MCP Server for OSCAL
This MCP server gives AI assistants OSCAL expertise via local tools for schemas, models, content validation, and querying/searching OSCAL documents.
Learn about OSCAL: list model types with metadata (
list_oscal_models) and retrieve JSON or XSD schemas (get_oscal_schema).Discover community resources, tools, and example catalogs (
list_oscal_resources).Validate OSCAL JSON content or files through a multi-level pipeline (well-formedness, JSON Schema, Pydantic models, optional oscal-cli).
Explore Component Definitions hierarchically: list definitions, capabilities, and components, then query by UUID, title, or type.
Query and list every major OSCAL model type: catalogs, profiles, SSPs, assessment plans, assessment results, POA&Ms, and mapping collections.
Drill into child elements: catalog controls/groups, SSP control-implementations and system components, profile imports/modify, assessment plan tasks/activities, assessment results/ findings, POA&M items, and mapping collection mappings.
Full-text search across all indexed OSCAL documents with model-type scoping and pagination, resolving results via
get_child_element.Query OSCAL documentation via a local search or an optional Amazon Bedrock Knowledge Base, with paged passages and doc lookups.
Index your own OSCAL JSON (and Markdown docs) from a directory using
OSCAL_DOCUMENTS_DIR, optionally with a persistent SQLite store.Get server metadata (
about) and run everything locally over stdio with file-integrity verification by default.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Server for OSCAL generate a valid OSCAL catalog template"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server for OSCAL
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.
To get started, seeInstallation below.
Contents
Features: what the tools cover, local-only operation, and integrity checks
What is OSCAL? and What is MCP?: background
How to use / examples: sample sessions covering models, templates, catalogs, and AWS component definitions
Installation: one-click MCP Bundle (
.mcpb) for Claude Desktop, or the PyPI package with configuration for Kiro, Claude Desktop, and VS CodeUsing your own OSCAL Content:
OSCAL_DOCUMENTS_DIRand store settingsOSCAL Agent: the standalone Strands/Bedrock agent, sessions, and conversation management
Development, Security, Known limitations, Related projects, License
Related MCP server: nist-mcp
Features
Together, the tools provided by this MCP server are meant to enable your preferred AI assistant to provide accurate, authoritative guidance 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 lightweight 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 streamable-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 the bundled OSCAL schemas and the pre-built content database. Each time the server starts, both are verified against their manifests. A schema mismatch produces an error and prevents startup; a database mismatch causes the server to discard the bundled database and start with an empty one.
The tools cover OSCAL schemas and model metadata, Metaschema allowed-values, constraint, reference, and definition lookup plus source reading (get_allowed_values, get_constraints, find_references_to, get_definition, get_metaschema_source), multi-level content validation, Component Definition navigation, query/list/full-text search for every OSCAL model type (catalogs, profiles, SSPs, assessment plans and results, POA&Ms, mapping collections), community resources, and documentation. Search tools come in search/fetch pairs: text_search_oscal returns element IDs plus parentDocumentUuid that get_child_element resolves, and query_oscal_documentation returns paged {title, snippet} passages, with a docId on local pages that get_oscal_documentation reads as a line range. Results never include filesystem paths. See the tools README for the full list.
In addition to the MCP server, the package includes a standalone OSCAL agent built with Strands Agents. See the OSCAL Agent section below.
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: 8sExample 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: 15sExample 4: Query component definitions for information about AWS services
[OSCAL] > what components are available for Cognito?
