ocular
Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts
What you can do with it
Share of each task's required capabilities it coversPrefer a ready-made agent?
An MCP server is a connector for your own assistant. These finished products do the job for you: extract data from PDFs.Similar tools
Listed for the same task: extract data from PDFsReviews
No review yet. Used ocular? Be the first to help others choose.What it does
ocular is an MCP server, a connector that lets an AI assistant use it as a tool. It is installed locally as a package and runs on your machine.
From the publisher's description, Electra Index matched it to 2 capabilities: data extraction and document understanding. That makes it a candidate for tasks such as extract data from PDFs or analyze financial documents.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · not tested by Electra IndexInstall package
- NPM
ocular-mcpv0.1.0 · runs locally (stdio)
Required: OCULAR_BASE_URL, OCULAR_API_KEY, OCULAR_MODEL (get them from the publisher)
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"ocular": {
"command": "npx",
"args": [
"-y",
"ocular-mcp"
],
"env": {
"OCULAR_BASE_URL": "<your OCULAR_BASE_URL>",
"OCULAR_API_KEY": "<your OCULAR_API_KEY>",
"OCULAR_MODEL": "<your OCULAR_MODEL>"
}
}
}
}Replace the values in <angle brackets>.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Install package | ocular-mcp | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Package registries | npm | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Local install (package) | yes | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Remote access (hosted) | no | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Repository | https://github.com/xyun1996/ocular | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Version | 0.1.0 | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 5d ago |
Change history
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is ocular still online?
Free alerts · no account▲ 0Do you publish ocular? Get it seen by people choosing a tool
For publishers · optionalLaunch Spotlight: 60 days of clearly labelled Sponsored visibility on the use-case pages where ocular already appears, plus the weekly Pulse. No click in 60 days? The next 60 days are free.
Sponsored placements never change a score or a rank.
Questions about ocular
How do I connect ocular?
Install the npm package ocular-mcp. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
Does ocular need an API key or token?
Yes. The registry entry lists required values: OCULAR_BASE_URL, OCULAR_API_KEY, OCULAR_MODEL. Get them from the publisher.
What can I use ocular for?
Based on its description, it is most relevant to: extract data from PDFs, analyze financial documents, analyze patents, answer questions from internal documents.