How to integrate Here MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Here Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Here to CrewAI using the Composio tool router. By the end, you'll have a working Here agent that can find coffee shops near central park, get driving route for delivery truck, convert address to latitude and longitude, show hybrid map tile for times square through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Here account through Composio's Here MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Here connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Here
  • Build a conversational loop where your agent can execute Here operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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

The Here MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Here account. It provides structured and secure access to powerful location, mapping, and geocoding services, so your agent can perform actions like searching places, calculating routes, fetching map imagery, and converting addresses or coordinates on your behalf.

  • Smart place discovery and suggestions: Ask your agent to find points of interest, get autosuggested places based on partial queries, or discover addresses near a location.
  • Geocoding and reverse geocoding: Convert addresses to geographic coordinates or vice versa, enabling seamless location lookup and mapping in your workflows.
  • Map tile and imagery retrieval: Direct your agent to fetch satellite, base, or hybrid map tiles for specific locations, zoom levels, and formats for rich visual context.
  • Advanced routing and fleet planning: Have your agent calculate optimized routes with vehicle profiles, constraints, and even isolines for reachable areas based on time or distance.
  • Nearby search and contextual browsing: Let your agent browse or search for places around a given location, filtered by categories or names, to surface relevant local information.

Supported Tools & Triggers

Tools
Autosuggest PlacesTool to fetch possible completions for a partial search term.
Browse PlacesTool to search for places around a given location with optional filters.
Calculate Fleet Telematics RouteTool to calculate a route between waypoints with vehicle profile options.
Coordinates to Tile IndicesTool to convert geographic coordinates to Web Mercator XYZ tile indices.
Discover PlacesTool to discover places and addresses by free-form text near a location.
Geocode AddressTool to convert structured address data into geographic coordinates.
Get Aerial TileTool to retrieve a satellite/aerial map tile.
Get Base Map TileTool to retrieve a base map tile image without labels.
Get Hybrid Map TileTool to retrieve a hybrid (aerial + labels) map tile.
Get IsolinesTool to calculate isolines.
Get Label TileTool to retrieve a label overlay tile.
Get Line Overlay TileTool to retrieve a line overlay tile.
Get Map ImageTool to retrieve a static map image.
Get Base Map TileTool to retrieve a base map tile.
Compute Routing MatrixTool to compute a routing distance/time matrix.
Get Meta Info TileTool to retrieve metadata for a specific map tile.
Get POI TileTool to retrieve a point-of-interest overlay tile.
Get Terrain Map TileTool to retrieve a terrain map tile image.
Get Traffic FlowTool to retrieve real-time traffic flow data.
Get Traffic IncidentsTool to fetch real-time traffic incidents within a specified area.
Get Traffic TileTool to retrieve a traffic overlay tile.
Get Waypoint SequenceTool to optimize the visit order of multiple waypoints.
Daily Weather ForecastTool to provide daily weather forecasts (up to 7 days).
Get Weather ObservationTool to retrieve current weather observation.
Hourly Weather ForecastTool to fetch hourly weather forecasts.
Lookup Place DetailsTool to look up detailed information for a place by its HERE ID.
Reverse Geocode CoordinatesTool to convert geographic coordinates into a human-readable address.
Weather AlertsTool to retrieve severe weather alerts for specified locations or routes.
Get Astronomy ForecastTool to fetch astronomical data (sunrise, sunset) for a specific location.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Here connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Here via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Here MCP URL

Create a Composio Tool Router session for Here

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["here"],
)
url = session.mcp.url
What's happening:
  • You create a Here only session through Composio
  • Composio returns an MCP HTTP URL that exposes Here tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Here Assistant",
    goal="Help users interact with Here through natural language commands",
    backstory=(
        "You are an expert assistant with access to Here tools. "
        "You can perform various Here operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Here MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Here operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Here related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_here_agent.py

Complete Code

Here's the complete code to get you started with Here and CrewAI:

python
# file: crewai_here_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Here session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["here"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Here assistant agent
    toolkit_agent = Agent(
        role="Here Assistant",
        goal="Help users interact with Here through natural language commands",
        backstory=(
            "You are an expert assistant with access to Here tools. "
            "You can perform various Here operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Here operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Here related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Here through Composio's Tool Router. The agent can perform Here operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Here MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Here MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Here MCP with Claude Agent SDK

Google ADK

Google ADK

Use Here MCP with Google ADK

LangChain

LangChain

Use Here MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Here MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Here MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Here MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Here MCP?

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

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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 Here tools.

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

Yes, absolutely. You can configure which Here 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 Here data and credentials are handled as safely as possible.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free