Running tool list_components with the param (from mcp server: oscal-dev)
⋮ {}
- Completed in 0.49s
> There are 3 Cognito-related components available:
1. Cognito Identity - from "Cognito Identity Pools" component definition
2. Cognito Sync - from "Amazon Cognito Sync" component definition
3. Cognito Identity Provider - from "Amazon Cognito Identity User Pools" component definition
▸ Time: 7s
[OSCAL] > show me the names and IDs from all 3 components
Running tool query_component_definition with the param (from mcp server: oscal-dev)
⋮ {
⋮ "query_type": "by_uuid",
⋮ "query_value": "7fd5d354-6ec4-4f8e-8c5f-2904086bb597"
⋮ }
Running tool query_component_definition with the param (from mcp server: oscal-dev)
⋮ {
⋮ "query_type": "by_uuid",
⋮ "query_value": "a1d82e1d-3733-41f4-bc09-90ab47b9e82f"
⋮ }
Running tool query_component_definition with the param (from mcp server: oscal-dev)
⋮ {
⋮ "query_type": "by_uuid",
⋮ "query_value": "2519deaf-4612-4c70-aba2-d9080ae3c816"
⋮ }
- Completed in 0.13s
- Completed in 0.6s
- Completed in 0.6s
> 1. Cognito Sync
- Service ID: Cognito Sync
- API Endpoint Prefix: cognito-sync
- ARN Namespace: cognito-sync
2. Cognito Identity Provider
- Service ID: Cognito Identity Provider
- API Endpoint Prefix: cognito-idp
- ARN Namespace: cognito-idp
3. Cognito Identity
- Service ID: Cognito Identity
- API Endpoint Prefix: cognito-identity
- ARN Namespace: cognito-identity
▸ Time: 12s
[OSCAL] > show me everything in the EC2 component definition
Running tool query_component_definition with the param (from mcp server: oscal-dev)
⋮ {
⋮ "component_definition_filter": "Elastic Compute Cloud (EC2)",
⋮ "query_type": "all"
⋮ }
- Completed in 0.14s
> The EC2 component definition contains 1 component:
Component: EC2
- UUID: 66345eb9-7c0d-435c-b2b5-675fd977de80
- Type: service
- Description: Empty
Properties:
- Service ID: EC2
- Version: 2016-11-15
- Availability: REGIONAL and ZONAL
- Full Name: Elastic Compute Cloud (EC2)
- API Endpoint Prefix: ec2
- ARN Namespace: ec2
Regional Availability (34 regions):
Africa (Cape Town), Asia Pacific (Hong Kong, Tokyo, Seoul, Osaka, Mumbai, Hyderabad, Singapore, Sydney, Jakarta, Melbourne, Malaysia), Canada (Central, Calgary), China (Beijing, Ningxia),
Europe (Frankfurt, Zurich, Stockholm, Milan, Spain, Ireland, London, Paris), Israel (Tel Aviv), Middle East (UAE, Bahrain), South America (Sao Paulo), US East (N. Virginia, Ohio), AWS
GovCloud (US-East, US-West), US West (N. California, Oregon)
▸ Time: 10s
[OSCAL] > what's the ID of the Jakarta region?
> Based on the EC2 component data I just retrieved, the Jakarta region's resource fragment ID is:
8041109b-0a0b-46cc-bddb-91d703667637
This is the UUID for the "Asia Pacific (Jakarta)" region component.
▸ Time: 3s
[OSCAL] > get the region ID from that component
Running tool query_component_definition with the param (from mcp server: oscal-dev)
⋮ {
⋮ "query_type": "by_uuid",
⋮ "query_value": "8041109b-0a0b-46cc-bddb-91d703667637"
⋮ }
- Completed in 0.13s
> The region ID for Jakarta is: ap-southeast-3
▸ Time: 7s
[OSCAL] > /quitInstallation
Follow these instructions to setup the MCP server for use with your preferred IDE, AI agent, chatbot, etc. The server is distributed two ways:
MCP Bundle (
.mcpb): a single-file, one-click install for MCPB-compatible desktop apps such as Claude Desktop. Attached to every GitHub release. See MCP Bundle below.Python package on PyPI: works with any MCP client. The
uvxcommand (shown below) automatically downloads the latest version of the server from PyPI on startup.
To setup for development instead, seeDEVELOPING.md
MCP Bundle
An MCP Bundle packages the server, its manifest, and locked dependency versions into one file. The host app installs Python and the dependencies for you, so the prerequisites below don't apply.
Download
mcp-server-for-oscal-<version>.mcpbfrom the latest release.Open the file with your MCPB-compatible app. In Claude Desktop, double-click it or drag it onto Settings > Extensions, then click Install.
Optionally, configure the extension's settings. All are optional; the defaults run fully locally with the bundled content.
