Better Code Review Graph

mcp-name: io.github.n24q02m/better-code-review-graph

Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.

Sister projects from n24q02m (click to expand)

Project	Tagline	Tag
better-code-review-graph	Knowledge graph for token-efficient code reviews -- semantic search and call-...	MCP
better-email-mcp	IMAP/SMTP email for AI agents -- read, send, organize folders, and manage att...	MCP
better-godot-mcp	Composite MCP server for Godot Engine -- 17 composite tools for AI-assisted g...	MCP
better-notion-mcp	Markdown-first Notion for AI agents -- pages, databases, blocks, and comments...	MCP
better-telegram-mcp	Telegram for AI agents -- messages, chats, media, and contacts across both bo...	MCP
claude-plugins	Claude Code plugin marketplace for the n24q02m MCP servers -- install web sea...	Marketplace
imagine-mcp	Image and video understanding + generation for AI agents -- across Gemini, Op...	MCP
jules-task-archiver	Chrome Extension for bulk operations on Jules tasks via batchexecute API -- a...	Tooling
mcp-core	Shared foundation for building MCP servers -- Streamable HTTP transport, OAut...	MCP
mnemo-mcp	Persistent AI memory with hybrid search and embedded sync. Open, free, unlimi...	MCP
qwen3-embed	Lightweight Qwen3 text embedding and reranking via ONNX Runtime and GGUF	Library
skret	Secrets without the server.	CLI
tacet	TACET: a self-distilling neuro-symbolic cascade that amortises LLM cost in kn...	Tooling
web-core	Shared web infrastructure package for search, scraping, HTTP security, and st...	Library
wet-mcp	Open-source MCP server for AI agents: web search, content extraction, and lib...	MCP

Table of contents

• Features
• Status
• Documentation
• Tools
• Comparison
• Security
• Build from Source
• Trust Model
• License

Fork of code-review-graph with critical bug fixes, configurable embeddings, and production CI/CD. Parses your codebase with Tree-sitter, builds a structural graph of functions/classes/imports, and gives Claude (or any MCP client) precise context so it reads only what matters.

v2.0 migration (BREAKING)

See BREAKING_CHANGES.md for the full schema-change list, behavior-change summary, environment requirements, and rollback procedure.

This release adds temporal columns (valid_from_sha / valid_to_sha on every node + edge) and an opt-in security scanner. The schema migration is auto-applied on first GraphStore open, and a backup of the pre-2.0 DB is saved to <graph_db>.pre-2.0.bak so you can roll back if needed.

To downgrade and restore the pre-2.0 backup:

CRG_DOWNGRADE_TO_1_X=1 uv run better-code-review-graph

The backup is created the first time alembic crosses the breaking boundary (revision 005_temporal_columns); subsequent runs reuse the existing backup file. After a downgrade the v2-state DB is preserved at <graph_db>.post-2.0.archived so you can forward-roll again later.

What you get on v2.0+:

• Temporal queries -- query/search/impact accept as_of=<sha> for snapshot semantics; query(action="diff", from_sha=X, to_sha=Y) returns {added, removed, modified} buckets driven entirely by the temporal columns (no re-parse). See help(topic="query").
• Refactor auditing -- review(action="delta", show_line_shifts=true, ...) surfaces symbols whose line_start moved between two commits.
• Security scanning -- security(action="scan", ...) runs a regex-based Tier-1 scanner (5 rules) by default; pass engine="semgrep" (after uv add 'better-code-review-graph[security]') for the Tier-2 engine, which runs Semgrep's p/auto registry pack plus a 3-rule curated overlay. Findings persist on nodes.security_tags; report re-emits the cache as JSON or SARIF v2.1.0. See help(topic="security").

