How to Use the Precisely MCP in LlamaIndex

Q: How do I expose Precisely tools to LlamaIndex?

Install llama-index-tools-mcp and instantiate a BasicMCPClient. Wrap it with McpToolSpec and call await mcptoolspec.totoollistasync() to feed the endpoints into your FunctionAgent.

Q: Can LlamaIndex store Precisely property records in a vector database?

Yes. When the agent calls getpropertyinfo, the resulting JSON containing square footage and year built is ingested. You map that output directly into your document store for future semantic retrieval.

Q: What happens if the address verification fails during a query?

If verifyaddress returns an invalid deliverability status, your agent can catch the error before indexing bad data. It prompts the user for a correction rather than polluting your knowledge base with a fake location.

Q: Can I restrict which Precisely endpoints LlamaIndex uses?

You control this using the allowedtools filter during setup. If you only want the agent doing spatial math, you expose geocodeaddress and gettimezone while blocking the financial and demographic endpoints.

Q: How secure is the local tax data retrieval?

When your agent requests overlapping tax jurisdictions via getlocaltax, the query executes within a zero-trust environment. The MCP protocol requires only a single endpoint token, ensuring no raw financial queries leak outside the managed tunnel.

Index property intelligence and geographic coordinates directly into your LlamaIndex RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Precisely MCP to LlamaIndex

Create your Vinkius account to connect Precisely 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 Precisely with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Ground RAG queries in property facts

Triggering `get_property_info` pulls lot sizes, assessed values, and bedroom counts straight into your LlamaIndex workflow. Instead of just reading the data once, your application indexes these county assessor records into a vector store. When a user asks about a specific US address later, the answer comes from stored, factual API data rather than an LLM guess. You can combine this with `get_local_tax` to build a highly specific knowledge base. The agent fetches the combined city and special district tax rates down to the rooftop level. Those exact percentages become searchable context for any future financial queries against the index.

Precisely MCP Server risk vectoring

Calling `enrich_flood_risk` captures FEMA classifications and base elevations for immediate semantic storage. Your LlamaIndex agent grabs these environmental metrics alongside `enrich_crime_risk` scores. Since crime indices normalize to a national average of 100, the indexed data provides a clear numerical baseline for safety comparisons. Storing these outputs creates a historical record of property evaluations. A query like 'Which scanned properties had high flood risk?' searches the exact JSON outputs your tools previously retrieved. The agent doesn't need to re-run the external API if the data already lives in your vector database.

Build location-aware semantic search

Executing `geocode_address` converts raw text into exact latitude and longitude coordinates with a specific precision code. S8 means you hit the rooftop, while S5 indicates street-level. Your LlamaIndex application embeds this metadata, allowing users to filter RAG results by geographic certainty. From there, `reverse_geocode` translates raw map clicks back into structured postal addresses. If the user needs local context, `enrich_demographics` pulls education levels and consumer spending patterns for that specific census block. All of this context gets chunked and indexed for deep, multi-faceted spatial querying.

Setup guide

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

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient`. Wrap it with `McpToolSpec` and call `await mcp_tool_spec.to_tool_list_async()` to feed the endpoints into your `FunctionAgent`.

Yes. When the agent calls `get_property_info`, the resulting JSON containing square footage and year built is ingested. You map that output directly into your document store for future semantic retrieval.

If `verify_address` returns an invalid deliverability status, your agent can catch the error before indexing bad data. It prompts the user for a correction rather than polluting your knowledge base with a fake location.

You control this using the `allowed_tools` filter during setup. If you only want the agent doing spatial math, you expose `geocode_address` and `get_timezone` while blocking the financial and demographic endpoints.

When your agent requests overlapping tax jurisdictions via `get_local_tax`, the query executes within a zero-trust environment. The MCP protocol requires only a single endpoint token, ensuring no raw financial queries leak outside the managed tunnel.

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