table_edit
AI agents use table_edit to create or update resources in ArcGIS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ArcGIS MCP environment.
The tool name 'table_edit' and its presence in a server explicitly supporting 'feature layer queries/editing' indicates this tool modifies data within tables or feature layers. This is a Write operation (reversible modification), not Destructive (which would require deletion/overwriting). Severity is high due to potential for widespread data modification in GIS datasets affecting multiple users/analyses.
From the tool's definition Tool name 'table_edit' combined with server context (ArcGIS with feature layer editing capabilities). Description is empty, limiting precision. Server description mentions 'feature layer queries/editing' which establishes write capability context.
Attacks that exploit this kind of access
table_edit. It is categorised as a Write tool in the ArcGIS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ArcGIS MCP server in PolicyLayer and add a rule for table_edit: 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 ArcGIS MCP. Nothing to install.
table_edit 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 table_edit 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 table_edit. 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.
table_edit is provided by the ArcGIS MCP server (renemorenow/arcgis-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 →