AI agents call search_context to retrieve information from OmniHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or searches through existing memory data. The description is minimal ('Searches the user'), but the verb 'search' combined with the context of a memory management system clearly indicates a read-only operation that does not modify, delete, or execute external operations. No data is altered, and the blast radius of misuse is limited to information disclosure within the user's own memory store.
From the tool's definition Tool name 'search_context' and verb 'Searches' indicate a query/retrieval operation with no side effects on stored data.
Attacks that exploit this kind of access
Searches the user. It is categorised as a Read tool in the OmniHub MCP Server, which means it retrieves data without modifying state.
Register the OmniHub MCP server in PolicyLayer and add a rule for search_context: 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 OmniHub. Nothing to install.
search_context 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_context 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_context. 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_context is provided by the OmniHub MCP server (malharrrr/omnihub). 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 →