How to Use the JigsawStack MCP in LangChain

Q: How do I configure the JigsawStack MCP Server inside a LangChain project?

You install the langchain-mcp-adapters package and initialize the client using your Vinkius endpoint. Pass the tools directly into your agent constructor to let LangChain handle the execution.

Q: Can I trace JigsawStack tool executions in LangChain using LangSmith?

Yes, every call to tools like aiwebscrape or summarizetext registers as a distinct span in LangSmith. You see exact inputs, outputs, and execution times for debugging.

Q: What is the fastest way to extract structured text from images?

You call the extracttextfromimage tool within your chain to run OCR on any public image URL. The tool returns structured text blocks that your LLM can immediately parse.

Run LangChain agents that scrape, translate, and filter content dynamically using the JigsawStack MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JigsawStack MCP to LangChain

Create your Vinkius account to connect JigsawStack 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 JigsawStack with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain web scraping directly into text translation

The `ai_web_scrape` tool extracts clean data from any URL using natural language prompts. This tool outputs raw text directly into your LangChain schema, allowing the next node in your graph to consume it immediately. You feed that output directly into `translate_text` to localize the scraped data before storing it. LangSmith monitors the entire sequence, tracking exact latency and token usage for each step of the pipeline.

Filter text and images inside LangChain agents

The `check_profanity_text` tool scans text payloads for offensive language and returns a clean boolean verdict. Your LangChain agent evaluates this flag before deciding to execute the next tool in the chain. If you process visual media, `check_nsfw_image` evaluates image URLs to block explicit content before it reaches your vector database. This dual-layer check prevents bad data from corrupting your LangChain pipeline.

Connect LangChain to this MCP Server for live search

The `ai_web_search` tool queries the live web using natural language to retrieve fresh information. This tool gives your LangChain agent the ability to bypass its training cutoff dates instantly. Your agent extracts facts, summarizes them with `summarize_text`, and answers user queries with grounded data. You configure this server in seconds using the LangChain MCP adapter.

Setup guide

Set up JigsawStack 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 JigsawStack 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({
    "jigsawstack-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 JigsawStack 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 JigsawStack. 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 JigsawStack 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 JigsawStack MCP in LangChain

You install the `langchain-mcp-adapters` package and initialize the client using your Vinkius endpoint. Pass the tools directly into your agent constructor to let LangChain handle the execution.

Yes, every call to tools like `ai_web_scrape` or `summarize_text` registers as a distinct span in LangSmith. You see exact inputs, outputs, and execution times for debugging.

The adapter catches API errors and passes them back to your LangChain agent as text observations. Your agent then decides whether to retry the call or try a different tool path.

You call the `extract_text_from_image` tool within your chain to run OCR on any public image URL. The tool returns structured text blocks that your LLM can immediately parse.

All raw HTML and image URLs processed by JigsawStack are transmitted securely over HTTPS and never stored on the local Vinkius sandbox. Your data remains in memory only during the active tool execution lifecycle.

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