Provides tools for web search and webpage content extraction using the Tavily API, enabling AI agents to perform real-time web searches and fetch readable text from URLs.
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., "@Tavily Search MCP search for the latest breakthroughs in artificial intelligence"
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.
Tavily Search MCP is an MCP service based on Streamable HTTP that wraps Tavily's web search and webpage content extraction capabilities into MCP tools.
web_search: Performs a web search based on query keywords.
web_fetch: Extracts readable text content from a webpage URL.
Related MCP server: tavily-mcp
Python 3.11+
Tavily API Key
An MCP client that supports streamable_http
First create and activate your own Python virtual environment, then install the dependencies and the current project:
python -m pip install -r requirements.txt
python -m pip install -e .Copy the environment variable template:
cp .env.example .envFill in the configuration in .env:
TAVILY_API_KEY=tvly-your-api-key
MCP_SERVER_HOST=127.0.0.1
MCP_SERVER_PORT=21029
MCP_SERVER_PATH=/mcp
MCP_ALLOWED_HOSTS=127.0.0.1,127.0.0.1:21029,localhost,localhost:21029
MCP_ALLOWED_ORIGINS=*If deploying to a server, set MCP_SERVER_HOST to 0.0.0.0 and add your public domain or access hostname to MCP_ALLOWED_HOSTS.
python -m tavily_search_mcp.serverDefault local MCP address:
http://127.0.0.1:21029/mcpHealth check:
curl http://127.0.0.1:21029/healthList MCP tools:
python -m tavily_search_mcp.client --url http://127.0.0.1:21029/mcp list-toolsCall web search:
python -m tavily_search_mcp.client --url http://127.0.0.1:21029/mcp web-search "Tavily Python SDK" --max-results 2Call webpage content extraction:
python -m tavily_search_mcp.client --url http://127.0.0.1:21029/mcp web-fetch "https://docs.tavily.com/"Local service example:
{
"mcpServers": {
"tavily-search": {
"type": "streamable_http",
"url": "http://127.0.0.1:21029/mcp",
"headers": {}
}
}
}Remote service example:
{
"mcpServers": {
"tavily-search": {
"type": "streamable_http",
"url": "https://your-domain.example/mcp",
"headers": {}
}
}
}You can use the deployment script in the repository to upload and start the service with your own SSH key:
.\scripts\deploy_remote.ps1 -HostName "your-server.example" -User "ubuntu" -IdentityFile "<path-to-private-key>"This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Scrape, crawl and search the web for AI agents via MCP.
