OSCAL ToolsCAUTION
OSCAL tools for AI agents
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[![PyPI][pypi-badge]][pypi-url] [][pypi-url] [%22&replace=%241&label=OSCAL)][nist-oscal-url]
[pypi-badge]: https://img.shields.io/pypi/v/mcp-server-for-oscal.svg [pypi-url]: https://pypi.org/project/mcp-server-for-oscal/ [nist-oscal-url]: https://pages.nist.gov/OSCAL/ [mcp-spec-url]: https://modelcontextprotocol.io/docs/getting-started/intro [issues-url]: https://github.com/awslabs/mcp-server-for-oscal/issues/ [new-issue-url]: https://github.com/awslabs/mcp-server-for-oscal/issues/new
Instant OSCAL expertise for your favorite AI agent
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 t
28a1cb527d65OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-for-oscal -- None mcp-server-for-oscal==0.0.0
Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
about | read | return { |
Trust audit
CAUTIONgrade C · trust 78/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (15)
aws-oscal-content-v0.2.0.zip
mod = importlib.import_module(module_name)
mod = importlib.import_module(module_name)
mod = importlib.import_module(module_path)
.config.kiro
.config.kiro
.config.kiro
.config.kiro
.config.kiro
This design covers the refactoring of the `oscal_agent.py` module from an unused prototype into a production-ready Strands agent, along with centralizing the tool registry so both the MCP server and t
These are read from environment variables in `__init__` following the existing pattern:
1. THE Config class SHALL read an `OSCAL_AGENT_SESSION_STORAGE` environment variable with allowed values `file`, `s3`, or empty string.
2. THE Config class SHALL read an `OSCAL_AGENT_SESSION_DIR` environment variable for the File_Session_Manager directory path.
3. THE Config class SHALL read an `OSCAL_AGENT_SESSION_S3_BUCKET` environment variable for the S3_Session_Manager bucket name.
4. THE Config class SHALL read an `OSCAL_AGENT_SESSION_S3_PREFIX` environment variable for the S3_Session_Manager key prefix.
Gates applied: no_behavioural_pass.
28a1cb527d65full audit observations/trust-audit/mcp-server/awslabs__oscal-tools.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 28a1cb527d65 | CAUTION | C | 78 | first audit |
Questions
What is the OSCAL Tools MCP server?
OSCAL tools for AI agents
What tools does OSCAL Tools expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OSCAL Tools safe to connect to an agent?
With care. The audit graded it C (78/100) and found 15 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does OSCAL Tools need?
It reads OSCAL_AGENT_MAX_TOKENS from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does OSCAL Tools run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as mcp-server-for-oscal.
How current is this page?
The grade is for one exact copy of the source (28a1cb527d65), read on 2026-10-08. The repository is watched and re-audited when it changes.