A local tool for finding building permits and assessing whether properties on the San Francisco Peninsula may support projects such as SB 9 lot splits, accessory dwelling units, or redevelopment.

Use it to investigate building permits, parcel buildability, SB 9 possibilities, ADU opportunities, and redevelopment leads.

It brings permit and parcel information into an agent workflow, so property opportunities can be researched from an address. It requires an Address Intelligence API key.

permits — MCP server by RantumBits

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/rantumbits/addressintel-mcp/permits

Clone the repo

git clone --depth 1 https://github.com/RantumBits/addressintel-mcp

Made for: Claude Code, Codex, Cursor.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

permits scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

server.json · 12 lines

What it actually says

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

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 12 lines scan A c774ce002e74

Subscribe to this mod's changes

permits is an MCP server published in the GitHub repository RantumBits/addressintel-mcp (0 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Legal and compliance adu building-permits mcp model-context-protocol real-estate sb9

debary-mcp-compliance

MCP server "debary-mcp-compliance" as configured in DE-BARY-LLC/debary-mcp-compliance. Runs locally from the debary-mcp-compliance Python package.

DE-BARY-LLC/debary-mcp-compliance · not measured

taiwan-legal-db

MCP server "taiwan-legal-db" as configured in lawchat-oss/mcp-taiwan-legal-db. Runs mcp_server.server with .venv/bin/python.

lawchat-oss/mcp-taiwan-legal-db · not measured

mcp-sudact

Thin MCP client for Russian court practice (Sudact) hosted API: full-text case search + full decision text. Engine is hosted; this package only talks to the atomno-mcp backend. Runs locally from the atomno-mcp-sudact Python package. Needs 1 environment variable to run.

atomno-mcp/mcp-sudact · not measured

permits

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

debary-mcp-compliance

taiwan-legal-db

mcp-sudact

contract-review-ai-mcp

causallayer-mcp

causallayer