How to Use the Kissflow MCP in LlamaIndex

Q: How do I load Kissflow data into LlamaIndex?

Install llama-index-tools-mcp. Set up a BasicMCPClient, wrap it in an McpToolSpec, and call totoollistasync(). Pass those tools to your data loaders.

Q: Can LlamaIndex sync updates from Kissflow automatically?

You have to schedule the ingestion. LlamaIndex will call listdataformitems during the indexing run, but it does not listen for webhooks. Run the indexer periodically to keep the vector store fresh.

Q: Which Kissflow endpoints work best with LlamaIndex RAG apps?

Start with listdatasetitems for master reference data. Then index listprocessitems if you need users to search through historical workflow decisions.

Index your Kissflow environment into LlamaIndex to build searchable RAG applications on live process data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kissflow MCP to LlamaIndex

Create your Vinkius account to connect Kissflow 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 Kissflow with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorizing Master Datasets

LlamaIndex and this MCP Server turn static reference tables into queryable knowledge. Your setup calls `list_datasets` to map available master data, then iterates through `list_dataset_items` to pull every record. The framework embeds these rows into a vector store. When a user asks a question about vendor codes or compliance rules, the engine searches the vector index instead of hitting the API blindly. You get instant, semantically relevant answers grounded in actual Kissflow data.

Indexing Kissflow MCP Server Workflows

Workflow history holds massive operational value. By pointing LlamaIndex at `list_processes` and `list_process_items`, you dump the entire history of approvals, rejections, and delays into your RAG pipeline. This allows you to query historical bottlenecks. A user can ask why procurement took three weeks last November, and the index retrieves the exact process items that stalled. The integration feeds raw JSON directly into the document parsers.

Organizational Chart RAG

You can build an internal directory assistant by indexing your user base. The client pulls the roster via `list_users` and grabs group assignments using `list_groups`. It then enriches specific profiles via `get_user_details`. Once indexed, users can query the AI to find out who owns specific approval steps. The engine connects the semantic dots between a user's group membership and their role in a workflow.

Setup guide

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

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient`, wrap it in an `McpToolSpec`, and call `to_tool_list_async()`. Pass those tools to your data loaders.

You have to schedule the ingestion. LlamaIndex will call `list_dataform_items` during the indexing run, but it does not listen for webhooks. Run the indexer periodically to keep the vector store fresh.

The server just provides the raw data endpoints. LlamaIndex handles the actual chunking, embedding, and semantic retrieval after it pulls the records.

Start with `list_dataset_items` for master reference data. Then index `list_process_items` if you need users to search through historical workflow decisions.

The connection operates in an ephemeral, zero-trust environment. When your indexer pulls raw submissions via `list_dataform_items`, Vinkius routes the traffic securely without storing the payloads on disk. Authentication requires a single endpoint token.

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