Pipeline: Read shapefile, build spatial weights, optionally transform, and save to file. Parameters: - data_path: Path to point shapefile or GeoPackage - method: 'queen', 'rook', 'distance_band', 'knn' - id_field: Optional field name for IDs - threshold: Distance threshold (required if method='di...
AI agents use build_transform_and_save_weights 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.
This tool reads geospatial data, computes spatial weights, and writes the result to a file. The primary side effect is creating/writing a new file on disk. This is reversible (the file can be deleted), so Write is the appropriate category rather than Destructive. Severity is medium because it writes to arbitrary file paths specified by the caller, which could overwrite existing files.
From the tool's definition 'Pipeline: Read shapefile, build spatial weights, optionally transform, and save to file' and 'output_path: File path to save weights'
Documented attack patterns abuse exactly the kind of access build_transform_and_save_weights 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 build_transform_and_save_weights:
{
"version": "1",
"default": "deny",
"tools": {
"build_transform_and_save_weights": {
"limits": [
{
"counter": "build_transform_and_save_weights_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}build_transform_and_save_weights 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.
Pipeline: Read shapefile, build spatial weights, optionally transform, and save to file. Parameters: - data_path: Path to point shapefile or GeoPackage - method: 'queen', 'rook', 'distance_band', 'knn' - id_field: Optional field name for IDs - threshold: Distance threshold (required if method='distance_band') - k: Number of neighbors (required if method='knn') - binary: True for binary weights, False for inverse distance (DistanceBand only) - transform_type: 'r', 'v', 'b', 'o', or 'd' (optional) - output_path: File path to save weights - format: 'gal' or 'gwt' - overwrite: Allow overwriting if file exists. 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 build_transform_and_save_weights: 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.
build_transform_and_save_weights 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 build_transform_and_save_weights 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 build_transform_and_save_weights. 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.
build_transform_and_save_weights 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.