Setting | Environment variable | Description |
OSCAL documents directory |
| Directory of your own OSCAL JSON files to index alongside the bundled content. See Using your own OSCAL Content. |
Allow remote URIs |
| Allow tools to fetch OSCAL content from |
Bedrock Knowledge Base ID |
| Amazon Bedrock Knowledge Base for documentation queries. Leave empty to use the bundled local documentation search. |
AWS profile / AWS region |
| Credentials and region for Bedrock Knowledge Base queries. |
Log level |
|
|
Unlike the uvx configurations below, which fetch the latest PyPI release on startup, a bundle stays at the version you installed. To upgrade, download and install the .mcpb from a newer release.
Prerequisites
These apply to the PyPI package (every configuration below that uses uvx), not to the MCP Bundle.
uvpackage manager for Python (Installation instructions)Python 3.13 or higher (
uv python install 3.14). The server may work with later versions of Python, but we only test 3.13 & 3.14 for now.
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": ["mcp-server-for-oscal@latest"]
}
}
} For typical, runtime use of the MCP server, additional configuration should not be required. If needed, runtime environment variables can be configured in an "env": {} object 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": ["mcp-server-for-oscal@latest"],
"env": {},
"disabled": false,
"autoApprove": [
"*"
]
}
}
}Claude Desktop
The easiest way to install is with the MCP Bundle. Claude Desktop manages Python and dependencies for you, and lets you configure optional settings such as a directory of your own OSCAL documents.
Alternatively, open Settings > Developer > Edit Config in Claude Desktop and add the following to claude_desktop_config.json (located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"oscal": {
"command": "uvx",
"args": ["mcp-server-for-oscal@latest"]
}
}
}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 additional options and details.
{
"servers": {
"oscal": {
"command": "uvx",
"args": ["mcp-server-for-oscal@latest"]
}
}
}Using your own OSCAL Content
By default, the server ships with bundled OSCAL content (AWS component definitions, OSCAL documentation, and schemas). You can also point the server at a directory of your own OSCAL JSON files — catalogs, SSPs, profiles, assessment plans, assessment results, POA&Ms, or mapping collections. The server indexes them at startup and makes them available through all query and list tools.
Set the OSCAL_DOCUMENTS_DIR environment variable to the path of your OSCAL content directory. The path can be absolute or relative to the server's package directory. For example, in your MCP configuration:
{
"mcpServers": {
"oscal": {
"command": "uvx",
"args": ["mcp-server-for-oscal@latest"],
"env": {
"OSCAL_DOCUMENTS_DIR": "/path/to/your/oscal/files"
}
}
}
}The server scans the directory recursively for .json files and indexes any valid OSCAL documents it finds. Your content is merged with the bundled content — both are queryable in the same session. Markdown (.md) files in the directory are indexed as documentation: query_oscal_documentation searches them (also when a Bedrock Knowledge Base is configured), and get_oscal_documentation reads them by docId.
These environment variables control the OSCAL store behavior:
Variable | Default | Description |
| (empty) | Directory containing your OSCAL JSON files. Not scanned when empty. |
| (empty) | Path to a persistent SQLite database. When set, the index is reused across server restarts instead of being rebuilt each time. |
|
| Maximum number of parsed OSCAL documents to keep in the in-memory LRU cache. |
SettingOSCAL_STORE_DB_PATH is recommended if you have a large collection of OSCAL documents. The server only needs to index new or changed files on subsequent startups. A database created by an older server version is upgraded in place on first start.
OSCAL Agent
In addition to the MCP server, the package includes a standalone OSCAL agent built with Strands Agents. The agent uses the same tools as the MCP server and can be run directly:
# Via entry point
oscal-agent
# Or via module
python -m mcp_server_for_oscal.oscal_agentThe agent requires AWS Bedrock access and uses the same configuration environment variables as the MCP server.
Session Persistence
The agent supports session persistence so that conversation history and agent state survive across invocations. Choose between local filesystem or Amazon S3 storage:
# File-based session storage (new session)
oscal-agent --session-storage file
# Resume a previous session
oscal-agent --session-storage file --session-id <your-session-id>
# S3-based session storage
oscal-agent --session-storage s3 --session-s3-bucket my-bucketWhen session storage is enabled without a --session-id, a UUID is auto-generated and displayed so you can resume later. Session defaults can also be set via environment variables (see DEVELOPING.md).
