convez.ai
MCP Server
spark1security

n0s1-mcp

spark1security/n0s1-mcp

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server for n0s1 — scan Jira, Confluence, Slack, GitHub, GitLab, Zendesk, Linear, Asana, and Wrike for leaked secrets via any MCP-compatible AI assistant.

Instalação

$npx convez-ai spark1security/n0s1-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
1
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
v1.1.6
Issues abertas
1
Contribuidores
2

README

A tradução para o português deste README ainda está na fila.

n0s1-mcp

An MCP server that exposes n0s1 secret-scanning capabilities as tools for AI assistants (Claude, Cursor, etc.).

Scan Jira, Confluence, Slack, GitHub, GitLab, Zendesk, Linear, Asana, Wrike, and local filesystems for leaked secrets — directly from your AI workflow.

Quickstart

No install required. Add this to your MCP client config and run via uvx:

{
  "mcpServers": {
    "n0s1": {
      "command": "uvx",
      "args": ["n0s1-mcp"]
    }
  }
}

For Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
For Claude Code: .claude/mcp.json in your project, or ~/.claude/mcp.json globally.

Available Tools

ToolDescriptionRequired params
scan_jiraScan Jira ticketsserver, email, api_key
scan_confluenceScan Confluence pagesserver, email, api_key
scan_slackScan Slack channelsapi_key
scan_githubScan GitHub repositoriesapi_key, owner
scan_gitlabScan GitLab projectsapi_key, owner
scan_zendeskScan Zendesk ticketsserver, email, api_key
scan_linearScan Linear issuesapi_key
scan_asanaScan Asana tasksapi_key
scan_wrikeScan Wrike tasksapi_key
scan_localScan local filesystemscan_path
get_scan_statusGet status of a running/completed scanreport_uuid
get_scan_findingsGet paginated findings for a completed scanreport_uuid
analyze_reportSubmit or advance async AI credential validationreport_uuid

All scan_* tools accept these optional parameters:

ParameterDescription
report_uuidUUID to assign to the scan report. When set, overrides the auto-generated UUID written to the report JSON.
ai_analysisQueue async AI credential validation after the scan (requires n0s1 Professional)
n0s1_api_keyn0s1 API key; overrides N0S1_TOKEN env var
allow_secret_uploadAllow encrypted secrets to be uploaded to the n0s1 backend (default: false)

Pass wait_minutes to analyze_report (or directly on a scan tool alongside ai_analysis) to block until analysis completes.

Environment Variables

Credentials can be passed as tool arguments or pre-set as environment variables:

VariableUsed by
N0S1_TOKENAll scan tools with ai_analysis — Professional mode uploads and AI analysis
JIRA_TOKENscan_jira, scan_confluence
JIRA_EMAILscan_jira, scan_confluence
SLACK_TOKENscan_slack
GITHUB_TOKENscan_github
GITLAB_TOKENscan_gitlab
ZENDESK_TOKENscan_zendesk
ZENDESK_EMAILscan_zendesk
LINEAR_TOKENscan_linear
ASANA_TOKENscan_asana
WRIKE_TOKENscan_wrike

Example with env vars pre-configured:

{
  "mcpServers": {
    "n0s1": {
      "command": "uvx",
      "args": ["n0s1-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_...",
        "JIRA_TOKEN": "ATATT..."
      }
    }
  }
}

Usage Examples

Once connected, ask your AI assistant:

  • "Scan my Jira project SEC for leaked secrets"
  • "Check the GitHub org mycompany for exposed API keys"
  • "Scan the /home/user/project directory for secrets"
  • "Run an AI analysis on the scan report abc123"

For full parameter reference and AI analysis workflow details, see docs/ai.md.

Publishing to PyPI

pip install hatch
hatch build
hatch publish

License

GNU General Public License v3 — same as n0s1.

Ver o original no GitHub

Bom para

Relacionados