AI agents use add_table_join to create or update resources in QGIS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QGIS MCP environment.
Adding a table join modifies the structure and relationships of a vector layer by linking it to an external table, but this is reversible (joins can be removed). It does not delete data, execute arbitrary code, move money, or trigger uncontrolled external operations.
From the tool's definition Tool name 'add_table_join' combined with description 'Add a table join to a vector layer' indicates creation/modification of layer relationships and metadata. This is a write operation that modifies layer configuration.
Attacks that exploit this kind of access
Add a table join to a vector layer. It is categorised as a Write tool in the QGIS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the QGIS MCP server in PolicyLayer and add a rule for add_table_join: 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 QGIS MCP. Nothing to install.
add_table_join 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 add_table_join 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 add_table_join. 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.
add_table_join is provided by the QGIS MCP server (nkarasiak/qgis-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 →