hybrid_search
AI agents call hybrid_search to retrieve information from ContextForge MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search tools are retrieval operations with no side effects. Without a description, classification relies on the tool name and sibling context. The 'search' function suggests querying across federated services (MCP, REST, gRPC) without modifying data.
From the tool's definition Tool name 'hybrid_search' indicates a search operation that retrieves data. Description is empty, limiting confidence. Based on naming convention and context among sibling tools (add_content, add_edge, etc.), this appears to be a read-only query tool.
Attacks that exploit this kind of access
hybrid_search. It is categorised as a Read tool in the ContextForge MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the ContextForge MCP Gateway MCP server in PolicyLayer and add a rule for hybrid_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 ContextForge MCP Gateway. Nothing to install.
hybrid_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 hybrid_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 hybrid_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.
hybrid_search is provided by the ContextForge MCP Gateway MCP server (jrmatherly/mcp-context-forge). 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 →