Skip to main content
Glama
Sign In
@darkmoon_ai/mcp-server

@darkmoon_ai/mcp-server

by ASCIT31
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

@darkmoon_ai/mcp-server

A Model Context Protocol server that lets an MCP client (Claude Desktop, Goose, Continue, LibreChat, ...) drive Darkmoon, an open source (GPL-3.0) autonomous AI penetration testing platform.

Requires Darkmoon Pro

The Darkmoon engine and CLI are open source. This server talks to the Darkmoon Dashboard API, which is part of Darkmoon Pro and always self-hosted: there is no public hosted endpoint, so you supply the base URL of your own instance. It does not work against the open source CLI alone.

Related MCP server: Pentest MCP

Tools

Tool

Description

run_pentest

Start an autonomous pentest against one authorized target and return the run_id

get_run_status

Report running, completed, error or unknown for a run, from its run log

list_campaigns

List campaigns visible to the dashboard user (read only)

get_findings

Vulnerabilities and severity statistics for a campaign (read only)

Only run assessments against systems you own or are explicitly authorized in writing to test. Findings can include false positives and must be reviewed by a qualified human.

Configuration

Variable

Description

DARKMOON_BASE_URL

Base URL of your Darkmoon Pro Dashboard API (required)

DARKMOON_USERNAME, DARKMOON_PASSWORD

Dashboard credentials; a JWT is requested on each call and never cached

DARKMOON_TOKEN

Alternative to username/password: a pre-issued JWT

DARKMOON_TIMEOUT_MS

Optional per-request timeout, default 60000

Client configuration

Claude Desktop (claude_desktop_config.json), Continue and LibreChat use the same mcpServers shape:

{
  "mcpServers": {
    "darkmoon": {
      "command": "npx",
      "args": ["-y", "@darkmoon_ai/mcp-server"],
      "env": {
        "DARKMOON_BASE_URL": "https://darkmoon.example.internal",
        "DARKMOON_USERNAME": "your-dashboard-user",
        "DARKMOON_PASSWORD": "your-dashboard-password"
      }
    }
  }
}

Goose (~/.config/goose/config.yaml):

extensions:
  darkmoon:
    type: stdio
    enabled: true
    name: darkmoon
    cmd: npx
    args: ["-y", "@darkmoon_ai/mcp-server"]
    envs:
      DARKMOON_BASE_URL: https://darkmoon.example.internal
      DARKMOON_USERNAME: your-dashboard-user
      DARKMOON_PASSWORD: your-dashboard-password

Continue (.continue/mcpServers/darkmoon.yaml):

name: Darkmoon
version: 0.1.0
schema: v1
mcpServers:
  - name: darkmoon
    command: npx
    args: ["-y", "@darkmoon_ai/mcp-server"]
    env:
      DARKMOON_BASE_URL: https://darkmoon.example.internal
      DARKMOON_USERNAME: your-dashboard-user
      DARKMOON_PASSWORD: your-dashboard-password

Develop

npm install
npm run build
npm test      # mocked Dashboard API, in-memory MCP client and a real stdio process

License

GPL-3.0-only, same as Darkmoon.

Available Tools

4 tools
get_findingsGet campaign findingsA
Read-only

Return the vulnerabilities and aggregated severity statistics for a Darkmoon campaign (read only). Each finding carries title, severity, CVSS score, category, status (exploited, confirmed or unconfirmed), endpoint and remediation guidance. Findings may contain false positives and require human review.

Inputs: campaign_id (required).

get_run_statusGet run statusA
Read-only

Report whether a Darkmoon run is 'running', 'completed', 'error' or 'unknown' (run log not found), with the event count and the 5 most recent events.

Inputs: run_id (required).

list_campaignsList campaignsA
Read-only

List the Darkmoon campaigns visible to the dashboard user, with ids and status. Use a campaign id with get_findings.

Inputs: no named parameters.

run_pentestStart a Darkmoon pentestA

Start an autonomous Darkmoon penetration test against one authorized target. The run executes in the background and can take a long time. Returns the run_id; poll it with get_run_status and read results with get_findings once a campaign exists (list_campaigns). Only use against systems the user owns or has explicit written authorization to test. Findings can include false positives and must be reviewed by a qualified human.

Inputs: target (required), focus, program, severity.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation4/5

    Each tool targets a distinct action (start, status, list campaigns, get findings), but the relationship between a 'run' and a 'campaign' is not fully clear, which could cause slight misselection between get_run_status and list_campaigns when checking progress.

    Naming Consistency5/5

    All names follow a consistent snake_case verb_noun pattern (run_pentest, get_run_status, list_campaigns, get_findings), with clear verb prefixes that are easy to predict.

    Tool Count5/5

    Four tools is well-scoped for a focused pentest service; each tool (start, monitor, list campaigns, read findings) earns its place without redundancy or bloat.

    Completeness3/5

    Core start-monitor-results workflow is covered, but notable gaps exist: no cancel/stop for long-running runs, and no explicit way to map a run_id to its resulting campaign, forcing agents to guess from list_campaigns.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • keel

      lutfizp
      A
      license
      C
      quality
      C
      maintenance
      Enables authorized pentest and bug bounty workflows from any MCP client, with scoped recon, per-host rate limits, and scanner output turned into deduplicated, triaged finding cards.
      9
      19 PyPI
      2
      MIT

    • Pentest MCP

      fnelson71
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables authorized penetration testers to run reconnaissance, scanning, brute-force, exploitation, traffic capture, wordlist generation, and client-report workflows through MCP clients, with stdio/HTTP/SSE transport and OIDC bearer authentication.
      165 npm
      GPL 3.0

    • Pentest MCP

      daikiward0871
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables authorized penetration-testing workflows through MCP by exposing tools for network scanning, web fuzzing, subdomain enumeration, vulnerability scanning, brute-force checks, packet capture, and report generation with HTTP/STDIO/SSE transports and bearer/OIDC authentication.
      165 npm
      GPL 3.0

    • Pentest MCP

      erkut9520
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables authorized penetration testers to run reconnaissance, scanning, brute-force, traffic-capture, and exploitation tools through MCP clients, with authentication, engagement recordkeeping, and client report generation.
      165 npm
      GPL 3.0