Add OCI Vision MCP server - #365
Conversation
|
Automated review result: needs security/manual review. Reason:
Manual review should verify server-side authorization, URL/SSRF protections, object bounds and pagination, upload confirmation/audit behavior, untrusted OCR/backend content handling, and secret/customer-data redaction. No automated approval or merge was performed. |
krisrice
left a comment
There was a problem hiding this comment.
Maintainer-directed merge after review: GitHub reports the PR mergeable, all reported checks are passing, and the repository maintainer explicitly requested merging all mergeable PRs.
|
@antimverma can you please resubmit this PR? It was merged before we had a chance to complete review and I have since backed it out with in PR 389. Thanks. |
@dustin-sale @krisrice Resubmitted the OCI Vision MCP PR. |
Description
Adds the OCI Vision MCP server under
src/oci-vision-mcp-server.This server provides stdio MCP tools for OCI Vision image analysis and related Object Storage image workflows, including image analysis, OCR, object detection, face detection, async image jobs, Object Storage upload/list/fetch, stored result lookup, and runtime configuration status.
The implementation follows the repository MCP server structure and public packaging expectations:
pyproject.toml,uv.lock,README.md,CHANGELOG.md,LICENSE.txt,Containerfile, andoracle/package source.oracle.oci-vision-mcp-server./mcp, and/.well-known/*endpoints are not exposed.additional_user_agenttelemetry derived from package metadata.Fixes: N/A
Type of change
How Has This Been Tested?
Validated locally from
src/oci-vision-mcp-server:uv sync --locked --all-extras --devuv run pytest --cov=. --cov-branch --cov-report=term-missing236 passed, 2 skipped91.31%uv builddetect_facescompleted successfully on a local image.detect_textcompleted successfully on a local screenshot and returned OCR lines.Containerfile.pyproject.tomlmetadata and entry point validated.Test Configuration:
Checklist: