AI agents call openclaw_get_session_history to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries session history data without modifying, executing, deleting, or causing financial transactions. The action is a simple data retrieval with no side effects. The deprecated status further reduces risk. Confidence is slightly lowered (0.85 vs 1.0) due to lack of detail about what 'OpenClaw session history' contains or what exposure it might present, but the read-only nature is clear.
From the tool's definition Tool name 'openclaw_get_session_history' indicates retrieval of historical session data. Description states 'Get OpenClaw session history,' using the verb 'Get' which is a read operation.
Attacks that exploit this kind of access
${DEPRECATED} Get OpenClaw session history. It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for openclaw_get_session_history: 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_get_session_history 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 openclaw_get_session_history 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_get_session_history. 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_get_session_history 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 →