AI agents call get_integration 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 information about a single integration without modifying, deleting, or executing any operations. The explicit redaction of sensitive credential data further confirms it is designed as a safe read operation. No destructive, write, execute, or financial actions are performed.
From the tool's definition Tool description states 'Get one Nango integration' with credential fields redacted, indicating a retrieval operation with no side effects. The verb 'Get' combined with 'Credential-like response fields are redacted' confirms this is a read-only query.
Attacks that exploit this kind of access
Get one Nango integration. 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_integration: 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_integration 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_integration 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_integration. 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_integration 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 →