
Code graph for AI agents: impact analysis and call tracing over MCP (Python, TypeScript). Local
Code graph for AI agents: impact analysis and call tracing over MCP (Python, TypeScript). Local, deterministic, SQLite.
·
Ask "what breaks if I change this?" and get the call chain, not a guess.
CGIS parses a repository with tree-sitter into a graph of fully qualified symbols and the calls, imports and containment between them, stores it in SQLite, and serves it to AI agents over MCP. An agent that would otherwise grep and read whole files asks the graph instead.
--data-keys: no symbols, calls or impact)$ cgis ingest src --output graph.db
$ cgis impact cgis.query.engine.QueryEngine.get_flow_graph --db graph.db --depth 2
🔍 Analyzing transitive upstream callers of: cgis.query.engine.QueryEngine.get_flow_graph
METHOD cgis.query.engine.QueryEngine.get_flow_graph (cgis/query/engine.py:215)
├── FUNCTION cgis.query.context.context_service._collect_callees (cgis/query/context/context_service.py:44)
│ └── FUNCTION cgis.query.context.context_service.build_context (cgis/query/context/context_service.py:96)
└── METHOD cgis.guardian.collector.ContextCollector._graph_sections (cgis/guardian/collector.py:174)
├── METHOD cgis.guardian.collector.ContextCollector.collect_graph_context (cgis/guardian/collector.py:213)
└── METHOD cgis.guardian.collector.ContextCollector.collect_for_chunk (cgis/guardian/collector.py:303)Real output — CGIS run on its own source.
/plugin marketplace add zaebee/codegraph-brain
/plugin install cgis@codegraph-brainThat ships the MCP server, a skill that teaches the agent when to query the graph instead of reading files, and /cgis:ingest to build the graph on first use. The server is pulled from PyPI on demand via uvx, so there is nothing to clone or build.
{
"mcpServers": {
"cgis": { "command": "uvx", "args": ["--from", "codegraph-brain", "cgis-mcp"] }
}
}# No install needed — uvx fetches it from PyPI
uvx --from codegraph-brain cgis ingest ./my-project --output graph.db
uvx --from codegraph-brain cgis impact "my_module.core_function" --db graph.db --depth 5 # who calls this
uvx --from codegraph-brain cgis trace "my_module.MyClass.run" --db graph.db --depth 3 # what this calls
# add --format mermaid (or json) to either for a diagram or machine-readable outputOr install it for good: pip install codegraph-brain (Python 3.12+), then use cgis directly. The full command list is in CLI_USAGE.md.
CGIS runs on a working twelve-repository estate — four languages, 8,146 commits, shipping daily. On its FastAPI backend it classifies 82.7% of 87,845 edges definitively and prints the remaining 17.3% rather than inventing targets for them — including the part that is CGIS's own gap.
That share rose from 11.4% in #459, which stopped counting calls to missing symbols as resolved. About 4 points of what is left is a known resolver gap, not something undiscoverable: ingesting app/ strips the app. prefix its imports carry, and the import path does not yet reconcile the two — the same backend ingested at its package root reports 13.2%. The number is what the tool admits it cannot place today, and it is allowed to move the unflattering way.
Read the case study → — every figure measured and reproducible, including what CGIS doesn't cover.
Text retrieval hands an agent chunks that look related. It cannot say which of three functions named save a call reaches, or what sits five callers up. CGIS resolves every call site to a fully qualified name when the source allows it — and when it does not, the edge stays marked unresolved and is counted, never filled with a plausible guess.
| If you use… | CGIS adds |
|---|---|
| grep / file reads in the agent | Transitive callers and callees in one call, without spending context on whole files |
| LSP-backed symbol tools (e.g. Serena) | A persisted whole-repo graph for multi-hop impact, coupling, PageRank and drift |
| A repo map (e.g. aider) | Resolved edges you can traverse and audit, with the resolved/unresolved ratio reported |
The main tools:
| Tool | Answers |
|---|---|
cgis_ingest | Build or incrementally refresh the graph |
cgis_overview | Where to start: sizes and the largest packages, when you have no FQN yet |
cgis_find_symbol | Partial name → candidate FQNs |
cgis_analyze_impact | What breaks upstream if this changes? |
cgis_trace_flow | What does this call, transitively? |
cgis_get_structure | Class / module hierarchy |
cgis_context | A compact GraphRAG context package for one symbol |
cgis_metrics | Coupling, god classes, PageRank, package cohesion |
cgis_audit_reachability | Authz / IDOR coverage — does every handler reach its guard? |
cgis_drift | How far each domain has moved from its declared pattern |
cgis_validate | Graph integrity: resolved vs unresolved edges |
All 16 tools, with parameters: MCP_REFERENCE.md.
ResolverEngine maps raw calls to fully qualified names, or leaves them explicitly unresolved.graph LR
A[Source Code] --> B[Extractors]
B --> C[Resolver Engine]
C --> D[(SQLite Graph DB)]
D --> E[MCP Server]
D --> F[Prompt Compiler]
E --> G[AI Agents]
F --> GThe details — and a pipeline graph CGIS regenerates from its own source on every change — are in HOW_IT_WORKS.md, and the full map of every document with its generated cross-references to the code is in docs/INDEX.md.
Guardian is CGIS's built-in LLM reviewer — it reviews pull requests using the graph as context, not just the diff text. It runs in CI and posts inline comments anchored to the exact line.
qwen2.5-coder, llama3.1, granite-code, …) for free local inference, or at Mistral / Gemini / Claude / OpenCode Go (DeepSeek) in the cloud. You can even mix them — a strong cloud finder with a free local cross-model skeptic.# Build the graph, then review a PR with a local model (no API key).
