Simple connectivity test returning a static ok status.
AI agents call connection_test to retrieve information from Tensorus MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only queries the status of a connection and returns a predetermined response. It retrieves information without modifying, creating, deleting, or executing any operations on data or external systems. This is a safe diagnostic operation typical of read-only health checks.
From the tool's definition Tool name is 'connection_test' and description states it is a 'Simple connectivity test returning a static ok status.' This performs a health check with no side effects.
Attacks that exploit this kind of access
Simple connectivity test returning a static ok status. It is categorised as a Read tool in the Tensorus MCP MCP Server, which means it retrieves data without modifying state.
Register the Tensorus MCP server in PolicyLayer and add a rule for connection_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 Tensorus MCP. Nothing to install.
connection_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 connection_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 connection_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.
connection_test is provided by the Tensorus MCP server (tensorus/mcp). 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 →