This record as markdown: /tools/cowork-bench/fetch-json.md
What fetch_json does on Cowork Bench
AI agents call fetch_json to retrieve information from Cowork Bench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why fetch_json is rated Low
This tool retrieves remote data (a JSON file) without side effects. It is a straightforward read operation analogous to GET requests or data fetching. No data is modified, deleted, or executed. The severity is low because fetching remote JSON is generally safe unless the URL is attacker-controlled and the data is subsequently misused, but the tool itself performs only retrieval.
From the tool's definition Tool name 'fetch_json' and description 'Fetch a JSON file from a URL' indicate retrieval of data with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
The rule that runs fetch_json safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fetch_json, this is the rule to start with:
fetch_json 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 Cowork Bench, apply this rule, and every fetch_json call is checked against it from then on.
Questions about fetch_json
Fetch a JSON file from a URL. It is categorised as a Read tool in the Cowork Bench MCP Server, which means it retrieves data without modifying state.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for fetch_json: 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 Cowork Bench. Nothing to install.
fetch_json 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_json 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_json. 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_json is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue