MCP Server for OSCAL

MCP Server for OSCAL

Provides AI assistants with specialized tools to interact with NIST's Open Security Controls Assessment Language (OSCAL) framework. It enables agents to retrieve schemas, explore models, and generate valid OSCAL documentation for security compliance automation.

Category
访问服务器

README

<div align="center">

Build Status Version PyPI - Python Version PyPI PyPI - Downloads OSCAL GitHub License

</div>

MCP Server for OSCAL

<strong> Instant OSCAL expertise for your favorite AI agent </strong>

A Model Context Protocol (MCP) server that provides AI assistants (Claude, Cline, Kiro, Claude Code, etc.) with tools to work with NIST's Open Security Controls Assessment Language (OSCAL). Like many early adopters, we needed help implementing OSCAL proofs-of-concept to demonstrate value to business stakeholders. Perhaps due to limited availability of examples in the public domain, we found that most AI agents/LLMs alone produced inconsistent results related to OSCAL. The tools in this MCP server minimized that problem for our use-case and we hope it does the same for you.

[!TIP] To get started, see Installation below.

Features

Together, the tools provided by this MCP server are meant to enable your preferred AI assitant to provide accurate, authoritative gudiance about OSCAL architecture, models, use-cases, requirements, and implementation. You don't need to understand the tools to use them, but details are in the tools directory.

The server is lightwieght and meant to run locally without additional setup. By default, it uses stdio protocol for MCP transport. Do not attempt to use the server with streamble-http transport, as we've not yet implemented transport security or authentication.

The default tools should not connect to any remote services or resources - all required content is bundled with the server. As a security measure, we've implemented basic file integrity verification for bundled content. At build-time we generate manifests including SHA-256 hashes of all content files. Each time the server starts, all content files are verified against the hash manifests. Any mismatch should produce an error and prevent startup.

Existing tools and features cover a variety of use-cases but are far from comprehensive. Please share your feedback, feature requests, questions, or bug reports in a GitHub issue. Direct contributions are wanted and welcome.

What is OSCAL?

OSCAL (Open Security Controls Assessment Language) is a set of framework-agnostic, vendor-neutral, machine-readable schemas developed by NIST that describe the full life cycle of GRC (governance, risk, compliance) artifacts, from controls to remediation plans. OSCAL enables automation of GRC workflows by replacing digital paper (spreadsheets, PDFs, etc.) with a standard-based structured data format. To learn more about OSCAL, install this MCP server then ask your AI. Or see the official OSCAL website.

What is MCP?

MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect electronic devices, MCP provides a standardized way to connect AI applications to external systems.

How to use / Examples

Examples below were created with kiro-cli, but should work with any AI assistant that supports MCP servers.

Example 1: Learn about available OSCAL models

 % kiro-cli

> /tools trust get_oscal_schema list_oscal_models list_oscal_resources


Tools '@oscal/get_oscal_schema', '@oscal/list_oscal_models', '@oscal/list_oscal_resources' are now trusted. I will not ask for confirmation before running these tools.


> How many GA OSCAL models are there? 


> I'll check the available OSCAL models to find out how many are in GA (Generally Available) status.
Running tool list_oscal_models with the param (from mcp server: oscal)
 ⋮  {}
 - Completed in 0.1s

> There are 8 GA OSCAL models:

Control Layer (3):
- Catalog
- Profile  
- Mapping Collection

Implementation Layer (2):
- Component Definition
- System Security Plan (SSP)

Assessment Layer (3):
- Assessment Plan (SAP)
- Assessment Results (SAR)
- Plan of Action and Milestones (POA&M)

All of these models have "GA" (Generally Available) status, meaning they are stable and ready for production use.
 ▸ Time: 8s

Example 2: OSCAL template generation

> generate a minimum, valid, OSCAL mapping in JSON for use as a template.

> I'll help you create a minimal, valid OSCAL mapping in JSON. Let me first check what OSCAL models are available to understand the structure.
Running tool list_oscal_models with the param (from mcp server: oscal)
 ⋮  {}
 - Completed in 0.1s

> Now let me get the schema for the mapping-collection model to understand its structure:
Running tool get_oscal_schema with the param (from mcp server: oscal)
 ⋮  {
 ⋮    "model_name": "mapping-collection",
 ⋮    "schema_type": "json"
 ⋮  }
 - Completed in 0.14s

> Based on the schema, I'll create a minimal, valid OSCAL mapping collection template. Here's the absolute minimum required structure:
I'll create the following file: ./oscal-mapping-template.json (using tool: write)
Purpose: Create minimal OSCAL mapping collection template

+     1: {
+     2:   "mapping-collection": {
+     3:     "uuid": "12345678-1234-4567-8901-123456789012",
+     4:     "metadata": {
+     5:       "title": "Sample Mapping Collection",
+     6:       "last-modified": "2026-01-06T20:46:28.034Z",
+     7:       "version": "1.0",
+     8:       "oscal-version": "1.2.0"
+     9:     },
+    10:     "provenance": {
+    11:       "method": "human",
+    12:       "matching-rationale": "semantic",
+    13:       "status": "draft",
+    14:       "mapping-description": "Sample mapping between two control frameworks"
+    15:     },
+    16:     "mappings": [
+    17:       {
+    18:         "uuid": "87654321-4321-7654-1098-210987654321",
+    19:         "source-resource": {
+    20:           "type": "catalog",
+    21:           "href": "https://example.com/source-catalog.json"
+    22:         },
+    23:         "target-resource": {
+    24:           "type": "catalog", 
+    25:           "href": "https://example.com/target-catalog.json"
+    26:         },
+    27:         "maps": [
+    28:           {
+    29:             "uuid": "11111111-2222-3333-4444-555555555555",
+    30:             "relationship": "equivalent",
+    31:             "sources": [
+    32:               {
+    33:                 "type": "control",
+    34:                 "id-ref": "ac-1"
+    35:               }
+    36:             ],
+    37:             "targets": [
+    38:               {
+    39:                 "type": "control",
+    40:                 "id-ref": "access-control-policy"
+    41:               }
+    42:             ]
+    43:           }
+    44:         ]
+    45:       }
+    46:     ]
+    47:   }
+    48: }

Creating: ./oscal-mapping-template.json
 - Completed in 0.8s

> I've created a minimal, valid OSCAL mapping collection template at ./oscal-mapping-template.json. This template includes:

Required elements:
- uuid: Unique identifier for the mapping collection
- metadata: Document metadata with title, last-modified timestamp, version, and OSCAL version
- provenance: Mapping methodology information including method, matching rationale, status, and description
- mappings: Array containing at least one mapping with:
  - uuid: Mapping identifier
  - source-resource and target-resource: References to the catalogs being mapped
  - maps: Array with mapping entries showing relationships between controls

Key features:
- Uses placeholder UUIDs (replace with actual UUIDs in production)
- Maps a source control "ac-1" to target control "access-control-policy" with "equivalent" relationship
- Includes minimal required fields only
- Valid JSON structure conforming to OSCAL 1.2.0 schema

You can customize this template by:
- Replacing placeholder UUIDs with real ones
- Updating the resource URLs to point to actual catalogs
- Adding more mapping entries in the maps array
- Modifying control IDs and relationships as needed
 ▸ Time: 21s

Example 3: Discover open source OSCAL catalogs

> What are some open source OSCAL catalogs?

