parameters requiredget_project_articlesGet all articles from a specific project
projectId (string): The project ID to get articles fromsearch_projectsSearch projects by name
projectName (string): The project name to search for (partial match)create_articleCreate 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_articleGet a specific article by ID with full content
articleId (string): The ID of the article to retrieveView Projects: Use get_projects to see all your projects
View Project Articles: Use get_project_articles with a project ID to see articles in that project
Create Article: Use create_article with a topic like "How to Use AI for Content Creation"
Get Article Content: Use get_article with the returned article ID to see the generated content
Visit SemanticPen.com
Sign up or log in to your account
Go to your API settings to generate an API key
Copy the key and use it in your MCP configuration
If you prefer to install manually:
npm install -g @semanticpen/mcp-serverThen use in your MCP config:
{
"command": "semantic-pen-mcp",
"env": {
"SEMANTIC_PEN_API_KEY": "your-api-key-here"
}
}"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
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
Create a new article
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Language for the article (default: English) | English |
| wordCount | No | Target word count (default: 1000) | |
| articleType | No | Type of article (default: Article) | Article |
| toneOfVoice | No | Tone of voice (default: Professional) | Professional |
| targetKeyword | No | Target SEO keyword for the article (optional) | |
| targetArticleTopic | Yes | The topic/title for the article |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'Create a new article,' which implies a write operation, but fails to disclose side effects, authentication needs, rate limits, or what the response contains. For a mutation tool, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no waste. It is concise and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has 6 parameters, no output schema, and no annotations. The description fails to explain return values, associations (e.g., project membership), or any caveats. While it covers the basic purpose, it is incomplete for an agent to fully understand the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and all parameters have meaningful descriptions with defaults. The description itself adds no parameter-level detail, but since the schema fully documents them, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Create a new article' uses a specific verb and resource, clearly indicating the action and object. It distinguishes itself from sibling tools (get_projects, get_project_articles, search_projects, get_article) as the only creation tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, no mention of prerequisites, context, or exclusions. It merely states the action without any situational framing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a specific article by ID with full content
| Name | Required | Description | Default |
|---|---|---|---|
| articleId | Yes | The ID of the article to retrieve |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It adds that the tool returns 'full content', which is useful beyond the name, but it does not mention error handling (e.g., 404 if article not found), permission requirements, or response structure. For a read-only operation this is somewhat acceptable, but deeper context would improve transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence, front-loaded, and contains no wasted words. It efficiently conveys the core action, target, and result in a compact form.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a low-complexity tool with one parameter and no output schema, the description provides sufficient context to select and invoke it correctly. It clarifies that the response includes the full article content, which is the key missing piece an agent would need. It could add error behavior details, but given the simplicity and sibling context, it is mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes the only parameter (articleId) with 100% coverage. The description merely repeats 'by ID' and adds no additional meaning about the parameter's format, constraints, or behavior. Since schema coverage is high, the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get'), the resource ('a specific article'), and the scope ('by ID with full content'). It distinguishes from sibling tools like get_project_articles (which likely retrieves articles belonging to a project) and search_projects (which searches projects), making its purpose precise.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the proper use case: retrieving a full article when you already have its ID. It does not explicitly mention alternatives or exclusions, but the sibling tool names provide context. The phrase 'by ID' signals that this is for targeted retrieval rather than listing or searching, offering clear context without explicit when-not-to-use directions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all articles from a specific project by project ID
| Name | Required | Description | Default |
|---|---|---|---|
| projectId | Yes | The project ID to get articles from |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only states what the tool does but reveals no additional behavior such as auth requirements, pagination, error handling, or result format. For a read operation, some transparency about these aspects would be expected.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no filler or redundant words. Every word contributes to the meaning, making it highly efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description is largely sufficient: it names the input and the expected result ('all articles'). However, the lack of behavioral and usage guidance slightly reduces completeness, preventing a perfect score.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully describes the single parameter 'projectId' with a clear description. The tool description adds minimal extra meaning beyond restating the parameter's role. Since schema coverage is 100%, the baseline is 3, and the description does not enhance parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get all articles'), the resource ('articles'), and the scope ('from a specific project by project ID'). It distinguishes itself from sibling tools like 'get_projects' (which lists projects) and 'get_article' (which likely retrieves a single article).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a project ID and need all its articles, but it does not explicitly contrast with sibling tools or state when not to use this tool. The context is sufficient for a simple case, but no alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get all projects from your article queue
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It implies a read-only operation via 'Get' and defines the scope as 'all projects from your article queue', but it does not disclose potential caveats like whether archived projects are included, pagination, or limits. This is adequate for a simple read tool but lacks rich behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that gets straight to the point with no wasted words. It is perfectly concise for a simple list-all tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless tool with no output schema, the description provides sufficient context: it states what is returned (all projects) and the source scope. While it does not describe the return format, the plural 'projects' implies a list, making it reasonably complete. However, adding a note about what a 'project' is might improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and the schema coverage is 100%, so the description does not need to explain parameter meanings. Per the rubric, a baseline of 4 is appropriate when there are no params.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to retrieve all projects within a specific scope ('your article queue'). The verb 'Get' and plural 'projects' make it distinct from sibling tools like 'search_projects' (which implies filtering) and 'get_project_articles' (which targets articles, not projects).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'search_projects'. It does not explicitly mention exclusions or prerequisites, leaving the agent to infer that this is the go-to for listing all projects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search projects by name
| Name | Required | Description | Default |
|---|---|---|---|
| projectName | Yes | The project name to search for (partial match) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits, but it only restates the tool's name. It does not mention that the search is read-only, whether it returns matches or a single result, pagination, or matching behavior beyond what the schema's 'partial match' note provides (which is in the schema, not the description).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single four-word sentence, leaving no wasted words. It is appropriately concise for the minimal information it conveys, though its brevity contributes to lack of context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with no output schema, the description is insufficiently complete. It does not indicate whether the result is a list of matching projects, their structure, or how the search behaves. It also lacks any usage context relative to sibling tools, making it difficult for an agent to fully understand the tool's role.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear parameter description ('partial match'). The tool description adds no additional semantic meaning beyond repeating the parameter name, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb (search) and resource (projects) with a scope (by name), distinguishing it from sibling tools like get_projects which likely fetches projects without searching. Though terse, it unambiguously conveys the tool's core function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool rather than get_projects or other siblings. It does not mention alternatives, prerequisites, or contexts where this search is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0create_articleget_articleget_project_articlesget_projectssearch_projectsEach 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.
All tool names follow a consistent verb_noun pattern (get_projects, get_project_articles, search_projects, create_article, get_article), making the API predictable.
The server is scoped to a focused domain (projects and articles) and 5 tools is a reasonable, manageable number for this purpose.
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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Live SEO workflow tools for Claude Code, Codex, and AI agents.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/pushkarsingh32/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
