Search conversations by semantic similarity.
AI agents call search_conversations to retrieve information from Session Buddy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval (searching/querying) with no side effects. It returns results based on semantic similarity matching against stored conversations but does not create, modify, delete, or execute any operations. The blast radius of misuse is minimal—an agent could retrieve unintended conversation data, but cannot alter system state or cause irreversible harm.
From the tool's definition Tool name 'search_conversations' and description 'Search conversations by semantic similarity' indicates a read-only query operation that retrieves matching conversation records without modifying or deleting data.
Attacks that exploit this kind of access
Search conversations by semantic similarity. It is categorised as a Read tool in the Session Buddy MCP Server, which means it retrieves data without modifying state.
Register the Session Buddy MCP server in PolicyLayer and add a rule for search_conversations: 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 Session Buddy. Nothing to install.
search_conversations 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 search_conversations 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 search_conversations. 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.
search_conversations is provided by the Session Buddy MCP server (lesleslie/session-buddy). 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 →