How to Use the FullStory MCP in LangChain

Q: Can LangChain handle complex FullStory queries?

Yes. You pass your JSON query criteria into listsessions through the agent. The framework manages the schema conversion so the tool receives the correct structure.

Q: How are privacy-sensitive records handled in LangChain?

You use deleteuser to purge specific profiles from the analytics boundary. This ensures your LangChain environment doesn't retain data that violates your retention policies.

Build multi-step diagnostic pipelines in LangChain by chaining FullStory session data directly into your reasoning agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FullStory MCP to LangChain

Create your Vinkius account to connect FullStory 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 FullStory with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain session data into your LangChain agents

Feed raw session telemetry from `get_session_events` directly into your agent's reasoning loop. You can now build chains that digest click trails and navigation mutations without manual intervention. Your agent decides when to trigger `get_session` based on the context of the current conversation. This creates a tight feedback loop where the model asks for more data only when it hits a dead end in the chain.

Sync CRM identities using LangChain workflows

Automate user profile management by piping your CRM records into `create_update_user`. You stop manually updating identities and let the agent handle the mapping as part of its execution sequence. This ensures that every session recording is correctly tagged with your internal identifiers. The agent maintains the link between your local database and the analytics boundary during every step of the pipeline.

Automate segment analysis with LangChain

Use `list_segments` to pull current audience definitions into your agent's memory. The model evaluates these population counts to determine if a specific bug impacts a high-value cohort. Once the agent identifies the segment, it executes `list_sessions` to retrieve the relevant recordings. You get a prioritized list of user issues formatted for your specific investigation requirements.

Setup guide

Set up FullStory 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 FullStory 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({
    "fullstory-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 FullStory 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 FullStory. 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 FullStory 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 FullStory MCP in LangChain

LangSmith logs every input and output for your MCP tools automatically. You see the exact latency and token usage for every call to `get_session` or `list_sessions`.

Yes. You pass your JSON query criteria into `list_sessions` through the agent. The framework manages the schema conversion so the tool receives the correct structure.

Your Vinkius endpoint handles the authentication layer. Only the data you explicitly request via tool calls enters your agent's context window.

Yes. Each tool call is independent, but you can maintain state by using the client session object. This keeps your user identifiers consistent across multiple chain steps.

You use `delete_user` to purge specific profiles from the analytics boundary. This ensures your LangChain environment doesn't retain data that violates your retention policies.

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