Skip to main content
The MCP server provides 8 tools. Each tool (except get_page) triggers an AI agent on the backend that searches the knowledge base from multiple angles, reads relevant pages, and synthesizes a structured response.

Search & Retrieve

search_knowledge

Search the KB for framework docs, APIs, and best practices

get_page

Retrieve a specific KB page by ID

Plan & Review

build_plan

Build a step-by-step ML execution plan

review_plan

Review a plan against KB best practices

Verify & Debug

verify_code_math

Verify code against authoritative ML/math descriptions

diagnose_failure

Diagnose training/deployment failures

Explore & Optimize

propose_hypothesis

Propose ranked next-step hypotheses

query_hyperparameter_priors

Query hyperparameter values, ranges & heuristics