The Contraption Company MCP server provides programmatic access to a Ghost blog's content through semantic search and structured data retrieval.
Core Features:
Semantic Search: Perform hybrid search across blog posts and pages using natural language queries with Voyage contextualized embeddings and Splade sparse vectors
Fetch Individual Content: Retrieve full blog posts or pages using slugs, canonical URLs, or post:// identifiers
List Posts: Browse posts with pagination (up to 10 per page), sorted by newest or oldest publication date
Access Members-Only Content: Full access to all published posts and pages, including members-only content via Ghost Admin API credentials
Automatic Updates: Background syncing polls the Ghost Admin API every 5 minutes to detect and incorporate new, updated, or deleted content
Query Logging: Records search queries for analytical purposes
Performance & Deployment:
Built on FastAPI and Chroma Cloud for fast responses
Publicly accessible hosted server at https://mcp.contraption.co with no authentication required
Supports local Docker deployment with configurable environment variables
Works with Cursor, ChatGPT, VS Code, Codex, Claude Code, and OpenAI SDK
Provides tools for accessing and searching Ghost blog content, including retrieving individual posts, listing posts with pagination, and performing semantic search across published content including members-only posts
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., "@Contraption Company MCP search for posts about AI-powered tools for developers"
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.
An MCP (Model Context Protocol) server for Contraption Company essay, built on Chroma Cloud.
Contraption Company MCP is available as a hosted MCP server with no authentication.
Field | Value |
Server URL |
|
Use the deep link to install directly in Cursor: Install Contraption Company MCP.
Or, create or edit ~/.cursor/mcp.json:
{
"mcpServers": {
"contraption-company": {
"url": "https://mcp.contraption.co"
}
}
}Open Settings → Connectors.
Click Create new connector.
Set MCP Server URL to https://mcp.contraption.co.
Leave authentication blank and save.
Create or edit .vscode/mcp.json:
{
"servers": {
"contraption-company": {
"type": "http",
"url": "https://mcp.contraption.co"
}
}
}Add to ~/.codex/config.toml:
[mcp_servers.contraption-company]
command = "npx"
args = ["mcp-remote", "--transport", "http", "https://mcp.contraption.co"]Run in your terminal:
claude mcp add --transport http contraption-company https://mcp.contraption.cofrom openai import OpenAI
client = OpenAI()
response = client.responses.create(
model="gpt-5",
input="List the newest Contraption Company blog posts.",
tools=[
{
"type": "mcp",
"server_label": "contraption-company",
"server_url": "https://mcp.contraption.co",
"require_approval": "never",
}
],
)
print(response)Related MCP server: Jekyll MCP Server
Search: Find posts and pages by query text
Automatic Indexing: Syncs with the blog API on startup and via scheduled polling
Full Content Access: Indexes all published posts and pages, including members-only content
Fast Performance: Powered by FastAPI and Chroma Cloud
Background Updates: Polls Ghost every few minutes for new, updated, or deleted posts and pages
Query Logging: Records searches in a dedicated Chroma collection for analysis
Docker Ready: Includes Dockerfile for easy deployment
Well Tested: Comprehensive test suite with pytest
Clone and install:
git clone <repository>
cd mcp
uv sync --all-extrasConfigure environment:
cp .env.example .env
# Edit .env with your credentialsRun the server:
./run.sh
# Or: uv run python -m src.main# Build
docker build -t contraption-mcp .
# Run
docker run -p 8000:8000 --env-file .env contraption-mcp
# Or use docker-compose
docker-compose upRunning locally requires credentials for external services:
Ghost Admin API Key: From your Ghost Admin panel (Settings > Integrations)
Chroma Cloud Credentials: Tenant ID, Database, and API key from Chroma Cloud
Chroma Query Collection (optional): Set CHROMA_QUERY_COLLECTION to override the default queries collection
Voyage API Key: Required to generate contextualized embeddings
Ghost Blog URL: Your Ghost blog's URL
Polling Interval (optional): Set POLL_INTERVAL_SECONDS to override the default 5 minute sync cadence
Members-only content and query logging are enabled by default. Ensure your privacy policy and access controls cover both.
Support: hello@contraption.co
Privacy policy: https://www.contraption.co/privacy/
Query logging and members-only content are enabled, and the privacy policy must cover both.
fetch(id): Fetch a single post or page using the canonical URL as the identifier. Provide the id returned by list_posts/search (which is the canonical URL); slugs and shorthand schemes are also accepted but responses always resolve to full URLs.
list_posts(sort_by, page, limit): List posts with pagination, returning canonical URLs as identifiers
search(query, limit): Search posts and pages by query text; returns canonical URLs for result IDs
GET /: Server info (redirects to GitHub repo for non-MCP requests)
GET /health: Health check
GET /debug/search: Debug search endpoint (see /debug/docs for Swagger UI)
/mcp/*: MCP protocol endpoints
The server polls the Ghost Admin API every 5 minutes to detect new, updated, or deleted posts and pages. Adjust the cadence by setting the POLL_INTERVAL_SECONDS environment variable.
# Install dev dependencies
make dev
# Run tests
make test
# Lint and format
make format lint
# Run all checks
make checkMIT
Fetch a blog post using the MCP HTTP-style contract.
