INTERNAL: redeem a one-shot code for a session token. The /kiosk/r/:code HTTP handler calls this server-side. Uses UPDATE...RETURNING so a race produces exactly one winner; expired codes fail atomically.
AI agents invoke maker_redeem_code to trigger actions in Crow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool redeems a one-time code and exchanges it for a session token via an atomic database UPDATE. It is not purely a read (it mutates state by consuming the code), not a simple write (it triggers authentication/authorization side effects), and not destructive in the irreversible data-deletion sense.
From the tool's definition 'redeem a one-shot code for a session token', 'UPDATE...RETURNING so a race produces exactly one winner; expired codes fail atomically'
Documented attack patterns abuse exactly the kind of access maker_redeem_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for maker_redeem_code:
{
"version": "1",
"default": "deny",
"tools": {
"maker_redeem_code": {
"limits": [
{
"counter": "maker_redeem_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} maker_redeem_code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
INTERNAL: redeem a one-shot code for a session token. The /kiosk/r/:code HTTP handler calls this server-side. Uses UPDATE...RETURNING so a race produces exactly one winner; expired codes fail atomically. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for maker_redeem_code: 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 Crow. Nothing to install.
maker_redeem_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the maker_redeem_code 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 maker_redeem_code. 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.
maker_redeem_code is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.