About this integration
Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.0
- Package
- ocular-mcp
- Last compatibility test
- Not independently tested
Connect your agent
ocular-mcpPublisher README and npm manifest were reviewed from pinned captures. This is documented evidence only: the package and provider endpoint were not executed or security-audited. Keep provider keys in the client's secret-management mechanism; provider/model compatibility depends on the configured endpoint.
Capabilities: Structured image and screenshot analysis, OCR and table extraction, UI comparison and error diagnosis, Chart analysis
Connected profiles
Additional details
io.github.xyun1996/ocular
Source ↗ · Checked 2026-09-170.1.0
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17OCULAR_BASE_URL, OCULAR_API_KEY, OCULAR_MODEL
Source ↗ · Checked 2026-09-17ocular-mcp
Source ↗ · Checked 2026-09-200.1.0
Source ↗ · Checked 2026-09-20After provider credentials are configured, an MCP client launches the local stdio process and exchanges protocol messages without a separate interactive server session.
Source ↗ · Checked 2026-09-20Requires an OpenAI-compatible multimodal endpoint, provider API key, and model name supplied through OCULAR_BASE_URL, OCULAR_API_KEY, and OCULAR_MODEL.
Source ↗ · Checked 2026-09-20The reviewed local connection is stdio using the ocular CLI installed by the ocular-mcp npm package; the separately documented HTTP deployment is not this catalog connection.
Source ↗ · Checked 2026-09-20Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-20