How to Use the Assertible MCP in LlamaIndex

Q: How does LlamaIndex verify API response structures with Assertible?

The agent uses validatejson to check incoming data against your schemas. This ensures that any data indexed into your knowledge base matches your official API specifications.

Q: Can LlamaIndex trigger an Assertible test run during a query?

Yes, the agent can invoke runspecifictest or runservicetests dynamically. It then indexes the live test results to answer questions about current system uptime.

Q: How do I sync my API specifications with this setup?

You use syncspecification to upload your OpenAPI or Swagger files. This updates your testing suite so that subsequent test runs reflect the latest API design.

Index Assertible test results and API schemas into LlamaIndex vector stores for ground-truth RAG queries.

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 LlamaIndex

Create your Vinkius account to connect Assertible to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index test histories using the Assertible MCP Server

Indexing test histories using `get_test_status_badge` lets your agent track API health trends over time. By pulling live badge status data, the agent gathers health indicators to update your knowledge base. This MCP integration lets you query your system to find out which endpoints fail most often. The agent retrieves the historical runs, matches them against current issues, and helps you debug without digging through raw logs.

Retrieve and validate live API schemas

Validating documents with `validate_json` ensures your RAG application only indexes structurally sound payloads. The agent checks incoming data against your actual schemas before feeding them to the LLM. This prevents the model from generating code or queries based on outdated payload formats. By checking schemas dynamically, your knowledge base remains accurate even when your backend changes.

Run automated service tests during query loops

Triggering live test runs with `run_service_tests` lets your agent answer queries with real-time uptime data. When a user asks about API health, the agent runs the suite to get fresh status updates directly from Assertible. It can also use `create_deployment` to spin up a test run for a specific environment. The live output is indexed immediately, giving the user a real-time answer backed by actual test execution.

Setup guide

Set up Assertible MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Assertible MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Assertible tools.",
)
response = await agent.run("List recent Assertible data")

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 LlamaIndex

Yes, you can index the output of your test runs into a vector store. The agent queries this index using the LlamaIndex MCP tool spec to analyze patterns in your API failures over time.

The agent uses `validate_json` to check incoming data against your schemas. This ensures that any data indexed into your knowledge base matches your official API specifications.

Yes, the agent can invoke `run_specific_test` or `run_service_tests` dynamically. It then indexes the live test results to answer questions about current system uptime.

You use `sync_specification` to upload your OpenAPI or Swagger files. This updates your testing suite so that subsequent test runs reflect the latest API design.

All schema data and badge URLs pass through an isolated, zero-trust MCP container. Your credentials and API definitions are never logged or cached on Vinkius servers, ensuring your testing infrastructure remains secure.

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