tenable-mcp-server
An MCP server for Tenable Vulnerability Management and the Tenable One platform, enabling LLMs to query assets, vulnerabilities, scans, exposure metrics, attack paths, and more via natural language.
README
Tenable MCP Server
An MCP (Model Context Protocol) server for Tenable Vulnerability Management and the wider Tenable One platform. Connects LLMs like Claude to your Tenable instance for querying assets, vulnerabilities, scans, exposure metrics, attack paths, web app scans, cloud security findings, and more — via natural language.
Built with FastMCP v3 and pyTenable.
Features
- 58 tools across 25 modules: assets, vulnerabilities, scans, exposure scoring, Attack Path Analysis, Web App Scanning (WAS), Attack Surface Management (ASM), Cloud Security (CNAPP), container security, compliance, tags, agents, networks, policies, users/groups, audit log, and patch verification
- Mock mode for demos and development — full test suite and every tool works with zero credentials
- Pagination on all list endpoints with safety caps for large exports
- Markdown output optimized for LLM consumption
- Graceful degradation when licensed features (Lumin/Tenable One, WAS, CNAPP, ASM) are unavailable
- STDIO and HTTP transports supported
- Read-mostly surface: the only write operations are scan launch/stop and tag assign/unassign, all marked with MCP tool annotations
Quick Start
Prerequisites
- Python 3.11+
- uv (recommended) or pip
- Tenable VM API keys (generate here) — or none at all for mock mode
Install
git clone <repo-url> && cd tenable-mcp-server
uv venv && source .venv/bin/activate
uv pip install -e ".[dev]"
Configure
cp .env.example .env
# Edit .env with your Tenable API keys
Or export directly:
export TENABLE_ACCESS_KEY=your-access-key
export TENABLE_SECRET_KEY=your-secret-key
Run
# STDIO transport (default, for Claude Desktop / Claude Code)
tenable-mcp
# Mock mode (no API keys needed)
TENABLE_MOCK=true tenable-mcp
# HTTP/SSE transport (binds 127.0.0.1 by default)
tenable-mcp --transport http --port 8000
Claude Desktop Integration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"tenable": {
"command": "uv",
"args": ["run", "--directory", "/path/to/tenable-mcp-server", "tenable-mcp"],
"env": {
"TENABLE_ACCESS_KEY": "your-access-key",
"TENABLE_SECRET_KEY": "your-secret-key"
}
}
}
}
For mock/demo mode, set "TENABLE_MOCK": "true" in env and omit the API keys.
Tools Reference
All tools return Markdown. Read-only tools carry readOnlyHint: true annotations.
Assets & Exposure
| Tool | Description |
|---|---|
tenable_list_assets |
List assets with hostname/IP/OS filters and pagination |
tenable_get_asset_details |
Full asset detail by UUID (hostname, IPs, OS, AES, ACR, tags) |
tenable_get_exposure_score |
Cyber Exposure Score (CES) from Tenable One |
tenable_get_asset_exposure |
Per-asset AES (0-1000) and ACR (1-10) |
tenable_get_severity_summary |
Open vulnerability counts by severity |
tenable_list_exposure_views / tenable_get_exposure_view |
Tenable One exposure view cards with CES trend series |
Vulnerabilities & Plugins
| Tool | Description |
|---|---|
tenable_list_vulnerabilities |
List vulns with severity/VPR/CVE/state filters |
tenable_get_vulnerability_details |
Full plugin details (description, solution, references) |
tenable_get_asset_vulnerabilities |
Per-asset vulnerability list |
tenable_list_plugin_families / tenable_get_plugin_details |
Plugin family and plugin metadata |
tenable_verify_patched_assets |
Before/after verification that CVEs/plugins are fixed on given assets |
tenable_search_recast_rules |
Recast/accept rule search |
Scans, Scanners & Policies
| Tool | Description |
|---|---|
tenable_list_scans / tenable_get_scan_results / tenable_get_scan_history |
Scan inventory, results, run history |
tenable_launch_scan / tenable_stop_scan |
Scan lifecycle (write operations) |
tenable_list_scanners / tenable_get_scanner_details |
Scanner fleet |
tenable_list_policies / tenable_get_policy_details |
Scan policies |
tenable_list_folders / tenable_list_exclusions / tenable_get_exclusion_details |
