Inkbolt vector and raster editor
Local vector and raster editing engine for agents: layered documents, saved sessions and exports.
Que pouvez-vous faire avec Inkbolt vector and raster editor ?
- Compose graphics with vector shapes, text, images, layers and artboards.
- Import artwork from SVG, PNG, JPEG and TIFF. Supported SVG content stays
- Select and mask image regions with feathered edges or foreground/background
- Edit and repair images with brushes, adjustments, patches, region fills,
- Review revisions with previews, comparisons, saved sessions and undo/redo.
- Deliver assets as PNG, JPEG, TIFF, SVG or PDF within the supported workflows.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
https://github.com/skulitom/Inkbolt/releases/download/v0.82.0/inkbolt-windows-x64.mcpbDocumentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
Inkbolt
Local vector and raster editing for AI agents.
Inkbolt gives agents an editable graphics workspace for diagrams, illustrations, layouts and image assets. Create or import artwork, make focused changes, inspect previews and export the result while keeping the source and revision history.
It runs locally through MCP over stdio, a JSON command-line interface, or the Rust library. There is no account, network service or telemetry, and no particular AI model is required.
Install and connect · Try the examples · Download a release
What you can do
- Compose graphics with vector shapes, text, images, layers and artboards.
- Import artwork from SVG, PNG, JPEG and TIFF. Supported SVG content stays editable, including styles, reusable symbols, placed images and positioned text.
- Select and mask image regions with feathered edges or foreground/background seeds. Keep masks editable and preserve the original image samples.
- Edit and repair images with brushes, adjustments, patches, region fills, content-sensitive moves and guided edge correction. Native storage supports high-precision samples and shares unchanged data across edits.
- Review revisions with previews, comparisons, saved sessions and undo/redo.
- Deliver assets as PNG, JPEG, TIFF, SVG or PDF within the supported workflows. Preflight reports output size and conversion losses before publication; file delivery preserves sources and refuses to overwrite existing outputs.
Agents discover tools and request individual operation schemas as they work. Unsupported features fail explicitly; declared approximations and conversion losses are reported.
How agents work with Inkbolt
- Discover the relevant tools and create or import a document.
- Make focused edits, preview the result and compare revisions.
- Save the editable session, check the intended export and publish to a new file.
Saved sessions let an agent resume work later with the document's revision history.
Get started
This README describes main. Download a release for a packaged build, or
build from source for the newer features below. Follow the
installation guide for your system and MCP client.
| Version | What to expect |
|---|---|
| v0.82.0 release | Windows x64, Linux x64 and macOS Apple silicon archives, plus a Windows desktop extension bundle. Release notes describe the included features. |
Build from main | Adds larger image editing, native JPEG import, guided selections and masks, patch repair, editable layered imports, and lower-memory exports. The large-image workflows described below require this newer source build. |
For an MCP client, use this launch command with the path to an existing folder where you want to work:
inkbolt --workspace PATH_TO_EXISTING_FOLDER mcp --tools core
The core catalog keeps initial tool discovery compact. Agents can request more operations and their schemas when needed.
Documentation
| Start here | Details |
|---|---|
| Examples | Runnable graphics and image workflows |
| Agent interface and tool discovery | Commands, MCP tools and schemas |
| Workspaces and sessions | Local resources, saved work and revision references |
| SVG import, image import and layered import | Editable inputs, source precision and conversion limits |
| Selections, masks and image repair | Image editing workflows and operation limits |
| Large-image workflows | 24 MP import, 50 MP editing, A2 delivery and 8192 x 8192 rendering; brush and retouch bounds |
| Image export | PNG/JPEG/TIFF file output, preflight and memory bounds |
| Capabilities and limits | Verified behavior and links to feature contracts |
| Platform support and benchmark results | Tested systems, agent evaluations and remaining gaps |
| Workload measurements | Reproducible runtime and memory checks, including Linux CLI and MCP sessions |
For context on other tools, see SVG and vector editing MCP servers for AI agents: 9 compared. The comparison was checked on 18 October 2026: Inkbolt was measured over MCP; the other servers were reviewed through their code and documentation.
Project status
Inkbolt is under active development. The core engine, CLI/MCP, saved sessions and file-delivery receipts are tested on Windows, Linux and macOS. Background export jobs currently require Windows. The platform guide records tested revisions and the scope of each platform's coverage.
The following large-image workflows have passed independent output checks on Windows and Linux:
| Workflow | Checked size |
|---|---|
| Baseline and progressive JPEG import | 24 MP |
| 16-bit image editing: cloned patch, selected brush, repair, feathered mask, undo/redo and TIFF export | 50 MP |
| A2 page delivery as PDF and PNG | 300 ppi |
| Rendering and PNG export with opaque, translucent and transparent regions | 8192 x 8192 |
These checks use fixed original fixtures and preserve source files and revision history. Windows regression budgets use five baseline repetitions and a separate five-repeat check. Each operation retains its own size, precision and work limits; cross-platform performance acceptance remains in progress.
Image-guided selection supports direct analysis of bounded regions and an opt-in whole-image mode. The latter uses a coarse image and refines boundaries at full resolution; it can miss small features. Both preserve the original image samples.
Editable RGB8 layered imports have also been checked at 8192 x 8192 on Windows and Linux. Larger canvases require an explicit import option. The native path reads larger encoded files in bounded chunks; its contract lists separate file, metadata and content limits.
Work in progress includes broader layered-file interchange, broader curve combinations, editable format interchange, agent usability and cross-platform performance acceptance.
The primary plan tracks development priorities. Benchmark results record agent evaluations and their limitations separately from engine feature coverage.
Contributors can start with the development guide, architecture and source requirements. Routine verification targets 2-3 minutes, with full checks at milestones.
License
Inkbolt is MIT licensed. Dependencies retain their own licenses; see third-party notices.
Questions fréquentes
Qu'est-ce que Inkbolt vector and raster editor ?
Local vector and raster editing engine for agents: layered documents, saved sessions and exports.
Comment installer Inkbolt vector and raster editor ?
Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.
Faut-il une clé API pour Inkbolt vector and raster editor ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
Inkbolt vector and raster editor est-il open source ?
Oui. Son code est sur GitHub sous licence MIT.
Qui maintient Inkbolt vector and raster editor ?
Il est publié par skulitom. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.