Search team reflections with access control.
AI agents call search_team_knowledge 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 retrieves or queries existing team knowledge/reflections without creating, modifying, deleting, or executing anything. It is a search/query operation with protective access controls in place. No side effects beyond information retrieval are indicated. This is classic Read category behavior.
From the tool's definition Tool name 'search_team_knowledge' and description 'Search team reflections with access control' indicate querying/retrieval of stored knowledge. The verb 'search' and lack of any modification, deletion, or execution language confirms read-only behavior.
Attacks that exploit this kind of access
Search team reflections with access control. 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_team_knowledge: 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_team_knowledge 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_team_knowledge 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_team_knowledge. 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_team_knowledge 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 →