Pick an Agency's matching engine. Given a buyer brief (services needed, location, budget, industry), returns a short ranked shortlist of agencies that best fit - the same logic behind the free 'Get Matched' tool. WHEN TO USE: when the user describes their needs/project and wants a RECOMMENDATION ...
AI agents call match_agencies to retrieve information from Pick an Agency without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
city | string | — | Target city. |
limit | integer | — | Shortlist size (default 5). |
budget | string | — | Monthly budget, e.g. '$5k-10k' or '5000'. |
country | string | — | Target country. |
industry | string | — | Buyer's industry, e.g. 'E-commerce'. |
services | array | Yes | Services the buyer needs, e.g. ['SEO', 'Content Marketing']. |
platforms | array | — | Ad platforms, e.g. ['Meta Ads', 'Google Ads']. |
Parameters from the server's own tool schema.
match_agencies performs a query-like operation against a database of 47,000+ agencies and returns ranked results based on buyer input criteria. It retrieves and filters existing data with no side effects, modifications, or external operations triggered. This is a classic Read operation—data retrieval without reversible or irreversible changes.
From the tool's definition Tool 'returns a short ranked shortlist' of agencies based on matching logic; described as a recommendation engine that filters and presents existing data without modifying, creating, or deleting anything.
Attacks that exploit this kind of access
Pick an Agency's matching engine. Given a buyer brief (services needed, location, budget, industry), returns a short ranked shortlist of agencies that best fit - the same logic behind the free 'Get Matched' tool. WHEN TO USE: when the user describes their needs/project and wants a RECOMMENDATION ('I need a social media agency in Paris, ~$5k/month'). Requires at least one service. Use search_agencies instead for open browsing/filtering without a brief; use get_agency to drill into one result afterwards. It is categorised as a Read tool in the Pick an Agency MCP Server, which means it retrieves data without modifying state.
match_agencies accepts 7 parameters: city, limit, budget, country, industry, services, platforms. Required: services. The full parameter table on this page comes from the server's own tool schema.
Register the Pick an Agency MCP server in PolicyLayer and add a rule for match_agencies: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pick an Agency. Nothing to install.
match_agencies is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the match_agencies rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for match_agencies. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
match_agencies is provided by the Pick an Agency MCP server (https://www.pickanagency.com/api/mcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →