Mint a short-lived SDK token for embedding the Onfido Web / iOS / Android SDKs in your frontend. The token is scoped to a single applicant and is how capture flows (document photo, selfie, video) run in-browser/in-app without exposing your API token.
AI agents use generate_sdk_token to create or update resources in Mcp Ap2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ap2 environment.
This tool creates (mints) a new credential/token, which is a Write operation. It does not read existing data, execute code, or perform destructive/financial actions. The severity is medium because a misused token could enable unauthorized identity capture flows on behalf of an applicant, though the token is short-lived and scoped to a single applicant, limiting blast radius.
From the tool's definition Mint a short-lived SDK token for embedding the Onfido Web / iOS / Android SDKs in your frontend. The token is scoped to a single applicant
Documented attack patterns abuse exactly the kind of access generate_sdk_token gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_sdk_token:
{
"version": "1",
"default": "deny",
"tools": {
"generate_sdk_token": {
"limits": [
{
"counter": "generate_sdk_token_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_sdk_token stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mint a short-lived SDK token for embedding the Onfido Web / iOS / Android SDKs in your frontend. The token is scoped to a single applicant and is how capture flows (document photo, selfie, video) run in-browser/in-app without exposing your API token. It is categorised as a Write tool in the Mcp Ap2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for generate_sdk_token: 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 Mcp Ap2. Nothing to install.
generate_sdk_token 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 generate_sdk_token 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 generate_sdk_token. 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.
generate_sdk_token is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.