How to Use the Fulcrum MCP in LlamaIndex

Q: How do I filter records by specific forms?

You provide the form ID as an argument to listfieldrecords. The agent typically discovers this ID first by calling listdataforms.

Ground your LlamaIndex RAG applications in live field data. Turn Fulcrum form submissions into queryable knowledge.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fulcrum MCP to LlamaIndex

Create your Vinkius account to connect Fulcrum 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 Fulcrum with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live field records into vector stores

LlamaIndex takes your raw field observations and turns them into semantic search embeddings via this MCP server. The agent calls `list_field_records` to pull the latest entries from your field teams. It then uses `get_record_details` to extract the metadata, timestamps, and specific text fields associated with each submission. LlamaIndex then chunks and indexes the raw text. When a user asks a question about recent site inspections, the agent searches the vector store instead of hallucinating. It grounds every answer in the actual data collected by your mobile workforce.

Map Fulcrum MCP Server schemas for semantic search

Before indexing anything, your agent needs context. It uses `list_data_forms` to identify all available data collection applications. Then, it runs `get_form_schema` to understand the exact structure of the fields, turning raw column names into human-readable definitions. This schema awareness drastically improves RAG accuracy. LlamaIndex uses the structural definitions to tag the vectors properly. When someone queries the system, the agent knows exactly which form contains the relevant information.

Embed SQL query results with LlamaIndex

Vector search falls flat on hard numbers, so index the results of relational queries instead. The agent executes `query_records_sql` to run complex aggregations across your entire dataset. It pulls back exact counts, averages, and filtered lists. LlamaIndex then takes that structured SQL output and integrates it into your knowledge base. You can verify the connection is active with `check_api_status` before running heavy queries, ensuring your RAG pipeline always has access to the latest field metrics.

Setup guide

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

Install llama-index-tools-mcp via pip. Wrap the basic client for this MCP server in an McpToolSpec and pass it directly to your FunctionAgent.

Yes. The agent translates your natural language question into a strict `query_records_sql` command, runs it, and summarizes the exact results.

It reads whatever currently exists in your cloud account. When a mobile worker syncs their offline device, the `list_field_records` tool immediately pulls the new entries.

You provide the form ID as an argument to `list_field_records`. The agent typically discovers this ID first by calling `list_data_forms`.

Your form schemas and raw field submissions never leave your controlled environment. The MCP protocol uses zero-trust architecture, meaning your vector embeddings are generated locally without exposing API keys to external models.

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