Overview
What ThreatPulse does
ThreatPulse answers the question every vulnerability backlog raises: which of these CVEs are actually being exploited, and which should we patch first?
- GET /v1/cve/CVE-2021-44228 returns one CVE with severity, CVSS and its version, the FIRST EPSS exploit probability, CISA KEV status with the date added and known ransomware use, exploit status (none, poc, weaponized) with the Metasploit, ExploitDB or GitHub sources, patch and vendor advisory links, affected products and a 0-100 urgency score.
- GET /v1/feed/critical?hours=24&min_severity=CRITICAL lists CVEs updated in the last 1-168 hours at or above a severity, most urgent first.
- POST /v1/scan matches package names (openssl@3.0.1, apache:log4j) or a package-lock, CycloneDX or SPDX SBOM to known CVEs (first 200 unique packages per call).
- POST /v1/prioritize ranks up to 100 CVE IDs by urgency, with a boost for CVEs that affect products in your stack.
The urgency score is transparent: up to 40 points from EPSS, 30 for a weaponized exploit (15 for a proof-of-concept), 15 for CISA KEV membership and 15 when no patch exists.
Where the data comes from
About 387,000 CVEs from NVD, synced hourly; CISA Known Exploited Vulnerabilities and GitHub proof-of-concept repositories every 6 hours; FIRST EPSS scores, ExploitDB, Metasploit modules and vendor advisories daily.
Three ways to connect
- REST with an X-API-Key header, described by an OpenAPI 3 schema (https://threatpulse.waltsoft.net/openapi.json ).
- MCP: the tool threatpulse___threatpulseQuery on the Amazon Bedrock AgentCore Gateway (pass cve_id, or packages to scan), for Claude, Strands Agents and other MCP clients.
- A2A (Agent2Agent 0.3): the agent card at https://threatpulse.waltsoft.net/.well-known/agent-card.json with the skills getCve, getCriticalFeed, scanPackages and prioritizeCves.
Who it is for
DevSecOps and vulnerability management teams triaging scanner output, CI/CD pipelines that should fail a build only on exploited vulnerabilities, SOC and threat intelligence analysts, and AI security agents that need exploit context before recommending a fix.
Billing
You pay per successful call on your AWS bill. Errors (400, 401, 404, 429, 5xx) are never billed. Rate limit: 50 requests per second, bursts up to 100.
Highlights
- Exploit intelligence per CVE in one call: CVSS, FIRST EPSS probability, CISA KEV status and ransomware use, Metasploit / ExploitDB / GitHub exploits, patch links and a transparent 0-100 urgency score
- Prioritize the backlog: scan package lists or package-lock, CycloneDX and SPDX SBOMs, rank up to 100 CVEs for your stack, and follow a feed of newly updated critical CVEs (NVD synced hourly)
- Agent-ready: REST with an OpenAPI 3 schema, an MCP tool on Amazon Bedrock AgentCore Gateway and an A2A agent card with four skills; pay only for successful calls on your AWS bill
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Quick Launch
Pricing
Dimension | Description | Cost/unit |
|---|---|---|
API Call | Single API call to the service | $0.01 |
Vendor refund policy
Contact support@waltsoft.net within 30 days for refund requests.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
- Amazon Bedrock AgentCore
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
To get started using the remote MCP server, follow the instructions below:
Available Tools This MCP server (Amazon Bedrock AgentCore Gateway) supports the following tool:
- threatpulse___threatpulseQuery - CVE exploit intelligence. Arguments: api_key, plus either cve_id (e.g. CVE-2021-44228) for one CVE with CVSS, EPSS, CISA KEV, exploit status, patches and a 0-100 urgency score, or packages (e.g. ["openssl@3.0.1","apache:log4j"]) to scan dependencies for known CVEs.
Prerequisites
- An active subscription to this product. Your API key (it starts with mp_) is stored in your AWS Secrets Manager after you choose Set up your account, and is also shown on the registration page.
- Install Node.js and npm (for mcp-remote), or Python 3.10+ (for the Strands Agents SDK).
Authentication The MCP endpoint needs no connection header. Pass your key as the api_key argument of every tool call; replace YOUR_API_KEY with your actual key below. A wrong or inactive key returns error code 401.
MCP endpoint: https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp
Claude Desktop Edit the configuration file at:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the below code:
{ "mcpServers": { "waltsoft-threatpulse": { "command": "npx", "args": [ "mcp-remote", "https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp" ] } } }Then ask, for example: "Use threatpulse___threatpulseQuery with cve_id CVE-2021-44228 and api_key YOUR_API_KEY".
Strands Agents (Python)
pip install strands-agents mcp from mcp.client.streamable_http import streamable_http_client from strands.tools.mcp import MCPClient URL = "https://waltsoft-marketplace-gateway-xncyjgs1uh.gateway.bedrock-agentcore.us-east-1.amazonaws.com/mcp" with MCPClient(lambda: streamable_http_client(URL)) as mcp: result = mcp.call_tool_sync("call-1", "threatpulse___threatpulseQuery", {"cve_id": "CVE-2021-44228", "api_key": "YOUR_API_KEY"}) print(result["content"][0]["text"])Example tool result
{"cve_id": "CVE-2021-44228", "severity": "CRITICAL", "cvss": 10, "epss_score": 0.99999, "exploit_status": "weaponized", "exploit_sources": ["https://www.exploit-db.com/exploits/51183"], "in_cisa_kev": true, "first_exploited_date": "2021-12-10", "ransomware_campaign": "Known", "urgency_score": 85, "patch_available": true}With packages the result is {"scanned", "total_deps", "vulnerabilities": [...]} sorted by urgency.
Rate Limits
- 50 requests per second (bursts up to 100).
- Exceeding returns HTTP 429 Too Many Requests.
- Use retry and exponential backoff to handle limits.
Learn More API Docs: https://threatpulse.waltsoft.net Support: support@waltsoft.net
Support
Vendor support
Email support@waltsoft.net for API questions and integration help. Response within 24 hours.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.