@codeatlas/mcp 1.2.0 → 2.0.1

package/README.md

@@ -1,10 +1,12 @@
 # @codeatlas/mcp
 
-> **Live codebase architecture for any MCP-compatible LLM client.**
-> 25 tools + 5 resources expose routes, sequences, dependency graphs, diffs, impact analysis, architecture violations, and full SQL access over your workspace — so the model gets structured answers instead of grepping through files.
+> **Live codebase architecture and AI code review for any MCP-compatible LLM client.**
+> 39 tools + 8 resources expose routes, sequences, dependency graphs, diffs, impact analysis, architecture violations, full SQL access, and AI-driven review findings over your workspace — so the model gets structured answers instead of grepping through files.
 
 Works with **Claude Code, Cursor, VS Code Copilot, Codex CLI, Gemini CLI, Antigravity, Continue** — anything that speaks the Model Context Protocol.
 
+**New in v2** — AI code review tools. Run a review with `run_review`, list findings with `list_ai_findings`, ask "what's wrong with auth?" with `search_ai_findings`, then ask for a one-shot context bundle to fix the issue with `review_and_fix_pack`. Findings are grounded in source quotes the model has to copy verbatim — no invented issues.
+
 ---
 
 ## Why it matters: token economics
@@ -79,7 +81,7 @@ After registering, reload your client and the 25 tools appear alongside its buil
 
 ## What it exposes
 
-### 25 tools
+### 39 tools
 
 **Context packs** — minimum-token retrieval primitives
 `list_entrypoints` · `list_entrypoints_paged` · `get_entrypoint_pack` · `get_feature_pack` · `pre_edit_brief` · `get_function_source` · `trace_call_path`
@@ -99,7 +101,10 @@ After registering, reload your client and the 25 tools appear alongside its buil
 **Interop**
 `export_openapi_spec` · `export_function_calling_spec` · `summarise_payload`
 
-### 5 resources
+**AI code review** — query, score, and act on findings (new in v2)
+`list_ai_findings` · `get_ai_finding` · `get_ai_finding_counts` · `update_ai_finding_status` · `get_review_guidelines` · `set_review_guidelines` · `search_ai_findings` · `summarise_findings` · `list_findings_by_guideline` · `get_review_summary` · `clear_findings` · `review_and_fix_pack` · `score_findings` · `propose_guideline_from_finding` · `review_diff_with_baseline`
+
+### 8 resources
 
 | URI | Contents |
 |-----|----------|
@@ -108,6 +113,13 @@ After registering, reload your client and the 25 tools appear alongside its buil
 | `codeatlas://workspace/features` | Feature clusters — label, file membership, cohesion, API count |
 | `codeatlas://workspace/entrypoints` | Every entry point flattened across all categories |
 | `codeatlas://workspace/diff-summary` | Baseline-vs-working summary across all 6 diagram layers |
+| `codeatlas://workspace/ai-findings` | All AI-review findings — severity, layer bindings, source quotes |
+| `codeatlas://workspace/review-guidelines` | Team review rules currently injected into every review prompt |
+| `codeatlas://workspace/review-summary` | Counts by layer + severity, top findings, last review metadata |
+
+### Push notifications
+
+Stdio clients that subscribe get `notifications/codeatlas/findings_changed` when findings are added, updated, or removed — no polling needed.
 
 ---
 
@@ -137,6 +149,12 @@ A tab opens at `http://localhost:7742` showing six linked diagram layers: system
 
 Set `CODEATLAS_EDITOR=<cmd>` to pick the editor (defaults to `$EDITOR`, then `code`, `cursor`, `subl`, `nvim`, `vim`).
 
+### Run an AI Review from the browser
+
+The home page has a **Start review** card that fans the review out across every entry point. **Changed only** restricts it to entry points whose code differs from baseline. **Specific review** opens a textarea so you can tell the AI exactly what to focus on. **Cancel** stops the in-flight LLM call immediately; **Clear** wipes findings and resets state.
+
+Each finding is tagged with the commit SHA it was reviewed against (or a content-hash for non-git workspaces). Re-running with the same code + guidelines surfaces a **"Nothing changed since last review"** badge instead of burning another LLM call.
+
 ### Connect an LLM
 
 AI Review and natural-language search use any OpenAI-compatible provider. Pick one: