MCP SERVERBuild a knowledge graph of the codebase once, then ask what a change reaches, get token-efficient review context, and scan for security issues over the graph.
LABSCO SUMMARY
The review tool is the payoff: instead of feeding a model a raw diff, it auto-detects the changed files, resolves what they impact through the call graph, and returns a structural summary with just the relevant snippets — which is where the token efficiency comes from. Running the security scan over the same graph means findings carry the structural context of what calls what, and the local-ONNX default keeps the whole thing working without sending code to an embedding service.
A code-knowledge-graph server for token-efficient code review: 7 composite tools — graph, query, review, security, config, help and a relay-setup helper — each dispatching to a set of actions, with semantic search and call-graph resolution across the codebase. Embeddings run locally by default.
Python 3.13, run with uvx better-code-review-graph over stdio, or from the Docker image. Embeddings default to a local ONNX model — no API key — with EMBEDDING_MODELS to configure a cloud or ordered model chain and SUMMARY_MODELS to enable summaries (empty disables them).
One command — uvx better-code-review-graph
USE CASES
Build the graph for the repo, then let the review tool auto-detect the changed files and hand back a structural summary, the impacted nodes and only the snippets that matter — instead of the full diff.
Run impact analysis over the changed files to see what depends on them, and spot-check random callsites from the result to confirm the graph is right before trusting it.
Scan over the knowledge graph with the heuristic or semgrep engine, export a SARIF report, and suppress the rules that do not apply.
Update the graph incrementally as the code changes, check its stats, and export it to move to another machine or CI runner.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
configServer configuration, status, and credential setup. Actions: status (show state), set (key, value -- keys: log_level), cache_clear (wipe embeddings), setup_status (credential state), setup_start (relay browser setup), setup_skip (local mode), setup_reset (clear credentials), setup_complete (re-resolve from env). Use help tool for full docs.
config__open_relayGet the relay configuration URL for better-code-review-graph, opening it in the user's browser when possible. Returns the relay URL, whether the browser launched, and the current status.
graphBuild and manage the code knowledge graph. Actions: build (full_rebuild, base, repo_root), update (base, repo_root), stats (repo_root), embed (repo_root), export (format, output_path, repo_root), import (import_path, repo_root), summarize (max_nodes, repo_root). Use help tool for full docs.
helpGet full documentation for any tool. Topics: graph | query | review | config | security | recipes. Use when compressed descriptions are insufficient.
queryQuery the code knowledge graph for relationships, search, and impact analysis. Actions: query (pattern, target), search (search_query), impact (changed_files|base), large_functions (min_lines), spot_check (n -- random callsite snippets from last callers_of/callees_of/inheritors_of/importers_of result), renamed_in_diff (base -- symbols whose callsite line shifted vs base ref), diff (from_sha, to_sha -- nodes added/removed/modified between two commit SHAs). Use help tool for full docs.
reviewGenerate token-efficient review context for code changes. Actions: context (default — auto-detects changed files from git diff, returns structural summary, impacted nodes, source snippets, and review guidance), delta (from_sha, to_sha — wraps the query.diff buckets and, when show_line_shifts=true, surfaces qualified_names whose line_start moved between the two commits for refactor auditing). Context params: changed_files (auto), max_depth=2, include_source=true, max_lines_per_file=200, base='HEAD~1', repo_root (auto). Delta params: from_sha, to_sha, show_line_shifts=false, repo, repo_root. Use help tool for full docs.
securitySecurity scanning over the code knowledge graph. Actions: scan (engine='heuristic'|'semgrep', repo_root), report (format='json'|'sarif', repo_root), suppress (rule_id, remove=false, repo_root), rule_list (engine='heuristic'|'semgrep'). Use help tool for full docs.
BEFORE YOU INSTALL
7 tools when we connected. Each tool is a router, with about 30 actions between them: graph, query, review, config and security take an action argument. large_functions and spot_check are actions of query, not tools.
uvx on PATH
The documented client runs the server on your machine.
CONTEXT COST
Rated by the size of the 7 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
uvx better-code-review-graph{
"mcpServers": {
"better-code-review-graph": {
"command": "uvx",
"args": [
"--python",
"3.13",
"better-code-review-graph"
],
"env": {
"MCP_TRANSPORT": "stdio"
}
}
}
}MCP servers
jgravelle
sverklo
cappyeo
jghiringhelli