LlamaIndex MCP demos
This repo demonstrates both how to create an MCP server using LlamaCloud and how to use LlamaIndex as an MCP client.
LlamaCloud as an MCP server
To provide a local MCP server that can be used by a client like Claude Desktop, you can use
mcp-server.py. You can use this to provide a tool that will use RAG to provide Claude with up-to-the-second private information that it can use to answer questions. You can provide as many of these tools as you want.Set up your LlamaCloud index
- Get a LlamaCloud account
- Create a new index with any data source you want. In our case we used Google Drive and provided a subset of the LlamaIndex documentation as a source. You could also upload documents directly to the index if you just want to test it out.
- Get an API key from the LlamaCloud UI
Set up your MCP server
- Clone this repository
- Create a
.envfile and add two environment variables:
Now let's look at the code. First you instantiate an MCP server:
Then you define your tool using the
@mcp.tool() decorator:Here our tool is called
llama_index_documentation; it instantiates a LlamaCloud index called mcp-demo-2 and then uses it as a query engine to answer the query, including some extra instructions in the prompt. You'll get instructions on how to set up your LlamaCloud index in the next section.Finally, you run the server:
Note the
stdio transport, used for communicating to Claude Desktop.Configure Claude Desktop
- Install Claude Desktop
- In the menu bar choose
Claude->Settings->Developer->Edit Config. This will show up a config file that you can edit in your preferred text editor.
- You'll want your config to look something like this (make sure to replace
$YOURPATHwith the path to the repository):
Make sure to restart Claude Desktop after configuring the file.
Now you're ready to query! You should see a tool icon with your server listed underneath the query box in Claude Desktop, like this:
LlamaIndex as an MCP client
LlamaIndex also has an MCP client integration, meaning you can turn any MCP server into a set of tools that can be used by an agent. You can see this in
mcp-client.py, where we use the BasicMCPClient to connect to our local MCP server.For simplicity of demo, we are using the same MCP server we just set up above. Ordinarily, you would not use MCP to connect LlamaCloud to a LlamaIndex agent, you would use QueryEngineTool and pass it directly to the agent.
Set up your MCP server
To provide a local MCP server that can be used by an HTTP client, we need to slightly modify
mcp-server.py to use the run_sse_async method instead of run. You can find this in mcp-http-server.py.Get your tools from the MCP server
Create an agent and ask a question
You're all set! You can now use the agent to answer questions from your LlamaCloud index.
LlamaIndex MCP demos
This repo demonstrates both how to create an MCP server using LlamaCloud and how to use LlamaIndex as an MCP client.
LlamaCloud as an MCP server
To provide a local MCP server that can be used by a client like Claude Desktop, you can use
mcp-server.py. You can use this to provide a tool that will use RAG to provide Claude with up-to-the-second private information that it can use to answer questions. You can provide as many of these tools as you want.Set up your LlamaCloud index
- Get a LlamaCloud account
- Create a new index with any data source you want. In our case we used Google Drive and provided a subset of the LlamaIndex documentation as a source. You could also upload documents directly to the index if you just want to test it out.
- Get an API key from the LlamaCloud UI
Set up your MCP server
- Clone this repository
- Create a
.envfile and add two environment variables:
Now let's look at the code. First you instantiate an MCP server:
Then you define your tool using the
@mcp.tool() decorator:Here our tool is called
llama_index_documentation; it instantiates a LlamaCloud index called mcp-demo-2 and then uses it as a query engine to answer the query, including some extra instructions in the prompt. You'll get instructions on how to set up your LlamaCloud index in the next section.Finally, you run the server:
Note the
stdio transport, used for communicating to Claude Desktop.Configure Claude Desktop
- Install Claude Desktop
- In the menu bar choose
Claude->Settings->Developer->Edit Config. This will show up a config file that you can edit in your preferred text editor.
- You'll want your config to look something like this (make sure to replace
$YOURPATHwith the path to the repository):
Make sure to restart Claude Desktop after configuring the file.
Now you're ready to query! You should see a tool icon with your server listed underneath the query box in Claude Desktop, like this:
LlamaIndex as an MCP client
LlamaIndex also has an MCP client integration, meaning you can turn any MCP server into a set of tools that can be used by an agent. You can see this in
mcp-client.py, where we use the BasicMCPClient to connect to our local MCP server.For simplicity of demo, we are using the same MCP server we just set up above. Ordinarily, you would not use MCP to connect LlamaCloud to a LlamaIndex agent, you would use QueryEngineTool and pass it directly to the agent.
Set up your MCP server
To provide a local MCP server that can be used by an HTTP client, we need to slightly modify
mcp-server.py to use the run_sse_async method instead of run. You can find this in mcp-http-server.py.Get your tools from the MCP server
Create an agent and ask a question
You're all set! You can now use the agent to answer questions from your LlamaCloud index.