AI agents use apply_connection_convention to create or update resources in Nango — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nango environment.
This tool modifies an existing connection by applying tags and metadata to it. This is a reversible write operation - the tags and metadata can be changed or removed later. It does not delete data (which would be Destructive), does not execute arbitrary code (which would be Execute), and does not involve financial transactions.
From the tool's definition Tool description states it will 'Apply suggested Nango MCP tags and metadata to an existing connection', which is a modification operation that creates or updates connection metadata.
Attacks that exploit this kind of access
Apply suggested Nango MCP tags and metadata to an existing connection. It is categorised as a Write tool in the Nango MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nango MCP server in PolicyLayer and add a rule for apply_connection_convention: 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.
apply_connection_convention is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the apply_connection_convention 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 apply_connection_convention. 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.
apply_connection_convention 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 →