Skip to main content
Glama

AddressIntel MCP server

A read-only Model Context Protocol server that puts SF Peninsula building-permit and parcel-buildability data inside Claude, ChatGPT, or any other MCP-capable agent.

It is a thin client over the public AddressIntel API, so it inherits that API's auth, rate limits and tier ceilings. Every tool is a GET. Nothing here can write.

Tools

Tool

What it answers

search_permits

What construction has actually been permitted at an address or in a city? Filters on city, keyword (address, project type, scope description, contractor, architect, permit number) and minimum valuation.

list_sb9_inventory

Which active listings can be split or duplexed under SB 9, and what blocks the ones that can't?

list_adu_leads

Which parcels have room for an ADU, and how many units / how much square footage?

list_redevelopment_leads

Which parcels are underbuilt against their allowable envelope (scrape-and-rebuild or expansion)?

list_market_signals

Which listings score highest for teardown or flip potential?

get_property_intelligence

Full scores and comparable sales for one property id.

The permit and parcel tools are the differentiated half: permit-level detail and parcel-level buildability for the Peninsula, rather than a nationwide owner list.

Related MCP server: permisapi-mcp

Install

No install step: npx fetches it on demand.

Claude Code

claude mcp add addressintel \
  -e ADDRESSINTEL_API_KEY=your_key \
  -- npx -y addressintel-mcp

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "addressintel": {
      "command": "npx",
      "args": ["-y", "addressintel-mcp"],
      "env": {
        "ADDRESSINTEL_API_KEY": "your_key"
      }
    }
  }
}

From source

For working on the server itself:

git clone https://github.com/RantumBits/addressintel-mcp.git
cd addressintel-mcp
npm install
npm run build     # emits dist/index.js

Then point the client at node /absolute/path/to/addressintel-mcp/dist/index.js instead of the npx command above.

Restart the client, then ask it something like "what demolition permits were issued in Menlo Park this year?" or "which Palo Alto listings are SB 9 eligible?"

Configuration

Variable

Default

Notes

ADDRESSINTEL_API_KEY

demo

Without a key the server uses the public demo tier: 10 requests/minute, 5 rows per call. Grab a free key at https://addressintel.co/developers for 30/min and 25 rows; the key is emailed to the address you enter.

ADDRESSINTEL_API_BASE

https://addressintel.co/api

Point at a local dev server (http://localhost:3000/api) when working on the API.

Development

npm run dev       # run from source over stdio
node test_mcp.mjs # smoke test: connect, list tools, call one

Tools are declared in one table in src/index.ts. Each entry carries its zod schema and its advertised JSON Schema side by side, so adding a tool means adding one entry, and the two shapes cannot drift apart.

Available Tools

6 tools
get_property_intelligenceA

Get detailed AI intelligence for a specific property. Returns teardown probabilities, flippability scores, comparable sales, and a developerROI field. Takes an id from list_market_signals. Treat developerROI as an AI screening estimate for ranking only, not as underwriting: it is a model output rather than arithmetic, and it disagrees materially with a build-to-zoning proforma on much of the inventory. Do not quote it as an expected return.

Inputs: id (required).

list_adu_leadsA

List parcels ranked by ADU (accessory dwelling unit) feasibility, including estimated max units, buildable square footage and the lot geometry behind the score.

Inputs: limit, minScore, excludeBlockers.

list_market_signalsA

Search for high-signal real estate investment opportunities (teardowns, flips). Use this to find properties before diving into specific details.

Inputs: city, limit, market, address.

list_redevelopment_leadsA

List underbuilt parcels: small, older homes using a low share of their allowable building envelope on sizable lots. Ranked by redevelopment score, with the FAR headroom that produced it.

Inputs: class, limit, minScore, excludeBlockers.

list_sb9_inventoryA

List active listings that are eligible for an SB 9 lot split or duplex conversion, with the per-parcel block reasons where they are not. California-only; this is a parcel-level buildability read, not a generic lead list.

Inputs: limit, status, minUnits, excludeBlockers.

search_permitsA

Search issued building permits across the SF Peninsula and adjacent Silicon Valley cities. Filter by city, keyword (address, project type, scope description, contractor, architect or permit number) and minimum valuation. Use this to find what construction has actually been permitted at an address or in a city.

Inputs: q, city, limit, offset, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 6 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: search_permits is unique, and the four list_* tools each target different criteria (SB9, ADU, redevelopment, market signals). However, list_redevelopment_leads and list_market_signals could overlap in identifying teardowns, and all list tools produce property leads, so there is minor potential for confusion.

    Naming Consistency4/5

    Tool names follow a verb_noun pattern with snake_case, which is consistent. The primary deviation is the verb set: search, list (four times), and get. This is a minor inconsistency because most tools use 'list' but search_permits and get_property_intelligence use different verbs.

    Tool Count5/5

    Six tools is well within the ideal 3-15 range. Each tool serves a distinct function in the real estate lead generation domain, and the count feels neither bloated nor sparse.

    Completeness4/5

    The core workflow is covered: search permits, generate multiple types of leads, and get detailed intelligence—though get_property_intelligence only takes ids from list_market_signals, leaving other lead lists without a deep-dive follow-up. Minor gaps like no general address lookup or update/delete operations are acceptable for a read-only intel server.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Open-source MCP server providing real estate regulatory intelligence (zoning, permits, entitlements, deal scoring) for US properties, enabling AI agents to access 10 callable tools.
      12
      5 npm
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      French building permits MCP server: 1.2M Sitadel permits (2014-2026, daily refresh), DVF transactions, cadastre DGFiP, PLU zoning, BRGM risks, and property-dealer opportunity scoring through 11 MCP tools. Free tier 500 req/month, no credit card.
      11
      303 PyPI
      3
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      MCP server for querying the San Diego Municipal Code, bulletins, permits, parcels, and zoning data with citations and freshness guarantees.
      14
      MIT
    • F
      license
      A
      quality
      C
      maintenance
      MCP server that exposes a Hawaii property pipeline as Claude tools, allowing natural language queries about parcel records, hazards, zoning, ADU eligibility, and more, based on real public data.
      3
      -