What's new in v1.6

• LLM-generated summaries -- graph(action="summarize") writes a one-paragraph docstring for each Function node via Gemini or OpenAI (cloud opt-in, no key = no-op). Run it after graph(action="update") to lift semantic-search recall by ~15% on repos with terse function names.
• Graph export in 4 formats -- graph(action="export", format=...) emits graphml (Gephi/Cytoscape), json-ld, dot (Graphviz), or cypher (Neo4j replay). Inline by default; pass output_path to write to disk.
• Source text capture -- Function nodes now persist their raw source so summaries can be regenerated whenever an edit changes the body. The cache key is sha256(source_text):provider; unchanged nodes cost zero LLM calls on re-run.
• Cost cap on summaries -- max_nodes (default 500) caps LLM calls per invocation; pair with cron / update cadence for predictable spend.
• Phase 1 quality wins (also new in this train): query(action="spot_check") for random callsite snippets, query(action="renamed_in_diff") for shifted callsites, dynamic-dispatch hints in callers_of results, a dedicated recipes help topic, and embeddings_count exposed in graph(action="stats").

Example -- after pulling new functions in, refresh embeddings with summaries:

graph(action="update")
graph(action="summarize", max_nodes=200)
graph(action="embed")

Features

Feature	code-review-graph	better-code-review-graph
Multi-word search	Broken (literal substring)	AND-logic word splitting
callers_of/callees_of	Empty results (bare name targets)	Qualified name resolution + bare fallback
Embedding	sentence-transformers + torch (1.1 GB)	qwen3-embed ONNX + cloud (200 MB), dual-mode
Output size	Unbounded (500K+ chars)	Paginated (max_results, truncated flag)
Tool design	9 individual tools	7 tools: graph + query + review + config + security + help + config__open_relay
Plugin hooks	Invalid PostEdit/PostGit	Valid PostToolUse

Status

2026-05-02 -- Architecture stabilization update

Past months saw significant churn around credential handling and the daemon-bridge auto-spawn pattern. This caused multi-process races, browser tab spam, and inconsistent setup UX across plugins. The architecture is now stable: 2 clean modes (stdio + HTTP), no daemon-bridge layer, no auto-spawn from stdio.

Apologies for the instability period. If you encountered issues with prior versions, please update to the latest release and follow the current Setup guide -- most prior workarounds are no longer needed.

Related plugins from the same author:

• wet-mcp -- Web search + content extraction
• mnemo-mcp -- Persistent AI memory
• imagine-mcp -- Image/video understanding + generation
• better-notion-mcp -- Notion API
• better-email-mcp -- Email management
• better-telegram-mcp -- Telegram
• better-godot-mcp -- Godot Engine

All plugins share the same architecture -- install once, learn pattern transfers.

Documentation

Full docs at mcp.n24q02m.com/servers/better-code-review-graph/setup/:

• Setup -- install methods for Claude Code, Codex, Gemini CLI, Cursor, Windsurf, mcp.json
• Modes overview -- stdio / local-relay / remote-relay / remote-oauth
• Multi-user setup -- per-JWT-sub credential model

Install with AI agent -- paste this to your AI coding agent:

Install MCP server better-code-review-graph following the steps at https://raw.githubusercontent.com/n24q02m/claude-plugins/main/plugins/better-code-review-graph/setup-with-agent.md

Tools

graph -- Graph lifecycle

Actions: build | update | stats | embed | export | summarize

Action	Description
build	Full or incremental graph build. Set full_rebuild=true to re-parse all files.
update	Alias for build with full_rebuild=false (incremental).
stats	Graph size, languages, node/edge breakdown, embedding count.
embed	Compute vector embeddings for semantic search. Dual-mode: local ONNX or cloud.
export	Export graph in graphml / json-ld / dot / cypher. Inline or to output_path.
summarize	LLM-generated one-paragraph docstrings for Function nodes (Gemini or OpenAI, cloud opt-in). Cost-capped via max_nodes.

query -- Graph queries

Actions: query | search | impact | large_functions

Action	Description
query	Predefined pattern queries: callers_of, callees_of, imports_of, importers_of, children_of, tests_for, inheritors_of, file_summary.
search	Search code entities by name/keyword or semantic similarity.
impact	Blast radius of changed files. Auto-detects from git diff. Paginated with max_results.
large_functions	Find functions/classes exceeding a line-count threshold.

