How to Use the Pelias Geocoder MCP in LangChain

Q: How do I pass Pelias Geocoder outputs to other tools in LangChain?

You map the output of tools like searchgeocode directly into your LangGraph state. The agent reads the resulting latitude and longitude, then uses those values as inputs for subsequent tools in your chain.

Feed clean coordinates from Pelias Geocoder straight into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pelias Geocoder MCP to LangChain

Create your Vinkius account to connect Pelias Geocoder to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Pelias Geocoder with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-step routing with LangChain and Pelias

The `search_geocode` tool acts as the entry point when your LangChain agent needs to resolve messy user-typed addresses into real coordinates. This MCP Server translates raw text into structured geographic data, feeding the next node in your LangGraph state machine. Once your agent gets the latitude and longitude, it passes those parameters to downstream APIs or databases in the same chain. You see the entire execution path, from the raw query to the Pelias API call, directly inside your LangSmith dashboard.

Real-time user typing inputs in LangChain

The `search_autocomplete` tool lets your LangChain agent suggest locations as a user types inside a conversational interface. This tool handles partial inputs and returns fast, ranked matches before the user even finishes typing. By integrating this tool with an MCP Server, you bypass writing custom API glue code in your LangGraph chain. The agent handles the keypress constraints and filters out irrelevant global locations based on local context.

Pinpoint geographic filtering for LangChain

The `search_bounding_box` tool restricts spatial queries to a defined rectangular coordinate set inside your LangChain agent. It keeps your agent from wandering across the globe when looking up hyper-local venues. You define the geographic boundaries directly in your prompt, and the agent uses this tool to extract matches within that box. It works with other tools like `search_country_filter` to ensure your data pipelines don't mix up international addresses.

Setup guide

Set up Pelias Geocoder MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Pelias Geocoder tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "pelias-geocoder-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Pelias Geocoder transactions"
    })
    print(result["messages"][-1].content)

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 Pelias Geocoder. 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 Pelias Geocoder 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 Pelias Geocoder MCP in LangChain

You map the output of tools like `search_geocode` directly into your LangGraph state. The agent reads the resulting latitude and longitude, then uses those values as inputs for subsequent tools in your chain.

Yes, every call made through this MCP Server shows up in your LangSmith trace. You can inspect exact inputs for tools like `reverse_geocode` to debug latency or bad coordinate inputs.

Your LangChain agent handles errors or rate limits based on your configured retry logic in the runnable chain. If a tool like `lookup_place_id` hits a limit, the framework manages the backoff before retrying.

This server lets your agent dynamically choose when to call geographic tools without you hardcoding the logic. The agent decides whether it needs `structured_geocoding` or a simple reverse lookup based on the conversation context.

Your raw coordinates and address strings stay inside the secure V8 sandbox managed by Vinkius. They only travel to your Pelias endpoint using your configured API keys, with no data cached or stored on our servers.

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