fetch
Retrieve one public AgentTool canon entry by exact stable ID, supplied directly or returned by search. Returns its complete public registry record, citation URL, and metadata. This tool reads public data only.
This record as markdown: /tools/dev-agenttool-agenttool/fetch.md
What fetch does on Agenttool
AI agents call fetch to retrieve information from Agenttool without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why fetch is rated Low
Even though fetch only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs fetch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agenttool, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch, this is the rule to start with:
fetch is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Agenttool, apply this rule, and every fetch call is checked against it from then on.
Questions about fetch
Retrieve one public AgentTool canon entry by exact stable ID, supplied directly or returned by search. Returns its complete public registry record, citation URL, and metadata. This tool reads public data only. It is categorised as a Read tool in the Agenttool MCP Server, which means it retrieves data without modifying state.
Register the Agenttool MCP server in PolicyLayer and add a rule for fetch: 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 Agenttool. Nothing to install.
fetch 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 fetch 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 fetch. 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.
fetch is provided by the Agenttool MCP server (https://api.agenttool.dev/v1/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agenttool, and thousands of servers like it.
This server
Across the catalogue