How to Use the Assertible MCP in LangChain

Q: How does LangChain handle Assertible deployment tracking?

The agent calls createdeployment to notify Assertible of a new build. It then monitors the deployment status and uses the output to decide the next step in your release chain.

Q: Do I need an active session to validate JSON schemas?

No, validatejson does not require authentication. You can run this tool statelessly within any chain to check payload structures against Draft 4 schemas instantly.

Trigger Assertible tests and track deployment runs directly inside your LangChain reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Assertible MCP to LangChain

Create your Vinkius account to connect Assertible 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 Assertible with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Assertible tests with LangChain agents

Triggering tests via `create_deployment` lets your LangChain agent manage deployment workflows in a single chain. When you deploy code, the agent starts the run, waits for the results, and decides whether to roll back or proceed based on the status. This setup uses LangSmith to track every tool call, giving you clear visibility into latency and payloads. If a test fails, the agent grabs the status with `get_test_status_badge` to update your team's Slack channel without manual intervention.

Automate specification syncs in multi-step pipelines

Syncing your API specs using `sync_specification` keeps your testing suite aligned with your code automatically. Your agent can pull your latest OpenAPI spec from a repository and immediately update Assertible without you lifting a finger. Once synchronized, the agent runs `validate_json` to verify that your mock payloads match the new schema. This prevents broken endpoints from reaching staging because the verification happens before any code gets merged.

Run targeted API tests via the Assertible MCP Server

Running targeted checks with `run_specific_test` allows your agent to bypass full test suites for minor updates. This MCP Server setup avoids running unrelated routes, which keeps your testing quick and saves API credits. If the agent detects a wider system change, it pivots to `run_service_tests` to run the full suite. You get fast feedback during development while maintaining complete coverage before production releases.

Setup guide

Set up Assertible 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 Assertible 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({
    "assertible-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 Assertible 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 Assertible. 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 Assertible 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 Assertible MCP in LangChain

You load the tools into your agent using the MCP adapter. The agent uses `run_specific_test` by passing the test ID when a specific endpoint needs validation, bypassing the full suite to save execution time.

Yes, you can build a chain that triggers on commit. The agent uses `sync_specification` to upload your new OpenAPI document directly to Assertible, keeping your assertions updated.

The agent calls `create_deployment` to notify Assertible of a new build. It then monitors the deployment status and uses the output to decide the next step in your release chain.

No, `validate_json` does not require authentication. You can run this tool statelessly within any chain to check payload structures against Draft 4 schemas instantly.

Your OpenAPI specs and test payloads are sent directly to Assertible via secure, ephemeral V8 sandboxes. Vinkius does not store your tokens or test data, keeping your API definitions completely private.

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