# How to integrate Geoapify MCP with LlamaIndex

```json
{
  "title": "How to integrate Geoapify MCP with LlamaIndex",
  "toolkit": "Geoapify",
  "toolkit_slug": "geoapify",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/geoapify/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/geoapify/framework/llama-index.md",
  "updated_at": "2026-05-12T10:12:46.064Z"
}
```

## Introduction

This guide walks you through connecting Geoapify to LlamaIndex using the Composio tool router. By the end, you'll have a working Geoapify agent that can find latitude and longitude for an address, suggest address completions as i type, show reachable area within 10 minutes driving through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Geoapify account through Composio's Geoapify MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Geoapify with

- [OpenAI Agents SDK](https://composio.dev/toolkits/geoapify/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/geoapify/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/geoapify/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/geoapify/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/geoapify/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/geoapify/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/geoapify/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/geoapify/framework/cli)
- [Google ADK](https://composio.dev/toolkits/geoapify/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/geoapify/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/geoapify/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/geoapify/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/geoapify/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Geoapify
- Connect LlamaIndex to the Geoapify MCP server
- Build a Geoapify-powered agent using LlamaIndex
- Interact with Geoapify through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## What is the Geoapify MCP server, and what's possible with it?

The Geoapify MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Geoapify account. It provides structured and secure access to powerful location-based services, so your agent can perform actions like geocoding addresses, generating routes, fetching map tiles, and analyzing geographic data on your behalf.
- Address autocomplete and geocoding: Instantly convert partial or full addresses into geographic coordinates, or fetch smart suggestions to speed up location entry.
- Routing and reachability analysis: Generate routes, calculate reachable areas (isochrones/isodistances), and let your agent determine how far you can travel from a point within a set time or distance.
- IP-based geolocation: Look up the approximate location of any IP address to enrich user data, personalize experiences, or detect regions automatically.
- Map visualization and customization: Fetch custom-styled map tiles and create personalized marker icons for fully tailored map displays in your applications or reports.
- Boundary and geometry operations: Retrieve administrative boundaries for any place or coordinate, and perform advanced geometric operations like combining or intersecting polygons to analyze spatial relationships.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `GEOAPIFY_ADDRESS_AUTOCOMPLETE` | Address Autocomplete | Tool to fetch address suggestions based on partial input. Use when you need to get predictive suggestions from incomplete address text. |
| `GEOAPIFY_BATCH_REQUESTS` | Batch Requests | Create or retrieve asynchronous batch processing jobs for geocoding, reverse geocoding, routing, or isoline APIs. Use cases: - Batch geocode up to 1000 addresses at once (forward geocoding) - Batch reverse geocode multiple coordinates - Process multiple routing or isoline requests in one batch Workflow: 1. Create a job by providing 'api' and 'inputs' (returns job ID and status 'pending') 2. Poll the job by providing 'id' until status changes from 'pending' to complete (results available) |
| `GEOAPIFY_BOUNDARIES` | Get Boundaries Containing Location | Retrieve all administrative boundaries that contain a given location. Returns hierarchical boundaries (suburb, city, county, state, country) as GeoJSON features. Use this to find what administrative areas a coordinate belongs to, get boundary polygons for mapping, or identify postal codes and political districts for a location. |
| `GEOAPIFY_CREATE_BATCH_FORWARD_GEOCODE_JOB` | Create Batch Forward Geocode Job | Tool to create a batch forward geocoding job for up to 1000 addresses. Use when you need to geocode multiple addresses asynchronously. Returns a job ID for retrieving results once processing is complete. |
| `GEOAPIFY_CREATE_BATCH_REVERSE_GEOCODE_JOB` | Create Batch Reverse Geocode Job | Tool to create a batch reverse geocoding job that converts multiple lat/lon coordinates into addresses asynchronously. Use when you need to reverse geocode multiple coordinates (up to 1000) in one request. Returns a job ID for retrieving results. |
| `GEOAPIFY_FORWARD_GEOCODING` | Forward Geocoding | Tool to convert an address into geographic coordinates. Use when you need latitude and longitude from an address. |
| `GEOAPIFY_GEOMETRY` | Geometry Operation | Tool to perform geometric operations on stored polygon geometries. Use when combining or intersecting multiple stored geometries. |
| `GEOAPIFY_GET_BATCH_FORWARD_GEOCODE_RESULTS` | Get Batch Forward Geocode Results | Tool to retrieve batch forward geocoding job results using the job ID. Use when you need to fetch geocoded addresses from a previously submitted batch job. Results available in JSON or CSV format. Job must be complete (status 200) to get results. |
| `GEOAPIFY_GET_BATCH_REVERSE_GEOCODE_RESULTS` | Get Batch Reverse Geocode Results | Tool to retrieve batch reverse geocoding job results. Use when you have a batch job ID from creating a batch reverse geocoding job and want to fetch the completed results. |
| `GEOAPIFY_GET_BOUNDARIES_CONSISTS_OF` | Get Child Boundaries (Consists Of) | Get boundaries that a specified location consists of. Returns child administrative divisions (states for country, districts for city). Useful for drilling down into sub-regions. |
| `GEOAPIFY_GET_MAP_STYLE` | Get Map Style JSON | Tool to retrieve vector map style JSON for MapLibre GL and Mapbox GL. Returns a Mapbox-compatible style specification for rendering vector tiles. |
| `GEOAPIFY_GET_STATIC_MAP` | Generate Static Map Image | Tool to generate static map images with customizable style, size, center, zoom, markers, and geometries. Use when you need a map image for display or printing. |
