Ocular vs Codex Delegate
A side-by-side look at the Ocular and Codex Delegate MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Ocular for coding agents work as a local process; choose Codex Delegate for coding agents as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Ocular when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
OCULAR_BASE_URL, OCULAR_API_KEY, OCULAR_MODEL. - You want tools like
analyze_image, extract_text_from_image, analyze_ui_screenshot.
Choose Codex Delegate when
- You need dedicated capabilities in the Coding Agents domain.
- You prefer a local stdio subprocess transport.
- You want tools like
delegate, cancel, doctor.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Coding Agents | Coding Agents |
| Quality signal | 60/100 · Good | 63/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | BYOK (pay the provider) |
| Required env vars | OCULAR_BASE_URLOCULAR_API_KEYOCULAR_MODEL | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 2 |
| Directory activity | 1 views 0 installs 0 upvotes | 6 views 0 installs 0 upvotes |
| Tools | 8 | 3 |
| Full listing | View Ocular | View Codex Delegate |
Tools & capabilities
Ocular tools 8
analyze_imageAnalyze a general image and return structured JSON for a coding agent.extract_text_from_imageExtract OCR text from screenshots, documents, tables, terminal output, or code images.analyze_ui_screenshotAnalyze a webpage, app, UI, or design mockup screenshot for frontend implementation work.diagnose_error_screenshotAnalyze error, terminal, console, browser, or build failure screenshots.compare_ui_screenshotsCompare two UI screenshots and return implementation-useful visual differences.extract_table_from_imageExtract visible table data from an image as structured JSON, Markdown, or CSV-oriented output.analyze_chart_imageAnalyze a chart image and return labels, trends, approximate values, and limitations.create_upload_sessionReturns upload instructions for the binary side channel (use this to analyze LOCAL image files without base64 corruption). Before uploading, verify the local file exists and is non-empty with Bash (e.g. `ls -la <path>` or `test -f <path> && stat -c %s <path>`). Then PUT the raw bytes to the returned upload_url with curl --data-binary (NOT base64); the response gives a file_id to pass to any vision tool. Stateless -- call once to learn the endpoint.
Codex Delegate tools 3
delegateDelegate a coding task to OpenAI Codex. Never run codex from the shell — use this tool. Check status before trusting result — a run that spawns then fails returns normally. Keep model, reasoningEffort and fast at their defaults unless the user asks. See the delegate skill.cancelCancel active runs. delegationId selects one (announced in progress before spawn — the only handle if a run wedges at startup), threadId all on its thread, neither all. Waits for settlement; if a process tree survives the kill deadline, it still returns and the delegate result warns. Status: cancelled, nothing-active, or not-found (no active run with this ID).doctorDiagnose plugin/CLI/login, recursion, and workspace (default: server cwd). deep adds no-quota help and model-catalog checks.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Ocular
{
"mcpServers": {
"ocular": {
"command": "npx",
"args": [
"-y",
"ocular-mcp"
],
"env": {
"OCULAR_BASE_URL": "YOUR_OCULAR_BASE_URL_HERE",
"OCULAR_API_KEY": "YOUR_OCULAR_API_KEY_HERE",
"OCULAR_MODEL": "YOUR_OCULAR_MODEL_HERE"
}
}
}
}
Codex Delegate
{
"mcpServers": {
"codex-delegate": {
"command": "npx",
"args": [
"-y",
"codex-delegate-mcp"
]
}
}
}
Frequently asked questions
Ocular is categorized under Coding Agents and uses a local stdio subprocess. Codex Delegate belongs to Coding Agents and uses a local stdio subprocess. Pick Ocular for coding agents work and Codex Delegate for coding agents.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Ocular has no declared pricing — check the project's own site. Codex Delegate is bring-your-own-key: usage is billed by the API provider you supply a key for. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add ocular and codex-delegate as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Ocular has a quality signal of 60/100 (Good) with 1 views, 0 installs and 0 GitHub stars. Codex Delegate has 63/100 (Good) with 6 views, 0 installs and 2 GitHub stars.