BatchDataSAFE
Model Context Protocol (MCP) server for BatchData.io property and address APIs - Real estate data integration for Claude and other AI assistants
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/zellerhaus-batchdata-mcp-real-estate)
[](https://smithery.ai/server/@zellerhaus/batchdata-mcp-real-estate)
A Model Context Protocol (MCP) server that integrates with BatchData.io's comprehensive property and address APIs. This server provides access to property data, address verification, skip tracing, geocoding, and advanced property search capabilities.
Features
Address Operations
- verify-address: Validate and standardize addresses using USPS verification
- autocomplete-address: Get intelligent address suggestions as you type
- geocode-address: Convert addresses to latitude/longitude coordinates
- reverse-geocode: Convert coordinates back to readable addresses
Property Operations
- lookup-property: Get detailed property information by address or APN (Assessor Parcel Number)
- search-properties: Advanced property search with comprehensive filters
- search-properties-by-boundary: Geographic boundary searches using bounding boxes or radius
- count-properties: Get property counts matching specific criteria (lightweight operation)
Installation
Installing via Smithery
To install batchdata-mcp-real-estate for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @zellerhaus/batchdata-mcp-real-estate --client claude
Manual Installation
- Clone or download this MCP server to your local machine
- Install dependencies:
cd batchdata-mcp-real-estate npm install
- Configure your API key:
- Get your API key from BatchData Settings or [register here](https://app.batchdata.com/registe
c37f518be84fOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add batchdata-mcp-server --env BATCHDATA_API_KEY=${BATCHDATA_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"batchdata-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"BATCHDATA_API_KEY": "${BATCHDATA_API_KEY}"
}
}
}
}Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
autocomplete-address | read | |
count-properties | read | |
geocode-address | read | |
lookup-property | read | |
reverse-geocode | read | |
search-properties | read | |
search-properties-by-boundary | read | |
verify-address | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, zod, dotenv, typescript, @types/node
Gates applied: no_behavioural_pass.
c37f518be84ffull audit observations/trust-audit/mcp-server/zellerhaus__batchdata.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | c37f518be84f | SAFE | B | 89 | first audit |
Questions
What is the BatchData MCP server?
Model Context Protocol (MCP) server for BatchData.io property and address APIs - Real estate data integration for Claude and other AI assistants
What tools does BatchData expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is BatchData safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does BatchData need?
It reads BATCHDATA_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does BatchData run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as batchdata-mcp-server at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (c37f518be84f), read on 2026-10-08. The repository is watched and re-audited when it changes.