// SCAN REPORT

Pick an Agency

3 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 2 Jul 2026

0 can modify or destroy data

3 read-only

3 tools total

Verified server · catalogue entry verified 02/07/2026 · full schemas captured for 3 of 3 tools

How to control Pick an Agency ↓

TOOL MAP

What Pick an Agency exposes to your agents

Read (3) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Pick an Agency costs in tokens

796 tokens of tool definitions, loaded on every request

0.4% of a 200k context window

321 heaviest tool: search_agencies

Full per-tool breakdown → Model it in the token calculator →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Pick an Agency

PolicyLayer is an MCP gateway — it sits between your AI agents and Pick an Agency, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "get_agency": {
    "limits": [
      {
        "counter": "get_agency_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Pick an Agency — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PICK AN AGENCY →

Instant setup, no code required.

FULL CATALOGUE

All 3 Pick an Agency tools

READ 3 tools

Read get_agency Fetch a single agency's full profile from Pick an Agency by its slug (the last path segment of its profile URL Read match_agencies Pick an Agency's matching engine. Given a buyer brief (services needed, location, budget, industry), returns a Read search_agencies Search Pick an Agency's directory of 47,000+ marketing agencies. Filter by free-text query, service (e.g. SEO,

FAQ

Questions about Pick an Agency

Is the Pick an Agency MCP server safe to use without restrictions? +

The Pick an Agency server is primarily read-only with 3 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Pick an Agency MCP server expose? +

3 tools across 1 categories: Read. 3 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Pick an Agency? +

Register the Pick an Agency MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Pick an Agency tool call.

Deterministic rules across all 3 Pick an Agency tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PICK AN AGENCY →

Instant setup, no code required.

3 Pick an Agency tools catalogued and risk-classified — across an index of 43,000+ MCP servers.