BlastRadius: Why Severity Scores Lie, and How Graph AI Solves Real Attack Paths

A developer built BlastRadius, an open-source graph-native AI agent that uses FalkorDB and the Model Context Protocol to map real attack paths through hybrid cloud infrastructure rather than ranking vulnerabilities by CVSS severity. The tool traces reachability from internet-facing entry points to crown-jewel assets via OpenCypher variable-length path queries, arguing that vector-database RAG approaches fail because vector distance does not capture topological connectivity.

"Defenders think in lists. Attackers think in graphs. As long as this is true, attackers win." — John Lambert, Distinguished Engineer, Microsoft Threat Intelligence It is 2:14 AM. Your security scanner finishes sweeping your hybrid cloud infrastructure and drops a fresh spreadsheet into your ticketing queue: 4,821 open vulnerabilities . Two hundred of them are flagged with a CVSS 9.8 or 10.0 Critical . Your SecOps team has the engineering bandwidth to patch roughly ten servers this sprint. How do you choose? If you do what 95% of security teams do, you sort the column by CVSS descending and start patching from the top: legacy-ftp : CVSS 10.0 Log4j remote code execution . batch-legacy : CVSS 9.8 CGI deserialization exploit . Congratulations: your team spent 36 uninterrupted engineering hours patching two isolated, legacy servers sitting on an air-gapped staging subnet with zero egress and zero access to customer data. Meanwhile, an unpatched CVSS 7.5 OpenSSL bug on your internet-facing api-gateway sat at ticket 384 in your backlog. Six hours later, an adversary used that single gateway to pivot into your microservices mesh and exfiltrate your entire customer database in three hops . The Vulnerability Mirage Isolated Subnet: Attacker ──x── legacy-ftp CVSS 10.0 ──x── DEAD END Production Route: Attacker ───── api-gateway CVSS 7.5 ───── db-customers PII ▲ └── THE REAL ATTACK PATH Severity scores tell you how dangerous a vulnerability is in isolation. They tell you nothing about whether an adversary can actually reach your crown jewels. We built BlastRadius https://github.com/saksham-2x7/BlastRadius V1 to invert this paradigm: a graph-native, autonomous AI agent powered by FalkorDB and the Model Context Protocol MCP that maps true network reachability, calculates topological choke points, and safely remediates attack paths without taking down production. Why hasn't the cybersecurity industry solved this already? Because answering the fundamental question— "Can an attacker on the public internet walk from an exposed ingress point to our customer database through exploitable vulnerabilities?" —is computationally agonizing in relational databases. To trace lateral movement across a dynamic cloud network in a relational database, you must execute recursive Common Table Expressions WITH RECURSIVE across five separate tables: hosts , network interfaces , firewall rules , installed services , and cve vulnerabilities . At 4 hops, relational engines devolve into massive Cartesian joins that bring relational query planners to their knees. Many modern "AI security tools" attempt to dump scan reports into vector databases RAG and prompt an LLM: "Find the attack path." This fails disastrously. Vector distance is not topological connectivity. LLMs cannot reliably trace multi-hop network paths in natural language; they hallucinate hops through air-gapped subnets, fabricate firewall allowances, and skip critical lateral constraints. In FalkorDB https://www.falkordb.com/ , network infrastructure is represented in its natural state: a directed property graph. Because FalkorDB is built on sparse matrix linear algebra GraphBLAS running over the ultra-fast Redis wire protocol, variable-length path traversal is not a pointer-chasing crawl—it is an optimized linear algebraic matrix multiplication executed in microseconds. Finding all paths from the public internet to our crown jewel database is a single OpenCypher query: php MATCH path = entry:InternetEntry - :EXPLOITABLE ROUTE 1..5 - target:CrownJewel {name: 'db-customers'} RETURN path, length path AS hops Public Internet │ ├── edge-apache ── api-gateway ──┐ ├── edge-nginx ── api-gateway ──┼── db-customers CROWN JEWEL ├── edge-node ── api-gateway ──┘ └── edge-apache ── worker-java ───── db-customers One query. Instant topological reality. FalkorDB identifies the exact four attack routes an adversary can execute today. To reflect real enterprise environments, BlastRadius ingests live vulnerability telemetry: Look at how raw scores compare to graph-grounded reality in our testbed: | Server Host | Role | Primary Vulnerability | CVSS | EPSS / KEV | Graph Attack Paths | True Threat Status | |---|---|---|---|---|---|---| | legacy-ftp | Deprecated Storage | Log4j CVE-2021-44228 | 10.0 | High KEV | 0 | Noise No route to crown jewels | | batch-legacy | Internal Batch Job | CGI RCE CVE-2014-6271 | 9.8 | Moderate | 0 | Noise Dead-end subnet | | api-gateway | Microservice