Conversation Management
For long-running workflows, you can select a conversation manager to control how the agent's context window is maintained:
# Summarize older messages to keep context manageable
oscal-agent --session-storage file --conversation-manager summarizing
# Sliding window (SDK default behavior)
oscal-agent --conversation-manager sliding-window
# No conversation management
oscal-agent --conversation-manager nullExisting 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.
Development
See DEVELOPING to get started.
Security
See CONTRIBUTING for more information.
Known limitations
It's not yet possible to use this MCP server with ChatGPT due to limited MCP support by ChatGPT.
The
streamable-httptransport does not yet implement authentication or transport security. Usestdiofor production workloads.
Related projects
Experimental Component Definitions for AWS services are bundled with this MCP server. You can find that content in the AWS Labs project OSCAL Content for AWS Services.
MCP Server for OSCAL uses oscal-bindings for its typed OSCAL models, including model-level content validation.
License
This project is licensed under the Apache-2.0 License.
Available Tools
46 toolsaboutA
Return server metadata: package version, keywords, bundled OSCAL version, and the number of documents loaded from OSCAL_DOCUMENTS_DIR.
Inputs: no named parameters.
find_references_toA
Find the fields, flags, props, and links that OSCAL Metaschema index-has-key
constraints require to reference an assembly by key (UUID or ID), with the matching
index, source file and line for both, and cross-document. Use when you need what must
point to a component, party, location, or resource, including prop and link references a
search for UUID fields misses. Results are paged within a response budget.
Inputs: assembly (required), limit, model, offset.
get_allowed_valuesA
Return the values OSCAL Metaschema allowed-values constraints permit at a target, with
allow-other, namespace and conditions for predicates, and source file and line. Use
when the JSON schema does not list the values; use get_constraints for other constraint
types. Results are paged within a response budget, and an empty page lists
suggested-targets.
Inputs: model (required), target (required), limit, offset.
get_capabilityA
Get one Capability by UUID as OSCAL JSON, or null when no Capability has that UUID. Use when working with Component Definitions that contain capabilities.
Inputs: uuid (required). Returns: result
get_child_elementA
Get one child element by UUID or token ID, with its OSCAL JSON in raw_json. If the
result is an ambiguous_element_id error, retry with parent_doc_uuid.
Inputs: element_id (required), parent_doc_uuid. Returns: result
get_constraintsA
List the OSCAL Metaschema constraints at a target (allowed-values, matches, index,
index-has-key, is-unique, has-cardinality, expect) with type-specific details and
source file and line; a bare definition name returns every constraint declared on it and
its local definitions. Use when you need rules the JSON schema does not express; use
get_allowed_values for the values themselves. Results are paged within a response
budget.
Inputs: model (required), target (required), limit, offset, +1 more.
get_definitionA
Return every OSCAL Metaschema definition with a given name, with formal name,
description, remarks, flags, model children, constraint summaries, and source file and
line. Use when you need documentation or structure that the generated JSON and XML schemas
shorten or drop. Results are paged within a response budget, and long remarks are marked
truncated.
Inputs: name (required), kind, limit, model, +1 more.
get_metaschema_sourceA
Read a line range of a bundled OSCAL Metaschema source file verbatim, or list the files
with line counts when file is omitted. Use when checking a source-file and line from
get_definition, get_allowed_values, get_constraints, or find_references_to. A response may
hold fewer lines to fit the response budget; continue from end-line + 1 while
has-more is true.
Inputs: file, line_count, start_line.
get_oscal_documentationA
Read an OSCAL documentation page by docId as a verbatim line range. Use when a
query_oscal_documentation snippet is not enough. A response may hold fewer lines to fit
the response budget; continue from end-line + 1 while has-more is true.
Inputs: doc_id (required), line_count, start_line.
get_oscal_schemaA
Return the JSON schema or XML Schema (XSD) of one OSCAL model as text.
Use when you need the structure of an OSCAL model: its properties, types, and required fields.
Inputs: model_name (required), schema_type. Returns: result
list_assessment_plan_activitiesA
List activities in loaded OSCAL Assessment Plans with UUID, title, and parent document. Get an activity's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_assessment_plansA
List loaded OSCAL Assessment Plans with UUID, title, child count, and size. Use when
picking a query_value for query_assessment_plan. Results are paged.
