Vecline MCP Server
Vecline runs on your own machine — the client starts it, so there is no endpoint to ping. 224 installs a week from npm. Last commit 22 Aug 2026.
Local-first image, vector and document toolkit that measures its own output. Nothing uploaded.
What the code does
We read the source, 5 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.
const probe = spawnSync(file, argv, {
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.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add vecline -- npx -y vecline{
"mcpServers": {
"vecline": {
"command": "npx",
"args": [
"-y",
"vecline"
]
}
}
}[mcp_servers.vecline]
command = "npx"
args = ["-y", "vecline"]{
"mcpServers": {
"vecline": {
"command": "npx",
"args": [
"-y",
"vecline"
]
}
}
}{
"servers": {
"vecline": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vecline"
]
}
}
}Optional settings from the registry entry, left out of the block above:
VECLINE_SOFFICE (Optional. Path to a LibreOffice `soffice` binary, used only by the Office conversion tools. Left unset, they are auto-detected; if LibreOffice is absent the affected tools report themselves as unavailable rather than failing).
Alternatives to Vecline
same job, measured the same waySemantic document memory using Redis vector store. Save and recall files with natural language.
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Local vector and raster editing engine for agents: layered documents, saved sessions and exports.
File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Local-first RAG MCP server: hybrid search over a folder of your own documents
Vecline — questions
Answers built from our own checks of this server.