AI agents call list_connections to retrieve information from A2db without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about saved database connections without side effects. The explicit statement that it returns 'no secrets' confirms it only reads non-sensitive metadata. It falls squarely in the Read category with low severity due to limited blast radius—an agent misuse would only expose connection names and database types already stored in the configuration.
From the tool's definition Tool name 'list_connections' and description 'List saved connections. Returns project/env/db and database type (no secrets)' indicate a read-only operation that retrieves metadata about configured database connections without exposing sensitive information or…
Attacks that exploit this kind of access
List saved connections. Returns project/env/db and database type (no secrets). It is categorised as a Read tool in the A2db MCP Server, which means it retrieves data without modifying state.
Register the A2db MCP server in PolicyLayer and add a rule for list_connections: 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 A2db. Nothing to install.
list_connections 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 list_connections 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 list_connections. 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.
list_connections is provided by the A2db MCP server (yoselabs/a2db). 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 →