Ingress | OpenSSL CVE-2022-3602 | 7.5 | Low | 3 of 4 | CRITICAL CHOKE POINT | If you follow traditional security advice, you spend your week patching legacy-ftp and batch-legacy . Your customer database remains completely exposed. BlastRadius immediately surfaces that patching a single CVE on api-gateway eliminates 75% of your total attack surface in one stroke. A common anti-pattern in generative AI projects is "Text-to-SQL" or "Text-to-Cypher," where the LLM is asked to write raw queries against production databases. In cybersecurity, this is unacceptable: BlastRadius uses the Model Context Protocol MCP . The LLM agent never writes raw Cypher. Instead, it interacts with FalkorDB through deterministic, strongly-typed MCP tools: ┌─────────────────┐ MCP Request ┌──────────────────┐ │ │ ────────────────────── │ │ │ AI Agent │ │ FalkorDB Engine │ │ Reasoning Core │ <────────────────────── │ Ground Truth │ └─────────────────┘ Typed Subgraph └──────────────────┘ find choke points : Runs FalkorDB's betweenness centrality algorithms to mathematically score nodes that funnel the highest percentage of attack traffic. get shortest attack path source, target : Executes FalkorDB's native shortest-path traversal to calculate minimum attacker effort. simulate remediation target node : Clones the active subgraph in memory, simulates patching or isolating the node, and recalculates remaining attack paths. apply remediation target node : Commits changes to the live graph and updates state. draft jira ticket finding : Formats an engineering ticket containing exact reproduction paths, affected assets, and rollback plans. When an operator asks: "Show the shortest route an attacker could take" , real-world networks often feature symmetric microservice ingress paths. In our reference architecture, FalkorDB evaluates all possible attack routes and detects a four-way tie , each requiring exactly 3 hops: internet → edge-apache → api-gateway → db-customers edge-nginx → edge-node → worker-java → Rather than arbitrarily picking one route or truncating results, BlastRadius highlights all four tied paths across our React Flow topology canvas simultaneously. Operators immediately grasp the redundancy of the adversary's options. The biggest obstacle to AI agents in infrastructure is trust . Nobody wants an autonomous agent making blind changes to production services. Most AI projects attempt to enforce safety through system prompts: "You are a helpful assistant. Please do not modify critical servers without asking." This is dangerous. LLM system prompts can be bypassed, misunderstood, or ignored under complex context windows. In BlastRadius, the graph enforces safety, not the AI prompt. User: "Fix everything safe" │ ▼ Agent: Inspect Node Tier │ ┌────────────────┴────────────────┐ ▼ ▼ Tier 1: Leaf Worker Tier 3: Choke Point Low Betweenness Centrality High Centrality / Ingress │ │ ▼ ▼ Simulate in FalkorDB REFUSE TO MODIFY │ │ ▼ ▼ Apply Patch Draft Jira Ticket with Paths Drop: 4 → 1 Rollback & Graph Proof Before touching any node, the MCP server calculates the node's Autonomy Tier directly from FalkorDB metrics: When the operator types: "Fix everything that is safe" , the agent patches the edge servers autonomously—dropping attack paths from 4 down to 1. But when it encounters api-gateway , it explicitly refuses. The agent informs the operator: "Remediation refused for api-gateway . This node has high topological centrality and serves active ingress routes. Severing or modifying this node without maintenance coordination risks dropping production traffic. I have drafted Jira ticket SEC-402 with full graph evidence, affected paths, and a rollback plan for human approval." The model did not decide this out of caution; the graph topology mathematically forbade it . Traditional chatbot agents suffer from stateless amnesia. If you return to the console three days later and ask: "Why didn't you patch the API gateway on Tuesday?" , a typical agent has no idea what you're talking about. BlastRadius writes its actions, simulations, and refusals back into FalkorDB as first-class graph entities : CREATE d:AgentDecision { action: 'REMEDIATION REFUSED', target: 'api-gateway', reason: 'HIGH BETWEENNESS CHOKE POINT', risk score: 0.89, timestamp: 1729208000 } - :EVALUATED AGAINST - h:Host {name: 'api-gateway'} Because reasoning is stored natively in the graph: Enterprise security tools cannot be toy prototypes with hardcoded data. BlastRadius allows teams to click Use your own data , upload network inventory or vulnerability scans, and instantly instantiate a private, isolated graph. Because FalkorDB handles multi-tenant graph namespaces with zero overhead, each user or organization operates within a strictly partitioned graph space—allowing rapid scan-to-graph conversion without infrastructure friction. Most security tooling generates more data, more alerts, and more cognitive fatigue. BlastRadius does the opposite: Attackers will always think in graphs. It’s time our defenses did too.