Accepts an id that can be a slug, canonical URL, or a post:// style identifier.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
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 mentions the MCP HTTP-style contract which provides some context, but doesn't describe important behavioral aspects like whether this is a read-only operation, error handling, authentication requirements, rate limits, or what happens when an invalid ID is provided. The description is minimal and lacks behavioral transparency for a tool with no annotation coverage.
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 extremely concise with only two sentences, both of which add value. The first sentence establishes the tool's purpose and context, while the second provides crucial parameter semantics. There is zero wasted text or redundancy.
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?
Given that there's an output schema (which means return values are documented elsewhere), the description provides adequate basic information about what the tool does and what the parameter accepts. However, for a tool with no annotations and only 0% schema description coverage, the description should ideally provide more behavioral context about how the tool operates, especially since it mentions an 'MCP HTTP-style contract' without explaining what that entails.
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?
With 0% schema description coverage for the single parameter 'id', the description provides valuable semantic information by explaining what the 'id' parameter can be: 'a slug, canonical URL, or a post:// style identifier.' This adds meaningful context beyond the basic string type in the schema. However, it doesn't provide examples or format specifications for these identifier types.
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: 'Fetch a blog post' specifies the verb (fetch) and resource (blog post). It distinguishes from sibling tools 'list_posts' and 'search' by focusing on retrieving a single post rather than listing or searching. However, it doesn't explicitly mention the sibling differentiation in the description text itself.
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 context by mentioning the MCP HTTP-style contract and acceptable identifier types, but doesn't explicitly state when to use this tool versus the 'list_posts' or 'search' siblings. No guidance is provided about when-not-to-use or alternative scenarios beyond the basic functionality description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List blog posts with pagination.
Args: sort_by: Sort order - 'newest' or 'oldest' (default: 'newest') page: Page number (default: 1) limit: Number of posts per page, max 10 (default: 10)
Returns: List of post summaries with metadata
| Name | Required | Description | Default |
|---|---|---|---|
| sort_by | No | newest | |
| page | No | ||
| limit | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It mentions pagination and max limit (10), which are useful behavioral traits. However, it doesn't cover aspects like rate limits, authentication needs, or error handling, leaving gaps for a tool with no annotation support.
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 well-structured and front-loaded with the core purpose. The Args and Returns sections are organized efficiently, with no wasted sentences—each part earns its place.
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?
Given the tool's moderate complexity (3 parameters, no annotations, but with an output schema), the description is fairly complete. It covers parameters well and mentions return values, though it could benefit from more behavioral context like error cases or performance hints.
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 0%, so the description must compensate. It provides clear semantics for all three parameters (sort_by, page, limit), including defaults and constraints (e.g., max 10 for limit), adding significant value beyond the bare 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 verb ('List') and resource ('blog posts'), and mentions pagination which adds specificity. However, it doesn't explicitly differentiate from sibling tools like 'fetch' or 'search', which might have overlapping functionality.
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 versus the sibling tools 'fetch' or 'search'. The description implies usage for listing posts with pagination but doesn't specify alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search blog posts using semantic search.
Args: query: Search query text limit: Maximum number of results to return (default: 10)
Returns: List of search results with relevance scores
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| limit | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
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 mentions semantic search and returns relevance scores, but fails to describe key traits like whether this is a read-only operation, potential rate limits, authentication needs, or how results are ordered. This leaves significant gaps in understanding the tool's behavior.
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 well-structured and front-loaded with the core purpose, followed by clear sections for Args and Returns. Every sentence adds value without redundancy, making it efficient and easy to parse for an AI agent.
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?
Given the tool's moderate complexity (2 parameters, semantic search), no annotations, and an output schema present (which handles return values), the description is reasonably complete. It covers the purpose, parameters, and return type, though it lacks behavioral context like error handling or performance considerations, which holds it back from 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 description coverage is 0%, so the description must compensate. It adds meaningful context for both parameters: 'query' is described as 'Search query text' and 'limit' as 'Maximum number of results to return (default: 10),' which clarifies their purposes beyond the bare schema. However, it doesn't detail constraints like query length or limit ranges.
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 as 'Search blog posts using semantic search,' which is a specific verb+resource combination. However, it doesn't explicitly differentiate this semantic search capability from potential sibling tools like 'fetch' or 'list_posts,' which might offer different search methods or scopes.
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 'fetch' or 'list_posts.' It lacks any context about prerequisites, such as whether blog posts need to be indexed or if authentication is required, leaving the agent with no usage differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose: fetch retrieves a specific post by identifier, list_posts provides paginated listings with sorting, and search performs semantic queries. There is no overlap in functionality, and an agent can easily differentiate between them based on their descriptions.
The naming is mostly consistent with a verb-based pattern (fetch, list_posts, search), but list_posts uses snake_case while the others are single words, creating a minor deviation. However, all names are clear and readable, with no chaotic mixing of conventions.
With 3 tools, this server is well-scoped for a blog-focused domain. Each tool serves a distinct and essential function (retrieval, listing, and searching), making the count appropriate and efficient for the intended purpose without being overly sparse or bloated.
The tools cover read operations (fetch, list, search) effectively, but there are notable gaps for a full blog management system, such as create, update, or delete operations. While the read surface is complete, the lack of write capabilities limits the server's coverage for broader agent workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Versioned documentation registry and semantic search for AI tools and coding assistants.
Search your knowledge bases from any AI assistant using hybrid RAG.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Search indexed websites, read raw page markdown, and score AI visibility for any site.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/philipithomas/ghost-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
