Whispergraph Mcp Server

Created By
Whisper Securitya month ago
Open-source, self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.
Overview

The internet's largest queryable infrastructure graph — 7.39 billion nodes, 39 billion edges, 5.6 million threat-intelligence relationships. Pivot from any IP, domain, or ASN across DNS, BGP, WHOIS, GeoIP, and threat intel in a single Cypher query.

Why WhisperGraph Most threat-intel and OSINT APIs are point lookups: you ask about one indicator, you get one record. Investigations don't work that way — you start from one suspicious domain and need to trace its hosting, its sibling domains, its registrar, its email infrastructure, the ASN announcing its IP, and which feeds have flagged anything nearby.

WhisperGraph stores all of that as a single connected graph and lets you traverse it natively. One query can answer questions that would take dozens of API calls anywhere else.

What's in the graph Layer Coverage DNS Full resolution graph — hostnames, A/AAAA/CNAME/MX/NS/TXT records, DNSSEC chains BGP Announced and registered prefixes, ASN relationships, RIR allocations, routing conflicts GeoIP IP → city → country, with point geometry for distance queries WHOIS Registrars, registrant emails (237M), phones (65M), nameservers, timestamped history Email MX records, SPF includes, DKIM, DMARC policies Web Hyperlink graph between hostnames Threat Intel 5.6M edges from 40+ feeds across 18 categories — malware, phishing, C2, scanning, abuse 20 node labels, 29 edge types, updated continuously.

Who uses it Threat hunters & SOC analysts — enrich IOCs, find related infrastructure, triage alerts in seconds CTI teams — build campaign maps, attribute infrastructure clusters, track actor TTPs OSINT investigators & journalists — uncover ownership patterns, map shell-domain networks Security researchers — measure phishing kit reuse, study BGP hijacks, trace bulletproof hosting Bug bounty & red team — map external attack surfaces of target organizations Vendor risk & compliance — assess vendor infrastructure exposure Academics — internet measurement research at full-graph scale Tools Tool What it does query Execute a validated Cypher query. Returns structured JSON. explain_indicator One-call threat assessment of any IP, hostname, ASN, or CIDR — returns score, level, factors, sources whisper_history Timestamped WHOIS or BGP snapshots for an indicator list_labels All node labels with counts describe_label Properties and count for a given label Plus 5 MCP resources (schema, query guide, stats, quota) and 7 prompt templates for common investigations: investigate-ip, map-attack-surface, compare-domains, blast-radius, threat-triage, whois-pivot, bgp-investigation.

Example questions you can ask "What's the threat reputation of 45.142.213.55, and what feeds flagged it?" "Show every domain sharing this domain's MX records and registrant email." "Map the full DNS and BGP attack surface of example.com." "Which ASNs in Russia have the highest concentration of phishing-flagged IPs this quarter?" "Find all domains registered within 24 hours of suspicious-domain.com using the same registrar." "What's the historical WHOIS for disputed-domain.com going back 5 years?" "Which prefixes does AS13335 currently announce, and were any of them previously announced by a different ASN?"

Server Config

{
  "mcpServers": {
    "whisper-graph": {
      "command": "npx",
      "args": [
        "-y",
        "@whisper-security/whisper-graph-mcp"
      ],
      "env": {
        "WHISPER_API_KEY": "your-api-key"
      }
    }
  }
}
Project Info
Created At
a month ago
Updated At
a month ago
Author Name
Whisper Security
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Docwand

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

14 hours ago