What is the purpose of 漏洞扫描 MCP 服务器?
It automates vulnerability scanning for emergency response by generating nuclei POCs, uploading them to the Marshal platform, creating workflows, and submitting tasks.
@XTeam-Wing
Basic information
Mcp services by marshal
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
漏洞扫描 MCP 服务器 is an MCP server based on the go-mcp library that automates vulnerability scanning tasks during emergency response. It integrates with the Marshal platform to generate nuclei POCs, create scan workflows, and submit scanning tasks.
Clone the repository, build with go build -o marshal-mcp ., then run with ./marshal-mcp --config=config/config.yaml. Edit config/config.yaml to set the Marshal API URL and a valid API token. The server listens on port 8000 by default.
It automates vulnerability scanning for emergency response by generating nuclei POCs, uploading them to the Marshal platform, creating workflows, and submitting tasks.
The server requires an API token set in `config.yaml` under `api.token`. It is automatically added to all Marshal API requests via the `Authorization` header.
The required parameters are `vuln_name`, `vuln_desc`, `urls`, and `cluster`. Optional parameters include priority, task_name, task_num, cycle_scan, domain, ip, port, engine, and interval_days.
Yes, it supports both the MCP protocol and HTTP API.
The default priority is “low”, default port range is 1–65535, default scan engine is “naabu”, and default scan interval is 7 days.
Painless E2E Automation for Mobile and Web

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Hindsight: Agent Memory That Learns
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
A curated list of references for MLOps
Comments