List all API providers (domains like "googleapis.com", "azure.com", "amazonaws.com") tracked in the APIs.guru directory. Returns { count, providers }. Use this to browse the directory by organization before drilling into a specific provider or API.
AI agents call list_providers to retrieve information from Mcp Apis Guru without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries metadata about API providers from a public directory without modifying, executing, deleting, or moving any data. It has no side effects and presents zero risk of unintended consequences even if invoked repeatedly or with unexpected arguments. The blast radius of misuse is minimal—at worst, an agent learns about available APIs, which is already public information.
From the tool's definition Tool description explicitly states it 'List all API providers' and 'Returns { count, providers }'. The word 'list' indicates a read-only query operation with no side effects. The purpose is to 'browse the directory', which is purely informational retrieval.
Attacks that exploit this kind of access
List all API providers (domains like "googleapis.com", "azure.com", "amazonaws.com") tracked in the APIs.guru directory. Returns { count, providers }. Use this to browse the directory by organization before drilling into a specific provider or API. It is categorised as a Read tool in the Mcp Apis Guru MCP Server, which means it retrieves data without modifying state.
Register the Mcp Apis Guru MCP server in PolicyLayer and add a rule for list_providers: 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 Mcp Apis Guru. Nothing to install.
list_providers 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 list_providers 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 list_providers. 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.
list_providers is provided by the Mcp Apis Guru MCP server (https://gateway.pipeworx.io/apis-guru/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 →