Get the structured todo list of a WASM agent as JSON. Use when native Task is wrong because the todo state lives inside the sandboxed WASM runtime and is not visible to the host process.
AI agents call wasm_agent_todos 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 tool performs data retrieval from a sandboxed WASM runtime with no side effects. It queries the internal state of a WASM agent and returns structured data (JSON), which is characteristic of a Read operation. The sandboxed context mitigates risk further, as the tool cannot modify, execute, or delete anything.
From the tool's definition The tool description explicitly states it 'Get[s] the structured todo list of a WASM agent as JSON', indicating a retrieval operation. No modification, deletion, or execution capabilities are mentioned.
Attacks that exploit this kind of access
Get the structured todo list of a WASM agent as JSON. Use when native Task is wrong because the todo state lives inside the sandboxed WASM runtime and is not visible to the host process. 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_todos: 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_todos 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_todos 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_todos. 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_todos 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.