How to Use the KnowFirst MCP in LangChain

Q: How does LangChain handle authentication for the KnowFirst MCP server?

The MultiServerMCPClient manages it. You provide your Vinkius endpoint token once during setup. After that, every call your LangChain agent makes to the KnowFirst server is authenticated automatically.

Build LangChain agents that chain KnowFirst tools together, turning raw market intelligence into a sequence of actionable steps.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KnowFirst MCP to LangChain

Create your Vinkius account to connect KnowFirst 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 KnowFirst with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Autonomous Research Agents

Start with a simple question, and your LangChain agent decides the rest. It can `search_intelligence_entities` to find a company, then `get_entity_profile` to pull its details, and finally `get_entity_connections` to map its relationships. You don't hardcode the steps; the agent figures out the sequence on its own. This is how you build an agent that investigates market shifts. It might start by checking `get_market_intelligence_trends`, then pivot to auditing a key player with `audit_entity_changes` if it spots an anomaly. LangSmith gives you a full trace of the agent's reasoning, showing exactly which tools it called and why.

Create Custom Intelligence Chains with LangChain

Link KnowFirst tools into a repeatable intelligence workflow. Your chain can automatically `search_data_sources` for a new financial report, then feed the results into a custom LLM to summarize the findings. You're not just calling tools; you're building a reusable data processing pipeline. This is useful for compliance or due diligence. A chain could take a list of entity IDs, run `get_entity_profile` on each one, and then use `list_entity_data_points` to check for specific risk signals. Each step's output is the next step's input, all managed inside your LangChain application.

Ground Your Agent with Real-Time Data

Stop your agents from making things up. Before answering a question about a market, your agent can call `check_knowfirst_api_status` to confirm the connection is live. Then, it uses tools like `list_intelligence_sources` to cite exactly where its information comes from. You can even build chains that react to data quality. If `list_entity_data_points` returns sparse information, the agent can be programmed to fall back to a broader `query_custom_intelligence` search. This makes your agent's responses more reliable because they're based on verified, up-to-the-minute data from this MCP server.

Setup guide

Set up KnowFirst 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 KnowFirst 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({
    "knowfirst-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 KnowFirst 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 KnowFirst. 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 KnowFirst 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 KnowFirst MCP in LangChain

You pass the tools from KnowFirst directly to your agent's prompt. Then you can just ask it to 'audit the changes for entity XYZ.' The agent will know to use the `audit_entity_changes` tool automatically.

Yes, that's the point of LangChain. You can create a chain where one step queries KnowFirst with `get_entity_profile` and the next step uses that data to look up a record in your own SQL database.

Use LangSmith. It gives you a complete trace of the agent's execution, showing the inputs and outputs for every KnowFirst tool call. You can see exactly why it chose `search_intelligence_entities` over `query_custom_intelligence`.

The `MultiServerMCPClient` manages it. You provide your Vinkius endpoint token once during setup. After that, every call your LangChain agent makes to the KnowFirst server is authenticated automatically.

Your queries and the data they return—like entity profiles or market trends—are processed in an ephemeral sandbox. Vinkius doesn't store your request history or the specific intelligence data you access. The connection is stateless unless you explicitly create a session.

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