| `GEOAPIFY_IP_GEOLOCATION` | IP Geolocation | Lookup geographic location information for an IP address. Returns city-level location data including country, region, city, coordinates, and additional metadata like currency and language. If no IP is provided, returns location for the caller's IP address. |
| `GEOAPIFY_ISOLINE` | Generate isoline (isochrone/isodistance) | Tool to generate isochrone or isodistance isolines. Use when visualizing reachable areas from a point; use `id` to poll ongoing calculations. |
| `GEOAPIFY_LIST_POSTCODES` | List Postcodes | Tool to list postcodes within a specified area or boundary. Use when you need to retrieve multiple postcodes in a geographic region using filters like circle, rectangle, or place ID. |
| `GEOAPIFY_MAP_MATCHING` | Map Matching | Snap GPS traces to the road network for accurate route reconstruction. Use this tool to: - Correct GPS drift and inaccuracies in recorded tracks - Align vehicle/cycling/walking traces to actual roads - Get road names and properties along the matched route - Calculate accurate distance and travel time from GPS data |
| `GEOAPIFY_MAP_TILES` | Fetch Geoapify Map Tiles | Tool to fetch raster map tiles or style JSON from Geoapify. Use when rendering custom maps with specific styles. |
| `GEOAPIFY_MARKER_ICON` | Create Marker Icon | Generate custom map marker icons as PNG images. Creates customizable marker icons for use in mapping applications (Leaflet, MapLibre GL, Google Maps, etc.). Supports multiple styles (material, circle, plain), custom colors, icons from Material Design and Font Awesome libraries, or custom text/numbers. Example use cases: - Create a red location pin with a star icon - Generate numbered markers (1, 2, 3...) for route waypoints - Create custom-colored markers matching your brand |
| `GEOAPIFY_PLACE_DETAILS` | Place Details | Tool to retrieve detailed information about a specific place. Use when you have a place ID or coordinates and need comprehensive metadata. |
| `GEOAPIFY_PLACES` | Places Search | Search for points of interest (POIs) like restaurants, hotels, attractions, hospitals, etc. within a geographic area. Use this tool when you need to find places by category near a location. You must provide either a 'filter' (to search within a bounded area) or 'bias' (to rank results by proximity to a point). Common use cases: - Find restaurants near a location: categories=['catering.restaurant'], bias='proximity:lon,lat' - Search for hotels in a city area: categories=['accommodation.hotel'], filter='circle:lon,lat,5000' - Find wheelchair-accessible attractions: categories=['tourism.attraction'], conditions=['wheelchair'] |
| `GEOAPIFY_POSTCODE` | Postcode Search | Tool to retrieve postcode information for a location. Use when you need to fetch postcode details based on a given postcode or geographic coordinates. |
| `GEOAPIFY_REVERSE_GEOCODING` | Reverse Geocoding | Tool to reverse geocode coordinates into a structured address. Use when converting lat/lon to human-readable addresses. |
| `GEOAPIFY_ROUTE_MATRIX` | Route Matrix | Tool to compute travel time and distance matrices. Use when you need durations and distances between multiple origin and destination pairs. |
| `GEOAPIFY_ROUTE_PLANNER` | Route Planner | Optimize multi-agent routes for deliveries, pickups, and service jobs. Solves Vehicle Routing Problems (VRP) including: Travelling Salesman (TSP), Capacitated VRP, VRP with Time Windows, and Pickup-Delivery problems. Required: Either 'jobs' (one-way tasks) or 'shipments' (pickup-delivery pairs). Coordinates: Use [longitude, latitude] format (not lat/lon). |
| `GEOAPIFY_ROUTING` | Routing | Tool to calculate routes between multiple waypoints. Use when you need both distance, time, and turn-by-turn directions for two or more coordinates. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Geoapify MCP server is an implementation of the Model Context Protocol that connects your AI agent to Geoapify. It provides structured and secure access so your agent can perform Geoapify operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Geoapify account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Geoapify

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Geoapify access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, geoapify)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Geoapify tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["geoapify"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Geoapify actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Geoapify actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["geoapify"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Geoapify actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Geoapify
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Geoapify, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["geoapify"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Geoapify actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Geoapify actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["geoapify"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Geoapify actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Geoapify to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Geoapify tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Geoapify MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/geoapify/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/geoapify/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/geoapify/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/geoapify/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/geoapify/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/geoapify/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/geoapify/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/geoapify/framework/cli)
- [Google ADK](https://composio.dev/toolkits/geoapify/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/geoapify/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/geoapify/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/geoapify/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/geoapify/framework/crew-ai)

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Geoapify MCP?

With a standalone Geoapify MCP server, the agents and LLMs can only access a fixed set of Geoapify tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Geoapify and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Geoapify tools.

### Can I manage the permissions and scopes for Geoapify while using Tool Router?

Yes, absolutely. You can configure which Geoapify scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Geoapify data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)