AI agents invoke openclaw_send_session to trigger actions in LocalAnt. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Sending a message to an external session (OpenClaw) constitutes triggering an external operation whose effects depend on the message content. Given the server context (shell, browser automation), the session could execute arbitrary actions. Confidence is reduced due to the DEPRECATED flag and lack of detail about what OpenClaw is or does.
From the tool's definition 'Send a message to an OpenClaw session' — triggers external operation on a running session; server description mentions 'shell commands, browser automation' context; marked DEPRECATED
Attacks that exploit this kind of access
${DEPRECATED} Send a message to an OpenClaw session. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalAnt MCP server in PolicyLayer and add a rule for openclaw_send_session: 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 LocalAnt. Nothing to install.
openclaw_send_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the openclaw_send_session 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 openclaw_send_session. 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.
openclaw_send_session is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →