Update a canvas using canvases.edit. Pass Slack params in
AI agents use update_canvas to create or update resources in Slack Max API MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack Max API MCP environment.
This tool modifies (but does not delete) existing Slack canvas data. Write category is appropriate as the action is reversible. Severity is medium because an agent could alter important team documentation or shared canvases, but the scope is limited to canvas objects within Slack rather than workspace-wide destructive impact.
From the tool's definition update_canvas uses canvases.edit to modify canvas content; described as 'Update a canvas' which is a reversible modification operation.
Attacks that exploit this kind of access
Update a canvas using canvases.edit. Pass Slack params in. It is categorised as a Write tool in the Slack Max API MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slack Max API MCP server in PolicyLayer and add a rule for update_canvas: 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 Slack Max API MCP. Nothing to install.
update_canvas 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 update_canvas 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 update_canvas. 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.
update_canvas is provided by the Slack Max API MCP server (jeongwoobin335/slack-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 →