Inputs: limit, offset.
list_assessment_plan_tasksA
List tasks in loaded OSCAL Assessment Plans with UUID, title, and parent document. Get a task's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_assessment_resultsA
List loaded OSCAL Assessment Results with UUID, title, child count, and size. Use when
picking a query_value for query_assessment_results. Results are paged.
Inputs: limit, offset.
list_assessment_results_findingsA
List findings in loaded OSCAL Assessment Results with UUID, title, and parent document. Get a finding's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_assessment_results_resultsA
List results in loaded OSCAL Assessment Results with UUID, title, and parent document. Get a result's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_capabilitiesA
List loaded Capabilities with UUID, name, and parent Component Definition. Use when working with Component Definitions that contain capabilities; the list is empty when none do. Results are paged.
Inputs: limit, offset.
list_catalog_controlsA
List controls in loaded OSCAL Catalogs with token ID (e.g. ac-1), title, and parent document. Get a control's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_catalog_groupsB
List control groups (families) in loaded OSCAL Catalogs with token ID, title, and parent document. Get a group's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_catalogsA
List loaded OSCAL Catalogs with UUID, title, child count, and size. Use when picking a
query_value for query_catalog. Results are paged.
Inputs: limit, offset.
list_component_definitionsA
List loaded Component Definitions with UUID, title, component count, and size. Use when
picking a component_definition_filter for query_component_definition. Results are paged.
Inputs: limit, offset.
list_componentsA
List loaded Components with UUID, title, and parent Component Definition. Use when
picking a query_value for query_component_definition. Results are paged.
Inputs: limit, offset.
list_mapping_collection_mappingsA
List mappings in loaded OSCAL Mapping Collections with UUID, title, and parent document. Get a mapping's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_mapping_collectionsA
List loaded OSCAL Mapping Collections with UUID, title, child count, and size. Use when
picking a query_value for query_mapping_collection. Results are paged.
Inputs: limit, offset.
list_oscal_modelsA
List the OSCAL model names, each with description, layer, formal and short names, and release status.
Use when you need a valid model_name for get_oscal_schema or a model for the Metaschema
tools.
Inputs: no named parameters.
list_oscal_resourcesA
List OSCAL community resources (tools, content, articles, talks) from the awesome-oscal
list, each with category and markdown text. Results are paged.
Inputs: limit, offset.
list_poam_itemsA
List POA&M items in loaded OSCAL POA&Ms with ID, title, and parent document. Get an item's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_poamsA
List loaded OSCAL Plans of Action and Milestones with UUID, title, child count, and size.
Use when picking a query_value for query_poam. Results are paged.
Inputs: limit, offset.
list_profile_importsA
List imports in loaded OSCAL Profiles, with positional IDs (import-0, import-1). Get an import's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_profile_modifyB
List the modify element (control tailoring) of loaded OSCAL Profiles, one per profile. Get its OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_profilesA
List loaded OSCAL Profiles with UUID, title, child count, and size. Use when picking a
query_value for query_profile. Results are paged.
Inputs: limit, offset.
list_ssp_control_implementationsA
List the control-implementation element of loaded OSCAL SSPs, one per SSP. Get its OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
list_sspsA
List loaded OSCAL System Security Plans with UUID, title, child count, and size. Use when
picking a query_value for query_ssp. Results are paged.
Inputs: limit, offset.
list_ssp_system_componentsA
List system components in loaded OSCAL SSPs with UUID, title, and parent document. Get a component's OSCAL JSON with get_child_element. Results are paged.
Inputs: limit, offset, parent_doc_uuid.
query_assessment_planA
Return loaded OSCAL Assessment Plans with childTypeCounts. For child elements, use list_assessment_plan_tasks or list_assessment_plan_activities, then
get_child_element.
Inputs: limit, offset, query_type, query_value.
query_assessment_resultsA
Return loaded OSCAL Assessment Results with childTypeCounts. For child elements, use list_assessment_results_results or list_assessment_results_findings, then
get_child_element.
Inputs: limit, offset, query_type, query_value.
query_catalogA
Return loaded OSCAL Catalogs with metadata and childTypeCounts. For controls and groups,
use list_catalog_controls or list_catalog_groups, then get_child_element.
