Test connectivity to a data source and list available tables.
AI agents call sources.test to retrieve information from Kelnix Datamind Curator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs non-destructive diagnostic checks and metadata queries only. It retrieves information about data source connectivity and schema without creating, modifying, or deleting data. It poses minimal risk when misused by an AI agent—the worst outcome is discovering which tables exist or connection status.
From the tool's definition Tool name 'sources.test' and description 'Test connectivity to a data source and list available tables' indicate read-only operations: testing connectivity (diagnostic) and listing tables (metadata retrieval).
Attacks that exploit this kind of access
Test connectivity to a data source and list available tables. It is categorised as a Read tool in the Kelnix Datamind Curator MCP Server, which means it retrieves data without modifying state.
Register the Kelnix Datamind Curator MCP server in PolicyLayer and add a rule for sources.test: 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 Kelnix Datamind Curator. Nothing to install.
sources.test 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 sources.test 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 sources.test. 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.
sources.test is provided by the Kelnix Datamind Curator MCP server (kelnixsolutions/kelnix-datamind-curator). 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 →