Test Confluence connection
AI agents call confluence_test_connection to retrieve information from Confluence MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Testing a connection is a non-invasive query that only checks the status of an external service. It has no side effects, does not retrieve sensitive data beyond what is necessary for diagnosis, and does not create, modify, delete, or execute operations. This is a standard Read category tool with minimal blast radius.
From the tool's definition Tool description states 'Test Confluence connection' — a read-only diagnostic operation that verifies connectivity without modifying or executing any data-altering operations.
Attacks that exploit this kind of access
Test Confluence connection. It is categorised as a Read tool in the Confluence MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Confluence MCP Server MCP server in PolicyLayer and add a rule for confluence_test_connection: 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 Confluence MCP Server. Nothing to install.
confluence_test_connection 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 confluence_test_connection 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 confluence_test_connection. 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.
confluence_test_connection is provided by the Confluence MCP Server MCP server (manateeit/confluence-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 →