Skip to main content
Glama
nkarasiak

QGIS MCP

by nkarasiak
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Execute Processing

execute_processing

Run QGIS Processing algorithms with custom parameters, and optionally load output layers into the project. Suitable for geoprocessing tasks like buffering, clipping, or raster analysis.

Instructions

Execute a QGIS Processing algorithm. Use get_algorithm_help to discover parameters. Layer params accept layer IDs or file paths. Set OUTPUT to 'memory:' for temp layers. timeout: seconds before the algorithm is cancelled (default 55). Raise it for heavy raster work, or use start_processing_job, which runs in the background with no limit. load_results: add the algorithm's outputs to the project and list them in 'loaded_layers' (the processing.runAndLoadResults() behaviour). This is the only way to keep a 'TEMPORARY_OUTPUT'/'memory:' result, which is otherwise discarded when the run ends. Only vector and raster destinations are loaded, never file or folder ones. ellipsoid: ellipsoid for distance/area measurements (e.g. 'EPSG:7030' for WGS 84, 'NONE' for planimetric). Default is the open project's ellipsoid.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
timeoutNo
algorithmYes
ellipsoidNo
parametersYes
load_resultsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.15.0
    • addedInput schema / properties / ellipsoid
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  2. Changed1 schema field changedv0.14.0
    • addedInput schema / properties / load_results
      Added value: +{
+  "default": false,
+  "type": "boolean"
+}
  3. Changed1 schema field changedv0.11.0
    • addedInput schema / properties / timeout
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  4. Changed3 schema fields changedv0.5.0
    • removedInput schema / properties / algorithm / title
      Removed value: -"Algorithm"
    • removedInput schema / properties / parameters / title
      Removed value: -"Parameters"
    • removedInput schema / title
      Removed value: -"execute_processingArguments"
  5. First observedv0.3.0

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden and does so very well. It discloses cancellation via timeout, memory-layer retention semantics, that load_results uses runAndLoadResults behavior, and that only vector/raster destinations are loaded. This is substantial behavior beyond what the schema reveals.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Every sentence earns its place, and the most actionable guidance is front-loaded. The parameter-focused sentences use a clear pattern, and the description remains tight despite covering several nuanced behaviors.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with no annotationsalert and no output schema, the description is remarkably complete. It covers parameter discovery, memory outputs, loading behavior, timeout handling, and ellipsoid semantics, giving an agent almost everything needed to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description compensates fully: it explains timeout defaults, ellipsoid examples and default, load_results impact, the 'memory:' output convention, and that layer parameters accept IDs or file paths. Even the dynamic parameters object is addressed by directing the agent to get_algorithm_help.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Execute a QGIS Processing algorithm.' It goes beyond the generic title by explaining the tool's role and pointing to get_algorithm_help for parameter discovery, which makes its scope clear relative to sibling tools like start_processing_job or run_model.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells the agent to use get_algorithm_help to discover parameters Alice and provides concrete guidance for heavy raster work: raise timeout or use start_processing_job for background execution. It clearly explains when load_results is necessary, though it does not contrast against every alternative such as execute_processing_batch.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools