share_group_replace
AI agents use share_group_replace 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.
Based on the name pattern, this tool likely modifies group sharing configurations or membership, which are data changes that can be reversed (Write category). The empty description reduces confidence slightly. Severity is medium because incorrect group sharing changes could affect access controls for multiple users, but the impact is typically reversible through administrative action.
From the tool's definition Tool name is 'share_group_replace' which indicates modifying group membership or sharing settings. The verb 'replace' suggests reversible modification of data associations.
Attacks that exploit this kind of access
share_group_replace. 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 share_group_replace: 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.
share_group_replace 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 share_group_replace 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 share_group_replace. 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.
share_group_replace 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 →