AI agents call search to retrieve information from Kontexta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query tool that retrieves and ranks data from a knowledge vault. It has no capability to modify, delete, or execute code. The description explicitly states it returns search results without follow-up actions. Classification as Read is appropriate with low severity since misuse would only expose existing information within the vault, not cause data loss or execute arbitrary operations.
From the tool's definition Tool performs 'Full-text (SQLite FTS5) keyword search across files' and 'Returns ranked matches' — a query operation with no modifications or side effects.
Attacks that exploit this kind of access
Full-text (SQLite FTS5) keyword search across files. Returns ranked matches with inline match_excerpt and title_highlight (no follow-up. It is categorised as a Read tool in the Kontexta MCP Server, which means it retrieves data without modifying state.
Register the Kontexta MCP server in PolicyLayer and add a rule for 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 Kontexta. Nothing to install.
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 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 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.
search is provided by the Kontexta MCP server (safiyu/kontexta). 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 →