QGIS MCP

Overview Schema Source Related Servers Discussions Admin

Create Processing Model

create_processing_model

Creates a QGIS Processing Model (.model3) from a structured spec, saves it to the user models folder, and registers it in the Processing Toolbox. Resolves algorithm names and validates parameters automatically.

Instructions

Build QGIS Processing Model (.model3) from structured spec; save to user models folder, register in Processing Toolbox. Only call needed: algorithm discovery + param validation run in the plugin against the live registry, so do NOT call list_processing_algorithms or get_algorithm_help first. Pass keyword ('buffer') or full id ('native:buffer'); handler resolves it. Ambiguous hint returns candidate list to refine and retry. Bad param/output names reported with the valid set.

Spec: inputs: [{name, type, description?, default?, optional?, parent_layer? (for field/distance), options? (for enum)}]. Types: vector, feature_source, raster, field, number, integer, distance, string, boolean, extent, crs, point, file, folder, enum, multiple_layers. steps: [{id, algorithm, description?, parameters: {ALG_PARAM: value}}]. algorithm = keyword or full id. Param values: '@input_name' = model input value '$step_id.OUTPUT' = earlier step output '=expression' = QGIS expression at run time else = static literal (number/bool/string/list) outputs: [{name, from_step, from_output, description?}] = exposed outputs; omit to expose the last step OUTPUT as 'Result'.

Name collision appends a suffix (name_2.model3, ...). Response returns the actual 'name', the 'requested_name', and 'resolved_steps' (which algorithm each hint mapped to).

Input Schema

TableJSON Schema

Name	Required	Default
`name`	Yes
`group`	No	Models
`steps`	Yes
`inputs`	No
`outputs`	No
`description`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.5.0Jun 25, 2026

TDQS

A5/5.0

Behavior5/5

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

No annotations are provided, so the description fully bears the transparency burden. It discloses name collision behavior, ambiguity handling, error reporting, and response structure, exceeding typical annotation coverage.

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?

The description is front-loaded with the core purpose and critical usage notes, followed by a well-organized spec. Every sentence adds value, and the structure aids quick comprehension despite the complexity.

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?

Given the tool's complexity, the description covers inputs, steps, outputs, error handling, and response format. It is self-contained and provides everything needed for correct invocation without relying on additional documentation.

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%, but the description explains all parameters in detail via the structured spec, including types, defaults, and usage patterns (e.g., @input_name, $step_id.OUTPUT). It fully compensates for the lack of schema descriptions.

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 clearly states the tool builds a QGIS processing model from a spec and saves/registers it. It uses a specific verb and resource, and distinguishes from siblings like run_model or list_processing_algorithms.

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

Usage Guidelines5/5

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

Explicitly warns not to call list_processing_algorithms or get_algorithm_help first, and explains how to handle ambiguous hints and bad parameters. Provides clear when-to-use and when-not-to-use guidance.

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

Deploy Server