MCP Tool: Save any GIS-MCP result dict to files, only when the user requests. Args: data: The dictionary returned by any GIS-MCP tool. filename: Base filename without extension. formats: List of formats to save (default = all). folder: Target folder (relative to configured storage directory, or a...
AI agents use save_results to create or update resources in GIS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GIS MCP Server environment.
The tool writes geospatial analysis results to persistent storage in multiple formats. While it modifies the filesystem, the operation is reversible (files are not encrypted or locked), and there is no destruction of existing data or execution of arbitrary code. It falls under Write rather than Execute because it merely persists structured data outputs without triggering external operations or code execution.
From the tool's definition Tool creates and saves files to disk ('save_results', 'saved_files mapping format -> path'). This is a reversible data creation/modification operation—files can be edited or deleted afterward.
Documented attack patterns abuse exactly the kind of access save_results gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GIS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for save_results:
{
"version": "1",
"default": "deny",
"tools": {
"save_results": {
"limits": [
{
"counter": "save_results_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_results stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
MCP Tool: Save any GIS-MCP result dict to files, only when the user requests. Args: data: The dictionary returned by any GIS-MCP tool. filename: Base filename without extension. formats: List of formats to save (default = all). folder: Target folder (relative to configured storage directory, or absolute path). Returns: Dict with 'saved_files' mapping format -> path. It is categorised as a Write tool in the GIS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GIS MCP Server MCP server in PolicyLayer and add a rule for save_results: 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 GIS MCP Server. Nothing to install.
save_results 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 save_results 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 save_results. 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.
save_results is provided by the GIS MCP Server MCP server (mahdin75/gis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GIS MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
98 GIS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.