Skip to main content
Glama

Inkscape Vector

inkscape_vector
Destructive

Edit and convert SVG vectors via Inkscape CLI: trace images, apply boolean/path operations, generate QR/barcodes, optimize files, and render previews.

Instructions

INKSCAPE_VECTOR — Vector editing, booleans, trace, QR/barcode, path ops, previews.

PORTMANTEAU RATIONALE: Inkscape exposes many CLI actions; grouping avoids tool explosion.

Operations include: trace_image, generate_barcode_qr, apply_boolean, path_simplify, optimize_svg, scour_svg, render_preview, query_document, measure_object, export_dxf, layers_to_files, object_raise/lower, set_document_units, and others (see Literal).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "operation": "<operation>"
    },
    "name": "inkscape_vector"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
dpiNoResolution for render_preview. steps: 90-degree turns for page_rotate.
colsNo
rowsNo
stepsNo
unitsNoTarget unit for set_document_units (px, mm, cm, in, pt, pc).px
offsetNoGrow (positive) or shrink (negative) amount for path_inset_outset.
path_idNo
text_idNo
x_shiftNo
y_shiftNo
object_idNoTarget element — measure_object, count_nodes, path_simplify, object_raise, object_lower.
operationYesSubcommand; must match InkscapeVectorOperation.
source_idNo
thresholdNoSimplification strength for path_simplify (1-10 passes).
input_pathNoPrimary document path.
object_idsNo
output_dirNoDestination directory for layers_to_files.
scale_stepNo
select_allNo
descriptionNo
output_pathNoOutput file when the operation writes a file.
trace_scansNo
trace_stackNo
barcode_dataNoPayload for generate_barcode_qr (required).
trace_smoothNo
rotation_stepNo
operation_typeNounion | difference | intersection | exclusion for apply_boolean. REQUIRED for align — one or two of left|hcenter|right / top|vcenter|bottom plus an optional anchor (last|first|biggest|smallest|page|drawing|selection|pref), e.g. "top", "hcenter vcenter", "top page". REQUIRED for distribute — exactly one of hgap|left|hcenter|right|vgap|top|vcenter|bottom.
trace_optimizeNo
trace_specklesNo
trace_smooth_cornersNo
trace_remove_backgroundNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

C2.8/5.0
Behavior2/5

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

Annotations declare destructiveHint=true and readOnlyHint=false, so the agent knows writes and possible data loss are involved, yet the description never says which operations overwrite the source document, which write to output_path, or whether inputs are mutated. For a 50-operation tool that includes optimize_svg, scour_svg and export operations, that gap is significant even with annotations present.

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

Conciseness3/5

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

It is short and front-loads the tool's identity, but the operation list largely duplicates the enum in the schema, which costs space without adding meaning. The rationale sentence is the only part that earns its place.

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

Completeness2/5

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

With 33 parameters, 50 enum operations, destructive annotations and no per-operation guidance, a three-sentence description is far too thin. The output schema is declared so return values need not be explained, but the mapping of operations to required parameters and side effects is left entirely to the schema.

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

Parameters2/5

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

Schema coverage is only 33% across 33 parameters, so the description carries a heavy burden and adds nothing beyond restating the operation enum. It never explains shared parameters like object_id, object_ids, path_id, or input_path, nor the required-payload rules (e.g. barcode_data) that the schema documents only in fragments.

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

Purpose4/5

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

The description names specific verb categories (trace, booleans, path ops, QR/barcode, previews) and lists concrete operations like trace_image and apply_boolean, so the resource and scope are identifiable. It does not distinguish this tool from siblings such as inkscape_gradient or inkscape_live, and the trailing 'and others (see Literal)' leaves the boundary fuzzy, which keeps it below a 5.

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

Usage Guidelines3/5

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

The PORTMANTEAU RATIONALE explains why so many operations are bundled ('grouping avoids tool explosion'), which implies this is the catch-all vector tool, but it gives no when-to-use vs alternatives guidance against the named siblings and no exclusions. An agent must infer from operation semantics which subcommand fits its intent.

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