Inputs: limit, offset, query_type, query_value.
query_component_definitionA
Return OSCAL Components from loaded Component Definitions as OSCAL JSON, or one Capability when a by_uuid or by_title query matches a Capability. Use when you need component details: call it directly with by_title or by_type when you know the name or type, else find UUIDs and titles first with list_components; use list_capabilities or get_capability only for Component Definitions that contain capabilities. Results are paged.
Inputs: limit, offset, query_type, query_value, +2 more. Returns: object
query_mapping_collectionB
Return loaded OSCAL Mapping Collections with metadata and childTypeCounts. For
mappings, use list_mapping_collection_mappings, then get_child_element.
Inputs: limit, offset, query_type, query_value.
query_oscal_documentationA
Search OSCAL documentation (Knowledge Base if configured, plus local docs) and return
paged passages. Use when a schema lacks the answer; for a model property try
get_oscal_schema. Pass a hit's docId to get_oscal_documentation for the full page.
Inputs: query (required), limit, offset.
query_poamA
Return loaded OSCAL Plans of Action and Milestones with metadata and childTypeCounts.
For POA&M items, use list_poam_items, then get_child_element.
Inputs: limit, offset, query_type, query_value.
query_profileA
Return loaded OSCAL Profiles with metadata and childTypeCounts. For child elements, use
list_profile_imports or list_profile_modify, then get_child_element.
Inputs: limit, offset, query_type, query_value.
query_sspA
Return loaded OSCAL SSPs with metadata and childTypeCounts. For child elements, use
list_ssp_control_implementations or list_ssp_system_components, then get_child_element.
Inputs: limit, offset, query_type, query_value.
text_search_oscalA
Search loaded OSCAL documents and child elements, including control prose, ranked by
relevance. Pass a child hit's entity ID and parentDocumentUuid to get_child_element.
Inputs: query_text (required), limit, offset, oscal_model_type.
validate_oscal_contentA
Validate OSCAL JSON text and return per-level results for JSON syntax, JSON Schema, the OSCAL model, and oscal-cli (skipped when not installed). Later levels are skipped when the JSON does not parse.
Inputs: content (required), model_type.
validate_oscal_fileA
Validate an OSCAL JSON file and return per-level results for JSON syntax, JSON Schema, the OSCAL model, and oscal-cli (skipped when not installed). Use when the document is in a file; for JSON text use validate_oscal_content.
Inputs: file_uri (required), model_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 46 tools
Tools generally follow clear model/action families, and descriptions explain the intended list-for-selection vs query-for-details workflow. A few parallel names such as list_catalogs/query_catalog and list_component_definitions/list_components could still invite misselection, but they are mostly distinguishable.
Most names are snake_case and verb-first, but the surface mixes list_, query_, get_, and search_ patterns with some singular/plural mismatches like list_poams vs query_poam. Awkward names like list_assessment_results_results and the unverbed about reduce predictability.
46 tools is heavy for an MCP server and creates a large selection surface. Although OSCAL is broad, many list/query/child tools could be consolidated through generic document and child-retrieval interfaces.
The server covers major OSCAL models, child-element navigation, schema and constraint inspection, validation, documentation search, and resource listing. Minor gaps remain around XML validation and write/update operations, but the read-oriented surface is largely complete.
Maintenance
Related MCP Connectors
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Compliance frameworks (SOC 2, ISO 27001, CMMC, NIST, more) delivered to AI agents as MCP tools.
Related MCP Servers
- AlicenseAqualityFmaintenanceProvides 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.4052Apache 2.0
- AlicenseAqualityDmaintenanceProvides structured access to the full NIST cybersecurity catalog, including SP 800/1800 publications, security controls, CSF 2.0, and the NVD database. It enables AI assistants to search and retrieve cybersecurity standards, CVEs, and compliance guidance directly from a local SQLite index.201MIT
- AlicenseNot gradedqualityDmaintenanceProvides comprehensive access to NIST cybersecurity frameworks and controls, enabling AI assistants and applications to query, analyze, and manage NIST security controls through a standardized interface.10MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants and IDEs to work with the AGNTCY Agent Directory, providing tools for validating, publishing, searching agent records, and navigating OASF taxonomies.4Apache 2.0