MCP Server for Feedly API
Description
# MCP Server for Feedly API This repository contains a minimal [python-sdk](https://github.com/modelcontextprotocol/python-sdk) server that exposes selected Feedly API endpoints as MCP tools. The server provides the following tools: - `feedly.search` - `feedly.collect` -…
About
# MCP Server for Feedly API This repository contains a minimal [python-sdk](https://github.com/modelcontextprotocol/python-sdk) server that exposes selected Feedly API endpoints as MCP tools. The server provides the following tools: - `feedly.search` - `feedly.collect` - `feedly.entity_lookup` - `feedly.autocomplete`…
Details
- Author
- hafnium49
- Downloads
- 340
- Categories
- Developer Tools
Jump to
- Exposes four Feedly API endpoints as MCP tools.
- Requires a Feedly authentication token.
- Runs over HTTP on port 8080.
- Built with the Python MCP SDK and httpx.
- Minimal setup with pip install and environment variable.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Server for Feedly APICommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Create a Python virtual environment, install dependencies (mcp, httpx, python-dotenv), export your FEEDLY_TOKEN, and run python server.py. The server listens on HTTP port 8080 and provides four tools: feedly.search, feedly.collect, feedly.entity_lookup, and feedly.autocomplete.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server for feedly api": {
"mcp_server_feedly": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}
}McpServers
{
"mcp_server_feedly": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}MCP Server for Feedly API
This repository contains a minimal python-sdk server that exposes selected Feedly API endpoints as MCP tools. The server provides the following tools:
- feedly.search
- feedly.collect
- feedly.entity_lookup
- feedly.autocomplete
These tools make it possible for MCP-aware language models to search and retrieve articles or NLP entity information from Feedly.
Setup
1. Create and activate a virtual environment and install dependencies:
python -m venv .venv
source .venv/bin/activate
pip install mcp httpx python-dotenv
2. Export your Feedly authentication token so the server can call the Feedly API:
export FEEDLY_TOKEN=YOUR_TOKEN_HERE
Running the server
Run the server over HTTP on port 8080:
python server.py
The MCP discovery document will be available at http://localhost:8080/.well-known/mcp/.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
