Models microservice topology in Neo4j and provides tools for directional lineage traversal, causal hypothesis ranking, composite risk scoring via graph metrics (PageRank, consumer counts, error ratios), and remediation audit tracking through Cypher queries.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@blastradius-mcp checkout-api is failing—trace downstream blast radius and rank likely root causes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Multi-hop microservice and dependency triage agent. It models a service topology in Neo4j, exposes triage and remediation tools over FastMCP, and drives them with a LangGraph workflow that pauses for human approval before anything mutating runs.
Capability | Module | Summary |
Directional lineage |
| Upstream dependency chain or downstream blast radius, with direction rules per edge type, plus a Mermaid diagram. |
Causal ranking |
| Scores root-cause candidates from four signals: graph hop distance, temporal delta, git-diff vs stack-token overlap, and trace match. |
Redundancy-aware risk |
| Composite score from PageRank, business tier, consumer count and error ratio. A healthy |
Safe remediation |
| Stages a dry-run plan with a rollback command, then executes only with approval and the |
Triage agent |
| LangGraph flow: investigate, risk and stage, |
Related MCP server: coderadius
blastradius-mcp/
├── pyproject.toml
├── docker-compose.yml # Neo4j 5.23 community
├── demo_runner.py # End-to-end demo
├── manifests/
│ ├── topology_seed.yaml # Services, workers, queues, datastores, configs, schemas
│ └── incident_fixtures.json # Simulated git diffs and error telemetry
└── app/
├── main.py # FastAPI app, mounts FastMCP at /mcp
├── config.py # Pydantic settings
├── models/schemas.py # Pydantic models and enums
├── db/ # Neo4j client and Cypher queries
├── ingestion/seed_graph.py # YAML and fixtures loader, PageRank
├── services/ # Lineage, hypothesis, risk, remediation
├── mcp_server/ # FastMCP server and tools
└── agent/triage_graph.py # LangGraph workflowPython 3.14 (pinned in .python-version)
Docker, for Neo4j
# 1. Start Neo4j
docker compose up -d
# 2. Install dependencies
uv sync
# 3. Run the end-to-end demo (seeds the graph, runs the agent, approves a plan)
uv run python demo_runner.py
# 4. Or start the API and MCP server
uv run uvicorn app.main:app --reload --port 8000Swagger UI: http://localhost:8000/docs
MCP endpoint: http://localhost:8000/mcp
Neo4j Browser: http://localhost:7474
Seeding runsMATCH (n) DETACH DELETE n. It wipes the entire database, including audit records. Only point it at a disposable Neo4j instance.
Settings are read from environment variables or a .env file.
Variable | Default |
|
|
|
|
|
|
|
|
The default password matches docker-compose.yml and is for local development only.
Method | Path | Purpose |
POST |
| Reset and seed the graph |
GET |
| Lineage traversal |
GET |
| Composite risk for a node |
POST |
| Run the agent until it pauses for approval |
POST |
| Resume the agent with an approval decision |
Tool | Type | Scope |
| Read-only |
|
| Read-only |
|
| Read-only |
|
| Staging, non-destructive |
|
| Mutating |
|
raw = 0.30*pagerank + 0.30*tier_weight + 0.25*consumer_ratio + 0.15*error_ratio
final = raw * (0.35 if healthy fallback else 1.0)Severity bands: P0 >= 0.75, P1 >= 0.50, P2 >= 0.25, P3 < 0.25.
Tier weights: TIER_1 1.0, TIER_2 0.75, TIER_3 0.40, TIER_4 0.10.
app/mcp_server/server.py (scope interceptor) is not implemented yet. Scope checks currently happen only inside execute_approved_plan, using scopes supplied by the caller.
Remediation is simulated: executing a plan updates the audit node but does not run git revert.
The LangGraph checkpointer is in-memory, so paused threads are lost on restart.
Apache License 2.0. See LICENSE.
This server cannot be deployed
Reliability intelligence: production incidents, risk register, controls catalog, knowledge graph.
Causal reasoning for reliability: root cause, blast radius, and service health for agents.
Change-impact intelligence for tracing dependencies, stale references and required updates.
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
