Search conversation history across all Claude instances
AI agents call claude_senator_search_memories to retrieve information from Claude Senator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries conversation history data without modifying, deleting, or executing operations. However, severity is elevated to medium rather than low because the data being searched (conversation history across multiple Claude instances) may contain sensitive context, secrets, or private information that could be exposed if an AI agent misuses search queries to extract confidential details.
From the tool's definition Tool name contains 'search' and description states 'Search conversation history across all Claude instances' — a retrieval operation with no modification capability.
Attacks that exploit this kind of access
Search conversation history across all Claude instances. It is categorised as a Read tool in the Claude Senator MCP Server, which means it retrieves data without modifying state.
Register the Claude Senator MCP server in PolicyLayer and add a rule for claude_senator_search_memories: 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 Senator. Nothing to install.
claude_senator_search_memories 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 claude_senator_search_memories 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 claude_senator_search_memories. 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.
claude_senator_search_memories is provided by the Claude Senator MCP server (vvkmnn/claude-senator-mcp). 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 →