How to Use the Mapillary MCP in LlamaIndex

Q: Can LlamaIndex search Mapillary sequences geographically?

Yes. Your agent calls searchsequences with a bounding box to find paths, then indexes the resulting metadata into your document store.

Q: How do I get specific metadata for a detection?

Use getdetectionvalue to retrieve the type, GPS coordinates, and image association for any detected object.

Index Mapillary street-level imagery and spatial detections directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapillary MCP to LlamaIndex

Create your Vinkius account to connect Mapillary 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 Mapillary with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index traffic sign detections with LlamaIndex

`get_image_detections` extracts object detections, confidence scores, and geometries from specific image IDs. The tool provides raw structured data that your pipeline converts into searchable document nodes. LlamaIndex indexes these detections into your vector store to enable natural language queries over physical assets. You can ask your agent where specific speed limit signs are located without querying raw databases.

Ground agent responses in actual map features

`get_map_features` retrieves verified physical assets and their coordinate details from the Mapillary database. The tool gives your engine direct access to ground-truth infrastructure data. This MCP Server feeds these features directly into your index as semantic nodes. Your agent queries this index to answer complex spatial questions with zero hallucination.

Track infrastructure changes over time

`get_sequence` retrieves the complete chronological list of images and creation dates for a specific driving pass. The tool lets you isolate how a specific street looked during different capture sessions. LlamaIndex parses this sequence metadata to build temporal indices. Your agent uses these indices to compare older and newer images, flagging missing assets or new construction automatically.

Setup guide

Set up Mapillary 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 Mapillary 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 Mapillary tools.",
)
response = await agent.run("List recent Mapillary 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 Mapillary. 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 Mapillary 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 Mapillary MCP in LlamaIndex

Initialize the MCP client, wrap it with McpToolSpec, and call to_tool_list_async. Pass these tools to your LlamaIndex agent to let it query imagery on demand.

Yes. Your agent calls search_sequences with a bounding box to find paths, then indexes the resulting metadata into your document store.

It provides live, coordinates-grounded street data instead of static documents. Your RAG pipeline queries actual physical asset locations directly from the Mapillary API.

Use get_detection_value to retrieve the type, GPS coordinates, and image association for any detected object.

Your GPS coordinates, detection values, and image geometries remain local to your LlamaIndex environment. The server uses ephemeral, zero-trust sandboxing to process requests without logging your 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