How to Use the FBI Crime Data Explorer MCP in LangChain

Build LangChain reasoning pipelines that query live FBI Crime Data Explorer metrics to back up policy analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FBI Crime Data Explorer MCP to LangChain

Create your Vinkius account to connect FBI Crime Data Explorer to LangChain 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 FBI Crime Data Explorer with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble multi-step crime data chains with LangChain

The `get_national_estimates` tool pulls official FBI crime statistics directly into your LangChain agent's execution loop. This MCP Server exposes four tools to query official public safety metrics directly inside your active run loops. When you pass these endpoints into a ReAct agent, it doesn't just pull raw numbers; it chains the output as the immediate input for the next step. Your LangChain agent runs the national query, spots a trend, and instantly triggers `get_state_summarized` to cross-reference the state-level reality. This LangChain pipeline runs autonomously, giving you a traced sequence of decisions inside LangSmith instead of a black-box guess.

Trace agency-level data flow with LangSmith observability

The `get_agency_summarized` tool pulls raw local law enforcement metrics directly into your LangChain workflow. You see the exact inputs, raw payloads, and token usage for every local agency lookup right in your developer dashboard. No more guessing why an agent hallucinated a local crime rate. By monitoring the exact payload returned from the API, you verify how your LangChain model parses raw local arrest and incident records.

Chain victim demographics with multi-server pipelines

The `get_nibrs_victim_demographics` tool injects granular demographic statistics directly into your active LangChain chains. You combine this demographic data with external databases or vector stores in a single, unified execution graph. Because LangChain handles multi-server setups natively, your agent can pull demographic data from this server and immediately pass it to a completely different MCP Server to generate localized policy recommendations. You control the state, the prompts, and the data flow.

Setup guide

Set up FBI Crime Data Explorer 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 FBI Crime Data Explorer 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({
    "fbi-crime-data-explorer-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 FBI Crime Data Explorer 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 FBI Crime Data Explorer. 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 FBI Crime Data Explorer 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 FBI Crime Data Explorer MCP in LangChain

Install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the MCP Server URL. Call client.get_tools() and pass them directly to your create_agent function.

Yes, LangChain agents use ReAct loops to determine tool execution order. The agent calls get_national_estimates first, analyzes the output, and then calls get_state_summarized to compare national and state trends.

LangSmith traces the exact JSON payloads returned by tools like get_agency_summarized. You inspect the raw inputs, API response latency, and token consumption for every crime data query.

The client adapter is stateless by default. If you need to maintain context across multiple API queries, use client.session() to manage your persistent connection.

All requests for local agency and national crime statistics run through Vinkius's zero-trust V8 Isolate Sandbox. Your FBI Crime Data Explorer MCP Server credentials are encrypted at rest and never exposed to the LLM or the client application.

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