Inkbolt vector and raster editor runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 23 Oct 2026.
Local vector and raster editing engine for agents: layered documents, saved sessions and exports.
What the code does
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
limits.as_object_mut().unwrap().extend(json!({"mask_feather_radius":masks::MAX_FEATHER,"mask_prepared_pixels":masks::MAX_PREPARED_PIXELS,"mask_document_prepared_pixels":masks::MAX_DOCUMENT_PIXELS,"mask_feather_work":masks::MAX_FEATHER_WORK}).as_object().unwrap().clone());
const result = spawnSync(path.resolve(binary), [], { cwd: base, input: '{"command":"capabilities"}\n', encoding: 'utf8', timeout: 15000, maxBuffer: 8 * 1024 * 1024, windowsHide: true });
for (const name of ['LICENSE', 'README.md', 'THIRD_PARTY_NOTICES.md']) files.set(name, await textFile(path.join(base, name)));
version = subprocess.check_output([str(paths['resvg']), '--version'], timeout=10, text=True).strip()
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Inkbolt vector and raster editor
same job, measured the same wayLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Semantic document memory using Redis vector store. Save and recall files with natural language.
Local-first RAG engine with MCP server for AI agent integration.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Vector motion editor MCP: 26 typed tools to observe, validate and edit documents, then export code.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Inkbolt vector and raster editor — questions
Answers built from our own checks of this server.