# --inline posts over HTTPS with GH_TOKEN (or GITHUB_TOKEN); no gh CLI needed.
# The reusable workflow exports GH_TOKEN for you.
cgis ingest ./src --output graph.db
GUARDIAN_PROVIDER=ollama GUARDIAN_MODEL=qwen2.5-coder:14b \
uv run python scripts/guardian_review.py --pr 123 --db graph.db --inline
# Or OpenCode Go / DeepSeek: deepseek-v4.1-flash unless GUARDIAN_MODEL names another.
# GUARDIAN_OPENCODE_EFFORT is low unless set (the catalog lists low|high|max; other values
# pass through to the gateway). GUARDIAN_OPENCODE_BASE_URL pins a different gateway.
# No ANTHROPIC_API_KEY is needed for this provider.
GUARDIAN_PROVIDER=opencode-go GUARDIAN_MODEL=deepseek-v4.1-flash OPENCODE_API_KEY=... \
uv run python scripts/guardian_review.py --pr 123 --db graph.db --inline
# Or a Claude skeptic over a Mistral finder: Claude Haiku 5.5 unless GUARDIAN_SKEPTIC_MODEL names
# another, at GUARDIAN_ANTHROPIC_EFFORT=low unless set (low|medium|high|xhigh|max). Claude models
# reject a sampling temperature, so GUARDIAN_TEMPERATURE must be unset.
GUARDIAN_SKEPTIC=anthropic ANTHROPIC_API_KEY=... MISTRAL_API_KEY=... \
uv run python scripts/guardian_review.py --pr 123 --db graph.db --inlineIn GitHub Actions, opencode-go needs no static key: the reusable workflow exchanges a short-lived GitHub OIDC token for inference access immediately before the review. Enable OIDC for GitHub Actions in the Opencode console, set the calling repository's OPENCODE_CLIENT_ID variable, and grant the review job id-token: write. OPENCODE_API_KEY is then minted at run time and never stored as a secret. Sign-in happens when GUARDIAN_PROVIDER is opencode-go, opencode, or unset (unset means the minted key makes opencode the auto-detected provider); an explicit other provider skips it.
No GPU on hand? Benchmark it on a notebook GPU → — free end to end, since the fixtures score without an LLM judge. Or point Guardian at a remote Ollama → — over an frp stcp tunnel, no public port, and a guard that refuses a review of a silently truncated prompt.
CGIS collects nothing: no telemetry, no analytics, no account. Your code and the graph built from it stay on your machine. The one exception is opt-in: Guardian, if you run it with a cloud model, sends the reviewed diff to the provider you chose. See PRIVACY.md.
Requires Python 3.12+ and uv.
git clone https://github.com/zaebee/codegraph-brain && cd codegraph-brain
uv sync
make pytestSee CONTRIBUTING.md for the standards: strict MyPy, linting, ontology compliance.
CGIS is free and you can run it yourself. If you would rather have the analysis than the tool, I run a fixed-price audit of your codebase's structure — authorisation coverage, blast radius, coupling, architectural drift — delivered in five working days, $2,400 fixed, with an explicit list of what the analysis cannot see. Read what's included →
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add cgis -- uvx --from codegraph-brain cgis-mcp{
"mcpServers": {
"cgis": {
"args": [
"--from",
"codegraph-brain",
"cgis-mcp"
],
"command": "uvx"
}
}
}code --add-mcp '{"name":"cgis","args":["--from","codegraph-brain","cgis-mcp"],"command":"uvx"}'[mcp_servers.cgis]
command = "uvx"
args = ["--from", "codegraph-brain", "cgis-mcp"]Runs locally on your device. Your client starts the server itself, so nothing has to be hosted.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/codegraph-brain to learn what the "Codegraph Brain" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
uvx --from codegraph-brain cgis ingest ./my-project --output graph.db
uvx --from codegraph-brain cgis impact "my_module.core_function" --db graph.db --depth 5 # who calls this
uvx --from codegraph-brain cgis trace "my_module.MyClass.run" --db graph.db --depth 3 # what this callsThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/codegraph-brain)Nothing comparable is listed yet.
codegraph-brain-v0.40.0codegraph-brain: v0.40.0Release notescodegraph-brain-v0.39.2codegraph-brain: v0.39.2Release notescodegraph-brain-v0.39.1codegraph-brain: v0.39.1Release notescodegraph-brain-v0.39.0codegraph-brain: v0.39.0Release notescodegraph-brain-v0.38.0codegraph-brain: v0.38.0Release notescodegraph-brain-v0.37.0codegraph-brain: v0.37.0Release notescodegraph-brain-v0.36.0codegraph-brain: v0.36.0Release notescodegraph-brain-v0.35.0codegraph-brain: v0.35.0Release notescodegraph-brain-v0.34.0codegraph-brain: v0.34.0Release notescodegraph-brain-v0.33.0codegraph-brain: v0.33.0Release notescodegraph-brain-v0.32.0codegraph-brain: v0.32.0Release notescodegraph-brain-v0.31.0codegraph-brain: v0.31.0Release notescodegraph-brain-v0.30.0codegraph-brain: v0.30.0Release notescodegraph-brain-v0.29.0codegraph-brain: v0.29.0Release notescodegraph-brain-v0.28.0codegraph-brain: v0.28.0Release notescodegraph-brain-v0.27.0codegraph-brain: v0.27.0Release notescodegraph-brain-v0.26.0codegraph-brain: v0.26.0Release notescodegraph-brain-v0.25.4codegraph-brain: v0.25.4Release notescodegraph-brain-v0.25.3codegraph-brain: v0.25.3Release notescodegraph-brain-v0.25.2codegraph-brain: v0.25.2Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "codegraph-brain" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.