How to Use the Keywords AI MCP in LangChain

Q: How do I monitor Keywords AI logs in my LangChain agents?

You hook the MCP tools into your agent's tool set. Use listrequests to pull logs and pass them into your LangChain prompt context for analysis.

Q: Can Keywords AI alert my LangChain pipeline about budget issues?

Yes. You can run getcredits as a periodic check in your chain. If the balance drops below your threshold, the agent can stop non-essential tasks.

Q: Does Keywords AI provide latency data for my LangChain chains?

It does. You can query getusagestats to retrieve latency metrics for your specific model requests, allowing your chains to optimize their own runtime.

Build chains that track LLM costs and latency directly within your LangChain pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keywords AI MCP to LangChain

Create your Vinkius account to connect Keywords AI 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 Keywords AI with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time cost and usage monitoring

Feed your chain's output into `get_usage_stats` to see exactly what your agents are spending. It replaces guesswork with hard numbers on token consumption. Monitor your spend across providers without leaving your code. Using `get_credits` inside a chain lets you build logic that halts execution if you hit a budget cap.

Unified model observability

Call `list_models` to dynamically swap LLM backends based on current performance data. Your LangChain agent can now query `list_requests_by_model` to verify if a specific model is failing before routing traffic to it. This gives your agent the context it needs to make routing decisions. It treats the Keywords AI MCP Server as a source of truth for infrastructure health.

Automated alert management

Integrate `list_alerts` directly into your LangSmith tracing. You can trigger custom logic whenever the gateway flags a performance issue or a spike in latency. It keeps your pipeline informed about its own operational environment. If `check_keywordsai_status` returns an error, your agent can immediately switch to a fallback provider.

Setup guide

Set up Keywords AI 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 Keywords AI 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({
    "keywords-ai-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 Keywords AI 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 Keywords AI. 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 Keywords AI 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 Keywords AI MCP in LangChain

You hook the MCP tools into your agent's tool set. Use `list_requests` to pull logs and pass them into your LangChain prompt context for analysis.

Yes. You can run `get_credits` as a periodic check in your chain. If the balance drops below your threshold, the agent can stop non-essential tasks.

It does. You can query `get_usage_stats` to retrieve latency metrics for your specific model requests, allowing your chains to optimize their own runtime.

Not at all. Install the MCP adapters, point your client to the Vinkius endpoint, and define the tools in your agent config.

Keywords AI only processes metadata and request logs required to calculate usage and costs. Your sensitive prompt content remains isolated within your own infrastructure.

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