Cedar For AgentsBLOCK
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
This repository contains the source code for software at the intersection of cedar and Agents.
Table of Contents
This repository contains a number of directories:
- rust which contains the source code for a number of Rust crates that provide functionality to secure Agentic workflows using Cedar as well bindings in WebAssembly and Python:
- mcp-tools-sdk : A crate for parsing and manipulating MCP tool descriptions and data.
- cedar-policy-mcp-schema-generator : A crate for auto-generating a Cedar Schema for an MCP Server's tool descriptions.
- cedar-policy-mcp-schema-generator-wasm : WebAssembly bindings for generating Cedar schemas and authorization requests from MCP tool descriptions in JavaScript and TypeScript environments, published as (`@cedar-policy/mcp-schema-generator-wasm)[https://www.npmjs.com/package/@cedar-policy/mcp-schema-generator-wasm] on NPM.
- cedar-policy-mcp-schema-generator-python : PyO3/maturin wrapper of the
cedar-policy-mcp-schema-generator, published as (cedar-policy-mcp-schema-generator)[https://pypi.org/project/cedar-policy-mcp-schema-generator/] on PyPI. - js which contains JavaScript packages that enable Agents to make use of Cedar and its Analysis Capabilities.
- cedar-analysis-mcp-server : A package that creates an MCP server that exposes an interface for Agents to use Cedar's analysis capabilities.
Security
See SECURITY for more information.
Contributing
We welcome contributions from the community.
640965b8ef16OBSERVED · 2026-10-12Connect
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.
claude mcp add wasm-integration-tests -- npx -y wasm-integration-tests
{
"mcpServers": {
"wasm-integration-tests": {
"command": "npx",
"args": [
"-y",
"wasm-integration-tests"
]
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze-policies | read | Analyze Cedar policies against a schema to validate policy structure and identify potential issues. |
compare-policy-sets | read | Compare two Cedar policy sets to verify that policy changes maintain intended authorization behavior. This tool identifies if changes make policies more or less permissive, helping developers ensure security is maintained when updating policies. |
read_file | read | Read a file from disk |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
pub fn exec(&self) -> Result<(), CliError> {import { generateSchema, generateRequest } from "../../pkg/cedar_policy_mcp_schema_generator_wasm.js";const pkg = JSON.parse(readFileSync(new URL("../../pkg/package.json", import.meta.url), "utf8"));node-fetch, zod, zod-to-json-schema, @types/fs-extra, @types/node, @types/node-fetch, ts-node, typescript
Most of the process (opening PRs, bumping versions, updating changelogs) only requires standard write access. A few key steps require elevated permissions:
Gates applied: no_behavioural_pass.
640965b8ef16full audit observations/trust-audit/mcp-server/cedar-policy__cedar-for-agents.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 |
|---|---|---|---|---|---|
| 2026-10-12 | 640965b8ef16 | BLOCK | D | 69 | first audit |
Questions
What tools does @cedar-policy/mcp-schema-generator-wasm expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @cedar-policy/mcp-schema-generator-wasm safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does @cedar-policy/mcp-schema-generator-wasm need?
No credential environment variables were found in its source, so it appears to need none.
How does @cedar-policy/mcp-schema-generator-wasm run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as wasm-integration-tests.
How current is this page?
The grade is for one exact copy of the source (640965b8ef16), read on 2026-10-12. The repository is watched and re-audited when it changes.