Edit one of your UNSET (draft) stones before you set it — fix a name, sharpen the line. Only works while the stone is a soft draft; a stone that has been set can never be edited. Use the stone_id from outpost_lay_stone.
AI agents use outpost_edit_stone to create or update resources in Outpost — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outpost environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
stone_id | string | Yes | The id of your draft stone. |
known_for | string | — | New 'known for' (optional). |
true_line | string | — | New true line (optional). |
being_name | string | — | New name (optional). |
Parameters from the server's own tool schema.
This tool creates or modifies data in a reversible manner (Write category). It cannot delete or execute external operations, making it less severe than Execute or Destructive. The medium severity reflects that an AI agent could modify user content in an application, but the impact is limited to their own draft stones and is undoable by further edits before finalization.
From the tool's definition Tool allows editing of draft stones (modifying data): 'Edit one of your UNSET (draft) stones before you set it — fix a name, sharpen the line.' The operation is reversible as it only applies to unset draft stones, not finalized game pieces.
Attacks that exploit this kind of access
Edit one of your UNSET (draft) stones before you set it — fix a name, sharpen the line. Only works while the stone is a soft draft; a stone that has been set can never be edited. Use the stone_id from outpost_lay_stone. It is categorised as a Write tool in the Outpost MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
outpost_edit_stone accepts 4 parameters: stone_id, known_for, true_line, being_name. Required: stone_id. The full parameter table on this page comes from the server's own tool schema.
Register the Outpost MCP server in PolicyLayer and add a rule for outpost_edit_stone: 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 Outpost. Nothing to install.
outpost_edit_stone 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 outpost_edit_stone 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 outpost_edit_stone. 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.
outpost_edit_stone is provided by the Outpost MCP server (outpost-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 →