AI agents call get_connection to retrieve information from Nango without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves connection information without side effects or modifications. While connections may contain sensitive metadata (auth tokens, endpoints, configuration), the explicit redaction of credential-like fields limits the blast radius. Classified as Read with medium severity due to the potential information disclosure of non-redacted connection details that could aid further attacks.
From the tool's definition Tool name 'get_connection' and description 'Get a Nango connection. Credential-like response fields are redacted' indicate retrieval of connection data without modification. The redaction of credential fields mitigates exposure risk.
Attacks that exploit this kind of access
Get a Nango connection. Credential-like response fields are redacted. It is categorised as a Read tool in the Nango MCP Server, which means it retrieves data without modifying state.
Register the Nango MCP server in PolicyLayer and add a rule for get_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 Nango. Nothing to install.
get_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 get_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 get_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.
get_connection is provided by the Nango MCP server (levsky22/nango-mcp-server). 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 →