sandbox_credentials_grant
Run sandbox-credentials.grant through the Appaloft application operation catalog. Shared with HTTP/API.
This record as markdown: /tools/appaloft-mcp/sandbox-credentials-grant.md
What sandbox_credentials_grant does on Appaloft
AI agents invoke sandbox_credentials_grant to trigger actions in Appaloft. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
grantId | string | Yes | |
sandboxId | string | Yes | |
secretRef | string | Yes | |
destination | string | Yes | |
parameterName | string | — | |
transformation | string | Yes |
Parameters from the server's own tool schema.
Why sandbox_credentials_grant is rated High
This tool grants credentials, a privileged operation that triggers execution of a grantable action. While it modifies state (credentials/permissions), its primary function is to execute a granted operation in an application context. The 'Shared with HTTP/API' note and operation catalog reference confirm it invokes external side effects.
From the tool's definition Tool name 'sandbox_credentials_grant' and description 'Run sandbox-credentials.grant through the Appaloft application operation catalog' indicate execution of a credentials-granting operation.
Risk signalsAccepts file system path (destination)
Attacks that exploit this kind of access
The rule that runs sandbox_credentials_grant safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Appaloft, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sandbox_credentials_grant, this is the rule to start with:
sandbox_credentials_grant 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Appaloft, apply this rule, and every sandbox_credentials_grant call is checked against it from then on.
Questions about sandbox_credentials_grant
Run sandbox-credentials.grant through the Appaloft application operation catalog. Shared with HTTP/API. It is categorised as a Execute tool in the Appaloft MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
sandbox_credentials_grant accepts 6 parameters: grantId, sandboxId, secretRef, destination, parameterName, transformation. Required: grantId, sandboxId, secretRef, destination, transformation. The full parameter table on this page comes from the server's own tool schema.
Register the Appaloft MCP server in PolicyLayer and add a rule for sandbox_credentials_grant: 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 Appaloft. Nothing to install.
sandbox_credentials_grant 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 sandbox_credentials_grant 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 sandbox_credentials_grant. 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.
sandbox_credentials_grant is provided by the Appaloft MCP server (@appaloft/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Appaloft, and thousands of servers like it.
Across the catalogue