AI agents call bundle_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.
bundle_search performs information retrieval only: it searches a knowledge vault using FTS5 and bundles results for consumption. No data is created, modified, deleted, or executed. The tool has no side effects beyond returning search results. Severity is low because misuse (e.g., searching for sensitive terms) is confined to data disclosure and cannot trigger destructive or financial actions.
From the tool's definition Tool description states 'Run an FTS search and concatenate matched bodies' — a read-only full-text search operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Run an FTS search and concatenate matched bodies into a single prompt-ready bundle (XML. 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 bundle_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.
bundle_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 bundle_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 bundle_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.
bundle_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 →