MCP Search & Fetch
Provides tools to perform web searches using Ollama's hosted search API and fetch content from web pages.
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., "@MCP Search & Fetchsearch for latest AI research papers"
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.
MCP Search & Fetch
An MCP server exposing Ollama's web search and web fetch capabilities as tools.
Features
web_search: Perform web searches using Ollama's hosted search API
web_fetch: Fetch content from web pages
Requirements
Ollama API key (get one from ollama.com)
Installation
pip install mcp-search-and-fetch
# Export your API key
OLLAMA_API_KEY=your_api_key_here
# Run the MCP server
mcp-search-and-fetchClone from Repository
# Clone the repository
git clone https://github.com/lkiesow/mcp-search-and-fetch.git
cd mcp-search-and-fetch
# Install dependencies
pip install -r requirements.txt
export OLLAMA_API_KEY=your_api_key_here
python mcp_search_and_fetch.pyDocker
To run the pre-built containers:
docker run -p 8000:8000 --env-file .env ghcr.io/lkiesow/mcp-search-and-fetch:latestOr, if you want to build your own containers:
docker build -t mcp-search-fetch .
docker run -p 8000:8000 --env-file .env mcp-search-fetchDocker Compose
An example ´docker-compose.yml` with Caddy as reverse proxy:
services:
search-and-fetch:
image: ghcr.io/lkiesow/mcp-search-and-fetch:1.0.1
container_name: search-and-fetch
restart: always
environment:
OLLAMA_API_KEY: secret.ollama.api.key
networks:
- mcp
caddy:
image: docker.io/library/caddy:2.10.2
container_name: caddy
restart: always
environment:
CADDY_DOMAIN: search-and-fetch.example.com
CADDY_API_KEY: secret.mcp.api.key
volumes:
- /opt/mcp-search-and-fetch/caddy:/etc/caddy
- caddy_data:/data
- caddy_config:/config
ports:
- 80:80
- 443:443
- 443:443/udp
networks:
- mcp
volumes:
caddy_data:
caddy_config:
networks:
mcp:And an example Caddyfile in the caddy directory like this:
{$CADDY_DOMAIN} {
@no_auth {
not header Authorization "Bearer {$CADDY_API_KEY}"
}
respond @no_auth "Unauthorized" 401
reverse_proxy /* search-and-fetch:8000
}Usage
Local (stdio)
python mcp_search_and_fetch.pyHTTP Server (Streamable HTTP)
# Set port and host in .env
export MCP_SERVER_PORT=8000
export MCP_SERVER_HOST=0.0.0.0
python mcp_search_and_fetch.pyConfiguration
You can either set environment variables or provide a .env file.
Take a look at the .env.sample for an example.
Environment Variable | Required | Default | Description |
| Yes | - | Your Ollama API key |
| No | - | Run HTTP server on specified port |
| No | 127.0.0.1 | Host to bind to |
Tools
web_search(query, max_results=3)
Performs a web search and returns results as JSON.
web_fetch(url)
Fetches content from a URL and returns it as JSON.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lkiesow/mcp-search-and-fetch'
If you have feedback or need assistance with the MCP directory API, please join our Discord server