feat: add OraClaw decision intelligence plugin (5 tools)

[Whatsonyourmind]

Summary

OraClaw is a decision intelligence MCP server providing mathematical optimization tools for AI agents. This plugin exposes 5 algorithm tools via the OraClaw hosted API.

Tools Included

Tool	Algorithm	Use Case
Multi-Armed Bandit	UCB1/Thompson/ε-Greedy	A/B testing, option selection
LP/MIP Solver	HiGHS	Budget allocation, scheduling, constraints
Graph Analytics	PageRank, Louvain	Network analysis, community detection
Anomaly Detection	Z-score/IQR	Outlier detection in numeric data
Time Series Forecast	ARIMA/Holt-Winters	Predictive analytics with confidence intervals

Authentication

Users provide an OraClaw API key (free signup at the API endpoint). The provider validates credentials against the /api/v1/pricing endpoint.

Links

• GitHub: https://github.com/Whatsonyourmind/oraclaw
• npm: @oraclaw/mcp-server (v1.1.1)
• MCP Registry: Published (io.github.Whatsonyourmind/oraclaw)
• Glama: AAA rating (Security A, License A, Quality A)
• PulseMCP: Listed (ci: add pre-check workflow #2,118 this week)

Privacy

No PII collected. Tool parameters sent to API for processing only. Anonymous telemetry (tool name + duration) can be opted out.

🤖 Generated with Claude Code

[xtaq]

Decision intelligence is a smart angle for the Dify ecosystem — most plugins compete in content generation, while optimization / forecasting / anomaly detection are much closer to workflows teams will actually pay for.

I also noticed you've already pushed OraClaw across multiple surfaces: MCP Registry, Glama, PulseMCP, npm, and now Dify. That cross-ecosystem distribution effort is impressive.

I'm curious: which surface is actually producing the highest-quality user feedback so far?

And from the builder side, does maintaining presence across multiple ecosystems feel strategically worth it, or mostly like fragmented overhead right now?

Would love to hear your take — you're one of the few people I’ve seen actively testing distribution across several agent/plugin channels at once.

[xtaq]

@Whatsonyourmind Since you’re already shipping across Dify / MCP / Glama / PulseMCP, you probably have a better feel than most people for which channels bring real users vs just visibility.

We’re testing a small hypothesis: sometimes the missing piece isn’t one more listing channel — it’s a GitHub-facing demo/landing layer that makes the plugin legible fast.

For a project like OraClaw, that usually means the first screen answers who this is for, what decision problem it solves, and why this is better than a generic analytics tool.

This is the focused CTA we’re using for that repo → demo packaging pass:
https://mindcore8.com/agents/b9407842-a43e-4bb3-b37a-8d2ab7120155?utm_source=github&utm_medium=comment&utm_campaign=t951_frontend_designer&utm_content=whatsonyourmind

If you want, I can suggest the hero + CTA structure I’d test first for OraClaw to improve higher-quality inbound.

[crazywoola]

❌ Request Changes

Decision: Request changes

Review Status

Check	Status	Required action
PR language	✅ Pass	—
Project structure	✅ Pass	—
README.md	✅ Pass	—
PRIVACY.md	❌ Fail	Add a non-empty top-level PRIVACY.md file. Detail: PRIVACY.md not found or empty. Please include a non-empty PRIVACY.md file.
Manifest author	✅ Pass	—
Icon validation	✅ Pass	—
Version check	✅ Pass	—
README language	✅ Pass	—
dify_plugin version	❌ Fail	Pin or bump dify_plugin to >= 0.5.0 in requirements.txt or pyproject.toml. Detail: dify_plugin must be >= 0.5.0; found >=0.0.1.

Next steps

• PRIVACY.md: Add a non-empty top-level PRIVACY.md file.
• dify_plugin version: Pin or bump dify_plugin to >= 0.5.0 in requirements.txt or pyproject.toml.

Please address the issues above and push an updated submission.

[Whatsonyourmind]

@crazywoola Both issues from your review are now addressed: PRIVACY.md has been added (uppercase) and dify_plugin has been bumped to >= 0.5.0 in requirements.txt. Ready for re-review when you have a moment.

[crazywoola]

You should submit a packed file only.