OraClaw MCP server as integration example — 12 decision intelligence tools

[Whatsonyourmind]

Hi! Love what lc2mcp does — bridging LangChain and MCP is exactly what the ecosystem needs.

I built OraClaw, an MCP server with 12 decision intelligence tools that could work as a solid integration showcase:

• Bandits (UCB1, Thompson, LinUCB) — optimal A/B testing
• LP Solver (HiGHS WASM) — scheduling, resource allocation
• Graph Analytics — PageRank, Louvain communities, shortest path
• Forecasting — ARIMA + Holt-Winters
• Anomaly Detection — Z-score, IQR
• CMA-ES — continuous optimization (10-100x faster than grid search)
• Monte Carlo — risk simulation
• • 5 more tools

I also have LangChain tool wrappers (oraclaw_tools.py) that could serve as a good test case for lc2mcp's conversion accuracy — they're relatively complex with structured input schemas.

MCP server: @oraclaw/mcp-server
LangChain wrappers: https://github.com/Whatsonyourmind/oraclaw/blob/master/integrations/langchain/oraclaw_tools.py

Would you be interested in adding OraClaw as an example in the lc2mcp docs? Happy to help test and document.

[Whatsonyourmind]

Update: OraClaw API is now live! Try it:

# Health check — 19 algorithms, 17 endpoints
curl https://vigilant-rotary-phone-97r5w6j6964pcp4gr-3001.app.github.dev/api/v1/health

# Multi-Armed Bandit example
curl -X POST https://vigilant-rotary-phone-97r5w6j6964pcp4gr-3001.app.github.dev/api/v1/optimize/bandit   -H 'Content-Type: application/json'   -d '{"arms":[{"id":"a","name":"A","pulls":50,"totalReward":35},{"id":"b","name":"B","pulls":50,"totalReward":30}]}'

All endpoints verified and sub-5ms. Full docs: https://github.com/Whatsonyourmind/oraclaw

[Whatsonyourmind]

Update: OraClaw is now live and installable!

API (live): https://oraclaw-api.onrender.com

curl https://oraclaw-api.onrender.com/api/v1/health
# → 19 algorithms, 17 endpoints, v2.3.0

npm packages (5 published, 10 more coming):

npm install @oraclaw/bandit @oraclaw/solver @oraclaw/decide @oraclaw/graph @oraclaw/calibrate

ClawHub skills (5 published, 9 more coming):

clawhub install oraclaw-bandit

Quick test — Multi-Armed Bandit:

curl -X POST https://oraclaw-api.onrender.com/api/v1/optimize/bandit   -H 'Content-Type: application/json'   -d '{"arms":[{"id":"a","name":"Option A","pulls":100,"totalReward":65},{"id":"b","name":"Option B","pulls":100,"totalReward":72}]}'

All sub-5ms, zero LLM cost. Remaining packages publishing automatically over the next few hours.