AI agents call fetch_token_broadcasts to retrieve information from Test without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves broadcast information for a token without modifying, deleting, or executing operations. It is a straightforward read operation with minimal risk if misused by an AI agent—at worst, an agent could retrieve unwanted token broadcast data, but no data would be altered or sensitive actions triggered.
From the tool's definition Tool name is 'fetch_token_broadcasts' with description 'Fetch broadcasts for a specific token'. The verb 'fetch' indicates data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Fetch broadcasts for a specific token. It is categorised as a Read tool in the Test MCP Server, which means it retrieves data without modifying state.
Register the Test MCP server in PolicyLayer and add a rule for fetch_token_broadcasts: 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 Test. Nothing to install.
fetch_token_broadcasts 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_token_broadcasts 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_token_broadcasts. 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_token_broadcasts is provided by the Test MCP server (jusscubs/mcp-server-test). 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 →