List the tools registered on a WASM agent sandbox. Use when native Task is wrong because the tool registry lives inside the WASM runtime and cannot be inspected from the host via standard reflection.
AI agents call wasm_agent_tools to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is primarily a Read operation—it lists/enumerates tools and their metadata from a WASM sandbox, with no side effects. Severity is medium rather than low because the information disclosed (available tools, their capabilities, and registry state) could inform subsequent attack vectors or privilege escalation if an attacker gains access to this tool.
From the tool's definition Tool name 'wasm_agent_tools' and description 'List the tools registered on a WASM agent sandbox' indicates a query/listing operation that retrieves information about available tools within a WASM runtime without modifying anything.
Attacks that exploit this kind of access
List the tools registered on a WASM agent sandbox. Use when native Task is wrong because the tool registry lives inside the WASM runtime and cannot be inspected from the host via standard reflection. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for wasm_agent_tools: 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 Claude Flow. Nothing to install.
wasm_agent_tools 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 wasm_agent_tools 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 wasm_agent_tools. 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.
wasm_agent_tools is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.