wehub-resource-sync
a0c8464e58
Build Package / build (ubuntu-latest) (push) Failing after 1s
CodeQL / Analyze (python) (push) Failing after 1s
Core Typecheck / core-typecheck (push) Failing after 1s
Linting / lint (push) Failing after 1s
llama-dev tests / test-llama-dev (push) Failing after 1s
Publish Sub-Package to PyPI if Needed / publish_subpackage_if_needed (push) Has been skipped
Sync Docs to Developer Hub / sync-docs (push) Failing after 0s
Build Package / build (windows-latest) (push) Has been cancelled
220 lines
7.1 KiB
Plaintext
220 lines
7.1 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Use LlamaIndex agent tools as MCP tools\n",
|
|
"\n",
|
|
"We have dozens of agent tools in [LlamaHub](https://llamahub.ai/?tab=tools) and they can all be instantly used as MCP tools! This notebook shows how exactly that's done, using the [Notion Tool](https://llamahub.ai/l/tools/llama-index-tools-notion?from=tools) as an example."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"First we install our tool, and our MCP server:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"!pip install llama-index-tools-notion mcp fastmcp"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Bring in our dependencies:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"MCP fastMCP server dependencies imported successfully!\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# Import dependencies for Model Context Protocol (MCP) fastMCP server\n",
|
|
"from typing import Any, Dict, List, Optional\n",
|
|
"from fastmcp import FastMCP\n",
|
|
"\n",
|
|
"print(\"MCP fastMCP server dependencies imported successfully!\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Instantiate our tools using an API key:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# Import and configure LlamaIndex Notion Tool Spec\n",
|
|
"from llama_index.tools.notion import NotionToolSpec\n",
|
|
"\n",
|
|
"notion_token = \"xxxx\"\n",
|
|
"tool_spec = NotionToolSpec(integration_token=notion_token)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Let's see what tools are available:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Tool 1: load_data\n",
|
|
"Tool 2: search_data\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"tools = tool_spec.to_tool_list()\n",
|
|
"\n",
|
|
"for i, tool in enumerate(tools):\n",
|
|
" print(f\"Tool {i+1}: {tool.metadata.name}\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Now we create and configure the fastMCP server, and register each tool:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"MCP Server configured with tools\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"mcp_server = FastMCP(\"MCP Agent Tools Server\")\n",
|
|
"\n",
|
|
"# Register the tools from the Notion ToolSpec\n",
|
|
"for tool in tools:\n",
|
|
" mcp_server.tool(\n",
|
|
" name=tool.metadata.name, description=tool.metadata.description\n",
|
|
" )(tool.real_fn)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"Now we can run our MCP server complete with our tools!"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #7fbfbf; text-decoration-color: #7fbfbf\">[06/27/25 16:27:47] </span><span style=\"color: #000080; text-decoration-color: #000080\">INFO </span> Starting MCP server <span style=\"color: #008000; text-decoration-color: #008000\">'MCP Agent Tools Server'</span> with transport <a href=\"file:///Users/seldo/projects/llamaindex/llama_index/docs/.venv/lib/python3.13/site-packages/fastmcp/server/server.py\" target=\"_blank\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">server.py</span></a><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">:</span><a href=\"file:///Users/seldo/projects/llamaindex/llama_index/docs/.venv/lib/python3.13/site-packages/fastmcp/server/server.py#1358\" target=\"_blank\"><span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\">1358</span></a>\n",
|
|
"<span style=\"color: #7fbfbf; text-decoration-color: #7fbfbf\"> </span> <span style=\"color: #008000; text-decoration-color: #008000\">'streamable-http'</span> on <span style=\"color: #0000ff; text-decoration-color: #0000ff; text-decoration: underline\">http://127.0.0.1:8000/mcp/</span> <span style=\"color: #7f7f7f; text-decoration-color: #7f7f7f\"> </span>\n",
|
|
"</pre>\n"
|
|
],
|
|
"text/plain": [
|
|
"\u001b[2;36m[06/27/25 16:27:47]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO \u001b[0m Starting MCP server \u001b[32m'MCP Agent Tools Server'\u001b[0m with transport \u001b]8;id=182776;file:///Users/seldo/projects/llamaindex/llama_index/docs/.venv/lib/python3.13/site-packages/fastmcp/server/server.py\u001b\\\u001b[2mserver.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=402767;file:///Users/seldo/projects/llamaindex/llama_index/docs/.venv/lib/python3.13/site-packages/fastmcp/server/server.py#1358\u001b\\\u001b[2m1358\u001b[0m\u001b]8;;\u001b\\\n",
|
|
"\u001b[2;36m \u001b[0m \u001b[32m'streamable-http'\u001b[0m on \u001b[4;94mhttp://127.0.0.1:8000/mcp/\u001b[0m \u001b[2m \u001b[0m\n"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"INFO: Started server process [24668]\n",
|
|
"INFO: Waiting for application startup.\n",
|
|
"INFO: Application startup complete.\n",
|
|
"INFO: Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"INFO: 127.0.0.1:54201 - \"POST /mcp/ HTTP/1.1\" 200 OK\n",
|
|
"INFO: 127.0.0.1:54201 - \"POST /mcp/ HTTP/1.1\" 202 Accepted\n",
|
|
"INFO: 127.0.0.1:54203 - \"GET /mcp/ HTTP/1.1\" 200 OK\n",
|
|
"INFO: 127.0.0.1:54209 - \"POST /mcp/ HTTP/1.1\" 200 OK\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"INFO: Shutting down\n",
|
|
"ERROR: ASGI callable returned without completing response.\n",
|
|
"ERROR: Cancel 0 running task(s), timeout graceful shutdown exceeded\n",
|
|
"INFO: Waiting for application shutdown.\n",
|
|
"INFO: Application shutdown complete.\n",
|
|
"INFO: Finished server process [24668]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"await mcp_server.run_async(transport=\"streamable-http\")"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": ".venv",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|