@Devrobotlabs/Visionapi
FreeNot checkedMCP server that lets AI assistants like Claude or Cursor extract structured data (e.g., invoices) from images and PDFs via Vision API, with tools for analysis,
About
MCP server that lets AI assistants like Claude or Cursor extract structured data (e.g., invoices) from images and PDFs via Vision API, with tools for analysis, questions, and preset management.
README
MCP server for the Vision API. Point Claude Code, Claude Desktop, Cursor or any other MCP host at a folder of scans and ask for the invoices — no integration to write, no API key in generated code, no contract paraphrased from memory.
You: pull the totals out of every invoice in ~/inbox and put them in a CSV
Claude: [vision_analyze × 7]
Done — 7 invoices, 14 credits. Three had no PO number; I left those cells empty.
Install
Nothing to install. Add it to your host's config and it runs via npx.
Claude Code — claude mcp add visionapi --env VISION_API_KEY=sk_live_... -- npx -y @devrobotlabs/visionapi-mcp ~/inbox
Claude Desktop — claude_desktop_config.json:
{
"mcpServers": {
"visionapi": {
"command": "npx",
"args": ["-y", "@devrobotlabs/visionapi-mcp", "/Users/me/inbox"],
"env": { "VISION_API_KEY": "sk_live_..." }
}
}
}
Cursor — .cursor/mcp.json, same shape:
{
"mcpServers": {
"visionapi": {
"command": "npx",
"args": ["-y", "@devrobotlabs/visionapi-mcp", "."],
"env": { "VISION_API_KEY": "sk_live_..." }
}
}
}
VS Code — .vscode/mcp.json:
{
"servers": {
"visionapi": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@devrobotlabs/visionapi-mcp", "${workspaceFolder}"],
"env": { "VISION_API_KEY": "sk_live_..." }
}
}
}
Get a key at app.visionapi.io/dashboard/keys. New accounts get 50 credits, no card.
The host config blocks live in this README rather than in an
examples/directory — a departure from the nine client libraries, and a deliberate one. A snippet that exists only in a README cannot drift from a runnable script nobody runs.
Which directories it can read
Every positional argument is a directory the server may read files from. With none given, the process working directory is the only root — which is the safe default, because MCP hosts launch a stdio server with the project directory as its cwd.
This matters more than it may look. The server holds a live spending credential and runs
with your filesystem permissions, so it can read anything your shell can. Asking it for the raw
text of ~/Documents/passport.jpg is a working way to get that document's contents into a
model's context and into whatever transcript your host keeps. The allowlist is what stops a
confused or manipulated agent doing that by accident.
Paths are resolved with realpath on both sides before being compared, so a symlink inside
an allowed directory cannot point out of it.
--allow-any-path turns the allowlist off entirely. It warns on stderr at startup and you
should have a reason.
Tools
| Tool | What it does | Cost |
|---|---|---|
vision_analyze |
Structured fields out of one image or PDF | 1 credit an image, 2 a PDF page |
vision_ask |
Up to 5 plain-language questions about one file | 1 credit an image, 1 a PDF page |
vision_detect |
What is this file? Ranked presets, no extraction | 1 credit per 5 calls |
vision_list_presets |
The preset catalogue | free |
vision_get_preset |
Every field one preset returns | free |
vision_credits |
Balance and buckets | free |
vision_get_task |
Status/result of a queued task | free |
The three that spend credits are annotated readOnlyHint: false, so a host that auto-approves
read-only tools will still stop and ask before one of them runs.
The catalogue is also exposed as resources — visionapi://presets and
visionapi://presets/{name} — for hosts that prefer them. Tools are the primary surface,
because resource support is uneven across hosts.
Output
Responses are rendered for a model to read, not dumped as JSON. A 37-field invoice preset over
a document that fills twelve of them comes back as a table plus one Not found in this document (25): … line, rather than as twenty-five repetitions of
{"value":null,"confidence":"low"} — three to four times smaller, and easier to act on.
Nothing is lost in the process. Every tool takes a format:
markdown(default) — the rendering above.compact_json— the same information as data, with_not_foundand_low_confidencearrays. For when the agent will parse rather than read.json— the API response verbatim. What to reach for when writing real HTTP code against the contract.
Confidence is printed only when it is not high, so (mid) and (low) stand out and the
common case costs nothing to read.
Long documents
Leave mode at auto. The API kills a synchronous request at 60 seconds; the server then
re-submits it to the queue and polls, reporting progress to your host as it goes. You are
charged once, because the timed-out attempt released its reservation in full.
Pass mode: "async" up front for anything over roughly ten pages, and pages: "1-5" to sample
a long document cheaply — you are charged for selected pages only.
Costs and failures
Failures cost nothing. Every non-2xx releases the credit reservation in full, so a failed call is safe to correct and repeat and there is no cleanup to do. The tool descriptions say so, which is why an agent using this server behaves sensibly after an error instead of either giving up or retrying something that cannot work.
Two errors carry advice that is worth knowing yourself:
| Error | What it means |
|---|---|
insufficient_credits |
Retrying cannot help — the balance does not change on its own. Top up. |
too_many_tasks |
Your own async tasks are at the plan's cap. It clears when one of them finishes, not on a timer — so sleeping and retrying blocks the very thing you are waiting for. |
Environment
| Variable | Required | Purpose |
|---|---|---|
VISION_API_KEY |
for billable tools | Your key. The catalogue tools work without it. |
VISION_API_URL |
no | Override the API base URL. Rarely needed. |
A missing key does not stop the server starting: it warns on stderr, tools/list still works,
and the first billable call returns a message naming the fix. A server that refuses to start
tells the user only that something is broken.
Development
npm install
npm run typecheck
npm test # 37 offline tests — no key, no network
npx @modelcontextprotocol/inspector node ./dist/cli.js ~/some/dir
npm install --no-save ../node to test against a local build of the client. Not
npm install ../node — that rewrites package.json to "file:../node", and that manifest is
what gets published.
Links
MIT licensed.
Install @Devrobotlabs/Visionapi in Claude Desktop, Claude Code & Cursor
unyly install devrobotlabs-visionapi-mcpInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add devrobotlabs-visionapi-mcp -- npx -y github:devrobotlabs/visionapi-mcpStep-by-step: how to install @Devrobotlabs/Visionapi
FAQ
Is @Devrobotlabs/Visionapi MCP free?
Yes, @Devrobotlabs/Visionapi MCP is free — one-click install via Unyly at no cost.
Does @Devrobotlabs/Visionapi need an API key?
No, @Devrobotlabs/Visionapi runs without API keys or environment variables.
Is @Devrobotlabs/Visionapi hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install @Devrobotlabs/Visionapi in Claude Desktop, Claude Code or Cursor?
Open @Devrobotlabs/Visionapi on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
mkinf
An Open Source registry of hosted MCP Servers to accelerate AI agent workflows.
Compare @Devrobotlabs/Visionapi with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
