AI agents use create_connect_session 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.
Session token creation is a Write operation: it generates a new authentication credential that enables subsequent API interactions. While not destructive or irreversible deletion, it does create a side effect (session state).
From the tool's definition Tool creates a Nango Connect session token, which modifies authentication state by generating a new session artifact. The description states 'Create a Nango Connect session token' — a generative action that produces a new, persistent resource.
Attacks that exploit this kind of access
Create a Nango Connect session token. 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 create_connect_session: 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.
create_connect_session 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 create_connect_session 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 create_connect_session. 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.
create_connect_session 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 →