search_resources
AI agents call search_resources to retrieve information from Mcp Openhexa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool description is empty, contextual evidence from the server description, sibling tool names, and function suggests this is a search/query operation that retrieves data without modifying or deleting anything. Confidence is lowered from 0.85 to 0.75 due to the missing description, but the pattern is clear.
From the tool's definition The tool name 'search_resources' and its position among sibling tools (get_dataset_details, list_datasets, get_pipeline_details, list_dataset_files, etc.) that are all retrieval operations, combined with the server's stated capability to 'query workspaces,…
Attacks that exploit this kind of access
search_resources. It is categorised as a Read tool in the Mcp Openhexa MCP Server, which means it retrieves data without modifying state.
Register the Mcp Openhexa MCP server in PolicyLayer and add a rule for search_resources: 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 Mcp Openhexa. Nothing to install.
search_resources 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_resources 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_resources. 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_resources is provided by the Mcp Openhexa MCP server (mcrimi/mcp-openhexa). 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 →