Skip to main content
Glama
vectorplease-mcp

vectorplease-mcp

Official
by vectorplease

@vectorplease/mcp

MCP server for Vector, Please: bitmap in, sticker-ready SVG out, from any MCP client.

Status: pre-release. Not yet published to npm.

Tools

Tool

What it does

convert_image

Converts a PNG, JPEG or WebP (local path, https url, or base64) into a sticker SVG. Optional preset, params, and outputPath to write the SVG to a file. Returns quality metrics.

get_conversion

Fetches a conversion by id, for one that was still running.

list_presets

Lists the presets: one starting point per kind of artwork.

Related MCP server: Quiver AI MCP Server

Running

Set VECTORPLEASE_API_KEY, then:

vectorplease-mcp          # stdio, for clients that launch the server
vectorplease-mcp --http   # streamable HTTP on http://127.0.0.1:3333/mcp (PORT, HOST to change)

The HTTP transport uses the server's own API key, so keep it on localhost or a trusted network. Images are limited to 10 MB; URLs must be https.

License

MIT

Available Tools

3 tools
convert_imageConvert an image to a sticker SVGA

Turns a PNG, JPEG or WebP image into a sticker-ready SVG with a white border and a die-cut outline. Give exactly one of path, url (https) or base64. Returns the SVG and quality metrics, or writes the SVG to outputPath.

Inputs: url, path, base64, params, +2 more. Returns: id, status, metrics, savedTo, +1 more

get_conversionGet a conversionA

Fetches a conversion by id, for example one that was still running.

Inputs: id (required). Returns: id, status, metrics, savedTo, +1 more

list_presetsList presetsA
Read-only

Lists the conversion presets: one starting point per kind of artwork.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: list_presets discovers presets, convert_image performs the conversion, and get_conversion retrieves a prior conversion by id. The create-vs-fetch boundary between the two conversion tools is unambiguous and reinforced by the descriptions.

    Naming Consistency5/5

    All three names follow a consistent verb_noun pattern (list_presets, convert_image, get_conversion) with uniform snake_case. No deviation or mixing of conventions.

    Tool Count4/5

    The server has a narrow, well-defined purpose and three tools cover its core flow without redundancy. It sits at the low end of the ideal range, so it is slightly thin but not inappropriately so.

    Completeness4/5

    The pipeline of discovering presets, converting an image, and fetching a conversion result is fully covered. Minor gaps exist (e.g. no listing of past conversions or cancel/delete operations), but agents can work around them with known ids.

    Related MCP Connectors

    Related MCP Servers