LlamaIndex Setup

Connect a LlamaIndex agent to graph8’s MCP server. LlamaIndex’s llama-index-tools-mcp package wraps MCP tools as native LlamaIndex FunctionTools your agents can use.

Prerequisites

• Python 3.10+
• llama-index, llama-index-tools-mcp, llama-index-llms-anthropic (or your model provider)

pip install llama-index llama-index-tools-mcp llama-index-llms-anthropic

Hosted MCP (remote OAuth)

import asyncio
import os

from llama_index.core.agent import ReActAgent
from llama_index.llms.anthropic import Anthropic
from llama_index.tools.mcp import McpToolSpec, BasicMCPClient


async def main() -> None:
    client = BasicMCPClient("https://be.graph8.com/mcp/")
    tool_spec = McpToolSpec(client=client)
    tools = await tool_spec.to_tool_list_async()

    llm = Anthropic(
        model="claude-sonnet-4",
        api_key=os.environ["ANTHROPIC_API_KEY"],
    )
    agent = ReActAgent.from_tools(tools, llm=llm, verbose=True)

    response = await agent.achat(
        "Use g8_find_contacts to preview 10 VP Sales at fintech startups "
        "in New York. Return name, company, title."
    )
    print(response)


if __name__ == "__main__":
    asyncio.run(main())

The first call opens a browser for OAuth. Subsequent calls reuse the cached token.

Self-hosted MCP (stdio)

For headless or CI use, run the MCP server locally with stdio and a personal API key.

export G8_API_KEY="g8_..."

import asyncio
import os

from llama_index.core.agent import ReActAgent
from llama_index.llms.anthropic import Anthropic
from llama_index.tools.mcp import McpToolSpec, BasicMCPClient


async def main() -> None:
    client = BasicMCPClient(
        command_or_url="uvx",
        args=["g8-mcp-server"],
        env={
            "G8_API_KEY": os.environ["G8_API_KEY"],
            "G8_MCP_MODE": "gtm",
        },
    )
    tool_spec = McpToolSpec(client=client)
    tools = await tool_spec.to_tool_list_async()

    llm = Anthropic(model="claude-sonnet-4")
    agent = ReActAgent.from_tools(tools, llm=llm, verbose=True)

    response = await agent.achat("Search my CRM for contacts at Stripe.")
    print(response)


if __name__ == "__main__":
    asyncio.run(main())

Worked example: SaaS prospecting workflow

prompt = (
    "Find 25 VP Engineering at Series B SaaS in the US using g8_find_contacts. "
    "Pick the 10 with the highest signal score. Ask me to confirm before "
    "saving them to a new list via g8_build_contact_list."
)
response = await agent.achat(prompt)

Credit-charging tools require explicit confirmation. The MCP server returns a structured prompt the agent surfaces to the user before any save.

Related

• MCP Server overview
• MCP Tool Reference
• MCP FAQ
• End-to-end examples