Skip to main content
Glama
Agent to Brokerage Resolver MCP Server

Agent to Brokerage Resolver MCP Server

Agent to Brokerage Resolver MCP Server

Glama score MCP Registry npm version npm downloads license mcpservers.org

An MCP server for the Mamba Labs Agent to Brokerage Resolver actor on Apify. Give it a licensed US real estate agent, by license number or by name and state, and get the brokerage of record from the official state license register, that brokerage's active agent count and size band, and the agent's license status and expiry. It can also list every active agent at a brokerage, or every brokerage office in a zip code.

What's Inside

Related MCP server: LicenseGround MCP Server

What it does

Look up a licensed US real estate agent on the official state license register and get the brokerage of record, the brokerage's active agent count and size band (1, 2-15, 16-50, 51+), and the agent's license status and expiry. Covers 19 states; brokerage data in CA, IA, MO, NV, NY, OH, OR, TX, and VT. Three modes: lookup (one agent or a list, by license number or by name), roster_firm (active agents at one brokerage), and roster_zip (brokerage offices in a zip code, NY, MO, OR, and VT). Returns no emails, phone numbers, or home addresses. Ambiguous or unmatched inputs return a free row with row_status explaining why. A run that does not succeed is returned as an error with its run ID.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

{
  "mcpServers": {
    "mamba-agent-brokerage-resolver": {
      "command": "npx",
      "args": [
        "-y",
        "@mambalabsdev/mcp-agent-brokerage-resolver"
      ],
      "env": {
        "APIFY_TOKEN": "your-apify-token"
      }
    }
  }
}

Restart the client. The resolve_agent_brokerage tool appears.

Prerequisites

Example prompts

  • "Which brokerage is Texas agent 134224-SA with, and how big is it?"

  • "List the active agents at the brokerage with Texas license 566433-BB."

  • "Which real estate brokerages have an office in zip 14201, and how many agents does each have?"

Tool

resolve_agent_brokerage. One tool. Example arguments:

{ "mode": "lookup", "state": "TX", "license_number": "134224-SA" }

Inputs

Input

Type

Required

Description

mode

string

no

lookup, roster_firm, or roster_zip. Default lookup.

state

string

no

Two letter licensing state, for example TX.

license_number

string

no

Lookup mode. The agent's license number as the register prints it.

agent_name

string

no

Lookup mode, when there is no license number. First and last name.

brokerage_name

string

no

Narrows a name match; names the firm in roster_firm mode.

city

string

no

Narrows a name match by office city or license county.

licenses

string

no

Lookup batch, one per line: state then license number.

agents

string

no

Lookup batch, one per line: state, name, brokerage, city, separated by a vertical bar.

brokerage_license_number

string

no

roster_firm mode. The brokerage's license number.

zip

string

no

roster_zip mode. A five digit zip code.

zips

string

no

roster_zip batch, one zip per line.

include_agents

string

no

roster_zip mode. true also lists each office's active agents.

active_only

string

no

Roster modes. Active licenses only. Default true.

max_results

string

no

Roster modes. Rows per brokerage or zip, 1 to 1000. Default 100.

max_charge_usd

string

no

Optional. The run stops before the row that would take its charges over this amount.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

Event

Free plan

Bronze

Silver

Gold

agent-resolved, per matched lookup row

$0.005

$0.00475

$0.0045

$0.00425

roster-row, per roster row

$0.002

$0.0019

$0.0018

$0.0017

apify-actor-start, per run start

$0.0005

$0.000475

$0.00045

$0.000425

Ambiguous, not found, unsupported state, and capped rows are never charged.

Your keys

The actor needs no provider key. It reads MMG's own index of the state license registers through a Mamba Labs service and holds no key of its own. Each actor run sends its own Apify run token to that service, which reads the run from the Apify API on every request to confirm it is a live run of this actor. The service caches no result and never stores or logs the token.

Full actor documentation

apify.com/mambalabs/agent-brokerage-resolver

License

MIT. See LICENSE.

Available Tools

1 tool
resolve_agent_brokerageResolve agent brokerageA
Read-onlyIdempotent

Look up a licensed US real estate agent on the official state license register and get the brokerage of record, the brokerage's active agent count and size band (1, 2-15, 16-50, 51+), and the agent's license status and expiry. Covers 19 states; brokerage data in CA, IA, MO, NV, NY, OH, OR, TX, and VT. Three modes: lookup (one agent or a list, by license number or by name), roster_firm (active agents at one brokerage), and roster_zip (brokerage offices in a zip code, NY, MO, OR, and VT). Returns no emails, phone numbers, or home addresses. Ambiguous or unmatched inputs return a free row with row_status explaining why. A run that does not succeed is returned as an error with its run ID. Read-only; requires an APIFY_TOKEN and consumes Apify credits per matched row.

Inputs: zip, city, mode, zips, +11 more.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.5/5.0

    Scored across 1 tool

    Disambiguation5/5

    With a single tool, there is no possibility of misselection between tools. The tool's purpose (resolving an agent to a brokerage via three explicit modes) is unambiguous.

    Naming Consistency5/5

    The sole tool uses a clear snake_case verb_noun pattern (resolve_agent_brokerage). With only one tool there is no internal inconsistency, and the name is readable and domain-specific.

    Tool Count3/5

    One tool for an entire server is on the thin side; the three modes are packed into a single tool rather than exposed as separate operations. It is defensible for a narrow resolver, but by the stated guidance 1-2 tools is borderline.

    Completeness4/5

    The lookup, roster_firm, and roster_zip modes cover the main access patterns for agent and brokerage data. Minor gaps exist (e.g., no direct supported-states/coverage query or explicit brokerage lookup by name), but core workflows are covered.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Real-time contractor license verification across 45 US states. Verifies license status, expiration, and disciplinary history directly against state licensing board portals.
      4
      53 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents and procurement systems to verify contractor licenses against official state boards, search contractors by trade and location, audit workers' comp, surety bonds and OSHA safety records, and check SAM.gov federal debarment status. It returns a deterministic ALLOW/WARN/BLOCK compliance decision plus registry health metrics for US trade contractors.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables listing and verifying licensed contractors across California, Texas, Washington, Oregon, and Louisiana by state, trade, city, county, license number, or business name, returning license status, expiration, classifications, owners, address, and phone.
      1
      317 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants and agents to query U.S. real estate data, including property lookups, comparables, property searches, skip tracing, phone/address verification, and investor buy boxes, through plain-language requests.
      1
      MIT