Folders and scan exclusions |
Attack Path Analysis (Tenable One)
| Tool | Description |
|---|---|
tenable_list_attack_paths |
Prioritized attack paths with source/target and techniques |
tenable_list_attack_findings |
Attack path findings |
tenable_list_attack_techniques |
MITRE ATT&CK technique inventory |
tenable_apa_country_coverage |
Per-country APA coverage map bucketed by hostname prefix (ISO 3166-1 defaults, configurable) |
Web App Scanning, ASM, Cloud & Containers
| Tool | Description |
|---|---|
tenable_was_list_configs / tenable_was_get_scan_details / tenable_was_list_vulnerabilities |
Web App Scanning configs, scans, findings |
tenable_asm_list_assets / tenable_asm_get_asset_details |
Attack Surface Management inventory |
tenable_cloud_list_resources / tenable_cloud_list_findings |
CNAPP cloud resources and misconfigurations |
tenable_cloud_list_vm_vulns / tenable_cloud_list_container_image_vulns |
CNAPP VM and container image vulnerabilities |
tenable_list_container_images / tenable_list_container_repos / tenable_get_container_report |
Container Security |
Platform Administration
| Tool | Description |
|---|---|
tenable_list_tags / tenable_create_tag_value / tenable_assign_tags / tenable_unassign_tags / tenable_get_asset_tags |
Tag management |
tenable_list_agents / tenable_get_agent_details / tenable_list_agent_groups / tenable_get_agent_group_details |
Nessus agent fleet |
tenable_list_networks / tenable_get_network_details |
Network objects |
tenable_list_users / tenable_list_groups |
Users and groups |
tenable_list_audit_events |
Platform audit log |
tenable_list_compliance_findings / tenable_get_compliance_summary |
Compliance/audit findings |
Configuration
| Environment Variable | Default | Description |
|---|---|---|
TENABLE_ACCESS_KEY |
(required) | Tenable API access key |
TENABLE_SECRET_KEY |
(required) | Tenable API secret key |
TENABLE_URL |
https://cloud.tenable.com |
Tenable cloud URL |
TENABLE_MOCK |
false |
Enable mock mode for demo/testing |
TENABLE_MAX_EXPORT |
10000 |
Safety cap for export consumption |
TENABLE_DEFAULT_LIMIT |
50 |
Default pagination limit |
TENABLE_CLOUD_SECURITY_API_KEY |
(optional) | Tenable Cloud Security (CNAPP) API key |
TENABLE_ASM_API_KEY |
(optional) | Attack Surface Management API key |
TENABLE_HOSTNAME_COUNTRY_MAP |
(optional) | JSON map of hostname prefixes to country labels for APA coverage bucketing (defaults to ISO 3166-1 alpha-2) |
Development
# Run tests (uses mock mode automatically -- no credentials needed)
pytest tests/ -v
# Lint
ruff check src/ tests/
Architecture
- FastMCP v3 server with lifespan-managed
TenableIOclient - All pyTenable calls wrapped in
asyncio.to_thread()(pyTenable is synchronous) - Export iterators consumed with safety cap (
MAX_EXPORT_CONSUME = 10,000) then paginated in-memory - Cloud Security tools use direct GraphQL over httpx (https-only guard) instead of pyTenable's CNAPP client
- Error handling via
@handle_tenable_errorsdecorator mapping API errors to actionableToolErrormessages - Mock client mirrors the pyTenable interface with deterministic UUIDs for consistent test/demo data
Limitations
- License-gated features degrade, not fail: CES/AES/ACR, exposure views, APA, WAS, ASM, CNAPP, and Container Security require the corresponding Tenable licenses; tools return an explanatory message when the feature is unavailable on your instance.
- Tenable VM (cloud) only — Tenable Security Center (on-prem) is not supported; its API differs substantially.
- Export scale: vulnerability/asset exports are capped at
TENABLE_MAX_EXPORTrecords per call to keep responses LLM-sized. This is not a full data-lake export tool. - Write surface is minimal by design: scan launch/stop and tag operations only. No remediation, recast, or user-management writes.
- APA country coverage relies on hostname prefixes when asset tags are absent; hostnames that don't encode location won't bucket (they are reported as unmapped rather than guessed).
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。