codehub-exploring

Exploring Codebases with OpenCodeHub

When to Use

• "How does authentication work?"
• "What's the project structure?"
• "Where is the database logic?"
• "Show me the request lifecycle."
• Onboarding to a codebase you have not seen before.

Workflow

1. mcp__codehub__list_repos                              → Pick the repo name
2. READ codehub://repo/{name}/context                        → Stats + staleness envelope
3. mcp__codehub__query({query: "<concept>", repo})       → Hybrid BM25 + vector hits, grouped by process
4. mcp__codehub__context({name: "<symbol>", repo})       → 360-degree view, categorised edges, cochange side-section
5. mcp__codehub__sql for process traces                  → Step ordering from the relations table
6. Read source files only after the graph has pointed you at the hot spots

If the context envelope warns the index is stale, run codehub analyze in the terminal first.

Checklist

- [ ] mcp__codehub__list_repos — confirm the repo
- [ ] READ codehub://repo/{name}/context — check freshness
- [ ] mcp__codehub__query for the concept
- [ ] Scan returned processes (execution flows) before scanning files
- [ ] mcp__codehub__context on the strongest hit
- [ ] Inspect confidenceBreakdown — prefer confirmed edges for architectural claims
- [ ] Review cochanges as a secondary signal (git history, NOT call deps)
- [ ] Follow PROCESS_STEP edges via mcp__codehub__sql to trace the flow end-to-end
- [ ] Read source files for implementation detail only

Tools

mcp__codehub__query — hybrid BM25 + vector search, grouped by process

mcp__codehub__query({ query: "payment processing", repo: "my-app", limit: 20 })

→ results: ranked symbols with file path, kind, score
→ processes: execution flows that contain the top hits (populated when PROCESS_STEP edges exist)
→ next_steps: pointer to the next tool

Use it as the first broad read after the context resource. Prefer it over Grep for concept-level questions.

mcp__codehub__context — 360-degree view of a symbol