review -- Code review context

Token-optimized review context with structural summary, source snippets, and review guidance. Auto-detects changed files from git diff.

config -- Server configuration and credential setup

Actions: status | set | cache_clear | setup_status | setup_start | setup_skip | setup_reset | setup_complete

Action	Description
status	Server info: version, graph path, node/edge counts, embedding backend.
set	Update runtime settings (e.g., log_level).
cache_clear	Remove all computed embeddings.
setup_status	Show current credential state and setup URL.
setup_start	Start relay setup to configure API keys via browser.
setup_skip	Set local mode (skip relay permanently, use ONNX only).
setup_reset	Clear credentials and reset state.
setup_complete	Re-resolve credentials from environment variables.

security -- Security scanning

Actions: scan | report | suppress | rule_list

Action	Description
scan	Run a security scan (engine='heuristic' default, or 'semgrep'). Findings persist on nodes.security_tags.
report	Re-emit cached findings as JSON (format='json') or SARIF v2.1.0 (format='sarif').
suppress	Suppress a finding by rule_id (or remove=true to un-suppress).
rule_list	List available rules for an engine.

help -- Full documentation

Topics: graph | query | review | config | security | recipes

Returns complete documentation for each tool. Use when the compressed descriptions above are insufficient.

config__open_relay -- Re-trigger the relay setup form

Registered automatically from mcp-core. In HTTP mode it returns <PUBLIC_URL>/authorize so the agent can re-open the browser setup form (e.g. after credential expiry); in stdio mode it returns status: 'stdio_unsupported'.

Comparison

How better-code-review-graph stacks up against direct competitors in each pillar:

Capability	better-code-review-graph	Greptile	Sourcegraph (Cody / MCP)	CodeGraph (colbymchenry)
Codebase knowledge graph	Yes (Tree-sitter, 14 langs, SQLite)	Yes (functions/classes/deps)	Yes (precise code indexing)	Yes (Tree-sitter, 20+ langs, SQLite)
Persistent incremental updates	Yes (git-diff + file-hash re-parse)	?	Yes (continuous indexing)	Yes (OS file-watcher debounced)
Qualified call resolution (callers/callees)	Yes (same-file bare-call resolution + fallback)	?	Yes (go-to-def / find-references)	Yes (callers / callees / impact)
Semantic search / embeddings	Yes (qwen3 ONNX local + cloud Jina/Gemini/OpenAI/Cohere)	?	Yes (semantic + keyword + regex)	No (FTS5 full-text only)
Token-optimized review context	Yes (review tool, git-diff scoped)	Yes (PR review comments)	No (code-context assistant)	No (context layer, not review)
Security scanning	Yes (Semgrep p/auto + 3-rule overlay, SARIF)	?	?	No
Self-hostable	Yes (stdio default, machine-bound)	Yes (Docker / K8s / air-gapped)	Yes (self-hosted instance)	Yes (100% local, no API keys)
Free / open source	Yes (MIT)	No (proprietary SaaS; free OSS tier)	No (Enterprise license, source private)	Yes (MIT)

Sources: Greptile · Greptile pricing · Sourcegraph MCP · CodeGraph. Cells marked ? are capabilities the competitor does not publicly document, not confirmed absences.

Security

• Graceful fallbacks -- Cloud embedding failure falls back to local ONNX
• Error handling -- Tools return error strings with fix suggestions, never crash
• Read-only mount -- Docker mode mounts repo as :ro (read-only)

Build from Source

git clone https://github.com/n24q02m/better-code-review-graph
cd better-code-review-graph
uv sync --group dev
uv run pytest
uv run better-code-review-graph

Requirements: Python 3.13, uv

Trust Model

This plugin implements TC-Local (machine-bound, single trust principal). See the mcp-core trust model for full classification.

Mode	Storage	Encryption	Who can read your data?
stdio (default)	~/.better-code-review-graph-mcp/config.json	AES-GCM, machine-bound key	Only your OS user (file perm 0600)
HTTP self-host	Same as stdio	Same	Only you (admin = user)

License

MIT -- See LICENSE.