Search the team knowledge base. Finds content indexed by any team member.
AI agents call lctx_team_search to retrieve information from Logica Context 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 data from an indexed knowledge base without creating, modifying, deleting, or executing anything. It is a passive search interface, characteristic of the Read category. Severity is low because searching existing data carries minimal risk—no unintended state changes, financial impact, or resource consumption beyond normal query overhead is plausible.
From the tool's definition The tool description states it "Search[es] the team knowledge base" and "Finds content indexed by any team member." The name prefix "lctx_" and verb "search" indicate a read-only query operation with no mutation or side effects.
Attacks that exploit this kind of access
Search the team knowledge base. Finds content indexed by any team member. It is categorised as a Read tool in the Logica Context MCP Server, which means it retrieves data without modifying state.
Register the Logica Context MCP server in PolicyLayer and add a rule for lctx_team_search: 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 Logica Context. Nothing to install.
lctx_team_search 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 lctx_team_search 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 lctx_team_search. 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.
lctx_team_search is provided by the Logica Context MCP server (rovemark/logica-context). 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 →