How to Use the Zeev MCP in LlamaIndex

Q: How does LlamaIndex index Zeev task status changes?

When you run gettask or listtasks, the output data becomes a document chunk in your vector store. This allows future queries to retrieve not just the current state, but context about past states too.

Q: Can LlamaIndex query historical process definitions from Zeev?

Yes. You index the results of listprocesses and getprocess. This lets users ask questions like, 'What are our standard approval chains for vendor payments?' and get an answer grounded in your recorded workflow data.

Q: Is the MCP Server's output used by LlamaIndex to improve context?

Exactly. The results from tools like getrequest are treated as raw, verifiable facts that build out your knowledge index. This is how you get answers grounded in API data instead of hallucinations.

Q: What if I want to know about a cancelled request using LlamaIndex?

You index cancelrequest logs and process metadata. If you query for 'cancelled requests', the knowledge base will pull up relevant details from the records, even if the task is finished.

Index historical Zeev process data for RAG with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zeev MCP to LlamaIndex

Create your Vinkius account to connect Zeev 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 Zeev with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Knowledge Base of Workflow Definitions

LlamaIndex turns operational data into searchable knowledge. You can index the output from `list_processes` and `get_process`. This means you can query your entire historical library of Zeev workflows by natural language, not just IDs. The result is a vector store entry that grounds answers in actual API data, eliminating guesswork when building RAG applications.

Retrieving Past Task Statuses

You don't have to guess what happened last week. By indexing the results of `list_tasks` and `get_task`, you create a searchable history of every task status. Developers can combine this with document search, answering questions like, 'What was the outcome of Zeev task XYZ in Q3?' This makes live API data part of your unified knowledge index.

Analyzing Process Request History

Need to know why a request failed six months ago? Indexing `list_requests` and the detailed output of `get_request` allows semantic search across time. Instead of just listing IDs, you query the *context* of past workflow runs. The resulting knowledge base helps developers build apps that understand historical process failures and successful completions.

Setup guide

Set up Zeev 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 Zeev 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 Zeev tools.",
)
response = await agent.run("List recent Zeev 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 Zeev. 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 Zeev 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 Zeev MCP in LlamaIndex

When you run `get_task` or `list_tasks`, the output data becomes a document chunk in your vector store. This allows future queries to retrieve not just the current state, but context about past states too.

Yes. You index the results of `list_processes` and `get_process`. This lets users ask questions like, 'What are our standard approval chains for vendor payments?' and get an answer grounded in your recorded workflow data.

Exactly. The results from tools like `get_request` are treated as raw, verifiable facts that build out your knowledge index. This is how you get answers grounded in API data instead of hallucinations.

It touches process definition metadata and specific workflow execution records (requests and tasks). These are the core structured data points indexed by LlamaIndex.

You index `cancel_request` logs and process metadata. If you query for 'cancelled requests', the knowledge base will pull up relevant details from the records, even if the task is finished.

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