How to Use the Serviceform MCP in LlamaIndex

Q: How does Serviceform improve data retrieval when used with LlamaIndex?

LlamaIndex indexes the output of tools like listleads and getlead. You can query these records semantically, meaning you ask a question, and it finds the relevant lead record, even if the exact words aren't present.

Q: What criteria can I use to search chat history with Serviceform and LlamaIndex?

You pass criteria as a JSON string into listchats. The results are indexed, allowing you to later query for conversations based on complex filtering rules.

Q: Can LlamaIndex build a knowledge graph from Serviceform data?

Yes. By indexing the output of multiple tools like listforms and getspaceitems, you create a unified index that connects different types of structured API data.

Q: Does Serviceform help with understanding site structure when used with LlamaIndex?

Absolutely. Indexing the output from both listspaces and getspaceitems gives you a fully searchable, deep understanding of the website's content map.

Index Serviceform API data into a searchable knowledge base with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Serviceform MCP to LlamaIndex

Create your Vinkius account to connect Serviceform to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Serviceform with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Indexing Lead Capture Data via MCP Server

The `list_leads` tool lets you pull records of every lead captured. By passing this output to your indexer, the data becomes part of a searchable knowledge base. You can query past campaigns and get answers grounded in actual API results. This capability is huge for RAG applications. Instead of just running `get_lead`, you treat that result like a document, allowing semantic search over historical customer interactions.

Searching Chatbot History with LlamaIndex

When you use `list_chats` to pass criteria as a JSON string, the resulting chat histories are indexed. This means your knowledge base can answer questions like, 'What was the main topic of conversation in Q3?' without needing precise keywords. It moves beyond simple lookups. Your index combines live API data with documents, making historical service interactions fully queryable for insights.

Analyzing Site Content with MCP Server

You can use `list_spaces` and then combine it with `get_space_items`. Both sets of results are indexed into your vector store. This means you're not just listing items; you're building a searchable map of the entire site architecture. This unified index lets developers build complex applications that combine architectural knowledge (the spaces) with specific content details (the items).

Setup guide

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

LlamaIndex indexes the output of tools like `list_leads` and `get_lead`. You can query these records semantically, meaning you ask a question, and it finds the relevant lead record, even if the exact words aren't present.

You pass criteria as a JSON string into `list_chats`. The results are indexed, allowing you to later query for conversations based on complex filtering rules.

Yes. By indexing the output of multiple tools like `list_forms` and `get_space_items`, you create a unified index that connects different types of structured API data.

Absolutely. Indexing the output from both `list_spaces` and `get_space_items` gives you a fully searchable, deep understanding of the website's content map.

The server touches lead details. These specific records are indexed into your knowledge base, allowing you to recall and analyze them within a secure RAG context.

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