PostMCP
An MCP server for managing AI-generated social news posts in Firebase Firestore, enabling CRUD operations on posts with categories and tags.
README
PostMCP
An MCP (Model Context Protocol) server for managing AI-generated social news
posts in Firebase Firestore (AiPosts collection).
Quick Start
# Install dependencies
python3 -m venv .venv && .venv/bin/pip install -e ".[dev]"
# Configure environment
cp .env.example .env
# Edit .env with your Firebase project details
# Run the server
python -m postmcp
.envis optional. If you only launch PostMCP through an MCP client (Claude Desktop, Hermes Agent), pass the env vars in the client config instead..envis only needed when runningpython -m postmcpdirectly in the terminal (e.g., for testing).
Configuration
| Variable | Description |
|---|---|
FIREBASE_CLIENT_EMAIL |
Firebase service account email |
FIREBASE_PRIVATE_KEY |
Firebase service account private key |
FIREBASE_PROJECT_ID |
Firebase project ID |
POSTS_COLLECTION |
Firestore collection name (default: AiPosts) |
LOG_LEVEL |
Logging level (default: INFO) |
Connect from Claude Desktop
Add to your claude_desktop_config.json (see examples/claude_desktop_config.json):
{
"mcpServers": {
"postmcp": {
"command": "/ABSOLUTE/PATH/TO/PostMCP/.venv/bin/python",
"args": ["-m", "postmcp"],
"env": {
"FIREBASE_CLIENT_EMAIL": "your-service-account@your-project.iam.gserviceaccount.com",
"FIREBASE_PRIVATE_KEY": "-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----",
"FIREBASE_PROJECT_ID": "your-project-id"
}
}
}
}
Connect from Hermes Agent
Add to your ~/.hermes/config.yaml (see examples/hermes_config.yaml):
mcp_servers:
postmcp:
command: "/ABSOLUTE/PATH/TO/PostMCP/.venv/bin/python"
args: ["-m", "postmcp"]
env:
FIREBASE_CLIENT_EMAIL: "your-service-account@..."
FIREBASE_PRIVATE_KEY: "-----BEGIN PRIVATE KEY-----\n..."
FIREBASE_PROJECT_ID: "your-project-id"
Tools
create_post_tool— Create a new post with title, content, description, slug, images, categories, tagsget_post_tool— Get a post by IDlist_posts_tool— List posts filtered by category or tagupdate_post_tool— Update any field on a postdelete_post_tool— Delete a post by ID
Firestore Document Schema
AiPosts/{doc_id}
├── title: string
├── content: string (HTML)
├── description: string
├── slug: string
├── main_img: string (URL)
├── main_img_path: string (storage path)
├── category_ids: string[]
├── tags: string[]
├── views30: number
├── published: boolean
└── created_at: string (ISO 8601)
See AGENTS.md for full tool documentation for AI agents using this server.
See CLAUDE.md for development conventions.
Project Structure
src/postmcp/
├── server.py Entry point and MCP registration
├── config.py Configuration from env vars
├── types.py Pydantic models
├── tools/ MCP tool implementations
├── resources/ MCP resource providers
├── prompts/ MCP prompt templates
├── services/ Business logic layer
└── utils/ Logging, errors
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.