Running tool list_oscal_resources with the param (from mcp server: oscal)
 ⋮  {}
 - Completed in 0.51s

> Based on the OSCAL community resources, here are some notable open source OSCAL catalogs:

## Government/Official Catalogs

Australian Cyber Security Centre (ACSC)
- Information Security Manual (ISM) controls in OSCAL format
- Essential Eight Maturity Levels (ML1, ML2, ML3)
- Available at: https://www.cyber.gov.au/ism/oscal

CMS Acceptable Risk Safeguards (ARS)
- Tailored NIST SP 800-53 controls for Centers for Medicare and Medicaid Services
- Available at: https://github.com/CMSgov/ars-machine-readable

GovTech Singapore
- ICT&SS Policy catalog and profile for low-risk systems
- Available at: https://github.com/GovtechSG/tech-standards

## Industry/Standards Organizations

Center for Internet Security (CIS)
- CIS Critical Security Controls (formerly Top 18/20)
- Available at: https://github.com/CISecurity/CISControls_OSCAL/

Cloud Security Alliance (CSA)
- Cloud Controls Matrix v4 in OSCAL format
- Available at: https://cloudsecurityalliance.org/artifacts/ccm-machine-readable-bundle-json-yaml-oscal/

NIST SP 800-171 (Community)
- Maintained by Fathom5
- Available at: https://github.com/FATHOM5/oscal/tree/main/content/SP800-171/oscal-content

## Community Collections

CivicActions Component Definitions
- Cloud services, software, security and privacy controls
- Available at: https://github.com/CivicActions/oscal-component-definitions

RedHat OSCAL Content
- Component definitions: https://github.com/RedHatProductSecurity/oscal-component-definitions
- Custom profiles: https://github.com/RedHatProductSecurity/oscal-profiles

Brad Hards ISM Catalog
- Australian Government ISM controls (community version)
- Available at: https://github.com/bradh/ism-oscal

These catalogs provide ready-to-use OSCAL content for various compliance frameworks and can serve as templates or starting points for your own OSCAL implementations.
 ▸ Time: 15s

Installation

Follow these instructions to setup the MCP server for use with your preferred IDE, AI agent, chatbot, etc. The server is published as Python package on PyPI. The uvx command (shown below) automatically downloads the latest version of the server from PyPI on startup.

[!NOTE] To setup for development instead, see DEVELOPING.md

Prerequisites

Configuring IDEs and AI Tools

This server communicates via stdio (standard input/output) and can be integrated with various IDEs and agentic tools that support the Model Context Protocol. The configuration examples shown below are for your preferred IDE / chatbot / agent.

Configuration Format

Most MCP-compatible tools use a JSON configuration format described in the FastMCP documentation. Here's the basic structure:

{
  "mcpServers": {
    "oscal": {
      "command": "uvx",
      "args": ["--from", "mcp-server-for-oscal@latest", "server"],
      "env": {
      }
    }
  }
}

For typical, runtime use of the MCP server, additional configuration should not be required. If needed, runtime environment variables can be configured in the "env": {} object (shown above, empty) as described in the FastMCP documentation. See the file dotenv.example for available options.

[!Note] A dotenv file is only needed in a development environment.

Kiro Configuration

See Kiro's MCP documentation for additional options. Add to your .kiro/settings/mcp.json:

{
  "mcpServers": {
    "oscal": {
      "command": "uvx",
      "args": ["--from", "mcp-server-for-oscal@latest", "server"],
      "env": {},
      "disabled": false,
      "autoApprove": [
        "get_oscal_schema",
        "list_oscal_resources",
        "list_oscal_models",
        "query_oscal_documentation"
      ]
    }
  }
}

Claude Desktop

Add to your ~/.claude/claude_desktop_config.json:

{
  "mcpServers": {
    "oscal": {
      "command": "uvx",
      "args": ["--from", "mcp-server-for-oscal@latest", "server"]
    }
  }
}

VS Code

Run the MCP: Open User Configuration command, which opens the mcp.json file in your user profile. You can then manually add the server configuration to the file. See the VSCode/Copilot docs for addtional options and details.

{
  "servers": [
    "oscal": {
      "command": "uvx",
      "args": ["--from", "mcp-server-for-oscal@latest", "server"]
    }
  ]
}

Development

See DEVELOPING to get started.

Security

See CONTRIBUTING for more information.

License

This project is licensed under the Apache-2.0 License.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选