How to Use the Geoapify MCP in LlamaIndex

Q: How do I load Geoapify tools into LlamaIndex?

Install llama-index-tools-mcp. Set up a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call totoollistasync() to feed the tools to your agent.

Q: Can LlamaIndex store the output of Geoapify route calculations?

Yes. You configure the agent to write the JSON output from calculateroute directly into a Document object. Your pipeline then embeds and indexes that route data for future semantic queries.

Q: How does LlamaIndex handle the GeoJSON output from Geoapify?

The agent receives raw GeoJSON from tools like getboundariesconsistsof. You typically prompt the agent to summarize the polygon coordinates into a bounding box or center point before embedding it into the vector store.

Q: Can I limit which Geoapify tools my LlamaIndex agent accesses?

Yes. When initializing the tool spec, use the allowedtools filter. You might expose geocodesearch to public users while restricting routeplanner to internal logistics queries.

Q: What happens to address data sent to Geoapify via LlamaIndex?

Any raw street address passed to geocodeautocomplete routes through an ephemeral Vinkius sandbox. The connection uses strict TLS, and the memory state wipes completely once the coordinates return, preventing any long-term storage of user queries.

Index live geospatial data into your LlamaIndex RAG applications using the Geoapify integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geoapify MCP to LlamaIndex

Create your Vinkius account to connect Geoapify to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Geoapify with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Embed location data into LlamaIndex

Static documents lack geographic context. When your query engine hits a location entity, it triggers `get_place_details` via the MCP server. The engine retrieves fresh opening hours, contact info, and building geometry, then injects that structured data directly into the active context window. This changes how your RAG pipeline handles spatial queries. Instead of guessing based on outdated text, the system uses `search_places` to pull live POI data. It indexes these results on the fly, allowing users to ask natural language questions about current neighborhood amenities.

Spatial reasoning for your knowledge base

Text search fails when users ask questions about jurisdictions. By giving your `FunctionAgent` access to `get_boundaries_part_of`, the system instantly resolves which administrative or postal boundary contains a specific coordinate. The agent grounds its answers in actual political geography. You combine this with `geometry_operation`. If a user asks whether two delivery zones overlap, the agent pulls the GeoJSON from your vector store and runs an intersection check. The final answer relies on hard mathematical proof rather than semantic similarity.

Index dynamic travel times from Geoapify MCP Server

Distance matters less than actual travel time. When users query your RAG application about logistics, the agent calls `calculate_route_matrix` to generate real travel times between multiple indexed locations. It stores these results temporarily to answer complex routing questions. For broader accessibility queries, the agent uses `calculate_isoline`. It generates a polygon representing a 15-minute drive time and checks which of your indexed facilities fall inside that boundary. The user gets a precise, visually accurate response based on live road networks.

Setup guide

Set up Geoapify MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Geoapify MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Geoapify tools.",
)
response = await agent.run("List recent Geoapify data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Geoapify. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Geoapify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Geoapify MCP in LlamaIndex

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient` with your Vinkius URL, wrap it in an `McpToolSpec`, and call `to_tool_list_async()` to feed the tools to your agent.

Yes. You configure the agent to write the JSON output from `calculate_route` directly into a `Document` object. Your pipeline then embeds and indexes that route data for future semantic queries.

The agent receives raw GeoJSON from tools like `get_boundaries_consists_of`. You typically prompt the agent to summarize the polygon coordinates into a bounding box or center point before embedding it into the vector store.

Yes. When initializing the tool spec, use the `allowed_tools` filter. You might expose `geocode_search` to public users while restricting `route_planner` to internal logistics queries.

Any raw street address passed to `geocode_autocomplete` routes through an ephemeral Vinkius sandbox. The connection uses strict TLS, and the memory state wipes completely once the coordinates return, preventing any long-term storage of user queries.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript