# LlamaIndex Setup

> Connect LlamaIndex agents to graph8 via MCP using llama-index-tools-mcp

Source: https://docs.graph8.com/developers/llamaindex-setup/

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

> **Tip:**
> Try the developer tier free - 1,000 credits, no card required. [Get started](https://auth.graph8.com/en/signup).

## Prerequisites

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

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

## Hosted MCP (remote OAuth)

```python
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.

```bash
export G8_API_KEY="g8_..."
```

```python
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

```python
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](https://docs.graph8.com/developers/mcp/)
- [MCP Tool Reference](https://docs.graph8.com/developers/mcp-tools/)
- [MCP FAQ](https://docs.graph8.com/developers/mcp-faq/)
- [End-to-end examples](https://docs.graph8.com/developers/mcp-examples/)