Send a command to a connected OGrid instance and wait for the result. Command types: update_cell - { rowIndex: number, columnId: string, value: unknown } set_filter - { columnId: string, value: string | string[] } clear_filters - {} set_sort - { sortModel: [{ columnId, direction: "asc"|"desc" }] ...
AI agents use send_grid_command to create or update resources in Ogrid — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ogrid environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
type | string | Yes | Command type |
gridId | string | Yes | Grid ID as registered by connectGridToBridge() |
payload | object | Yes | Command-specific payload (see tool description for fields per type) |
timeoutMs | integer | — | How long to wait for the app to execute the command (default: 5000ms) |
Parameters from the server's own tool schema.
The update_cell command creates or modifies data in the grid, making this a Write operation. While filtering, sorting, and pagination are reversible state changes, the update_cell capability is the most severe aspect. This is not Execute (no arbitrary code), not Destructive (changes are reversible), not Financial.
From the tool's definition Tool description states 'Send a command to a connected OGrid instance' with command types including 'update_cell' which modifies data (rowIndex, columnId, value). Other commands like set_filter, set_sort, and go_to_page modify UI/state reversibly.
Risk signalsAccepts raw HTML/template content (payload)
Attacks that exploit this kind of access
Send a command to a connected OGrid instance and wait for the result. Command types: update_cell - { rowIndex: number, columnId: string, value: unknown } set_filter - { columnId: string, value: string | string[] } clear_filters - {} set_sort - { sortModel: [{ columnId, direction: "asc"|"desc" }] } go_to_page - { page: number }. It is categorised as a Write tool in the Ogrid MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
send_grid_command accepts 4 parameters: type, gridId, payload, timeoutMs. Required: type, gridId, payload. The full parameter table on this page comes from the server's own tool schema.
Register the Ogrid MCP server in PolicyLayer and add a rule for send_grid_command: 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 Ogrid. Nothing to install.
send_grid_command 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 send_grid_command 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 send_grid_command. 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.
send_grid_command is provided by the Ogrid MCP server (@alaarab/ogrid-mcp). 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 →