aris
Provides a GitHub Action that audits pull request dependencies against Aris and fails when a vulnerable dependency is introduced.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
aris-kg
Coding agents answer from training data that stops months before you use them. aris-kg connects
them to the Aris knowledge graph instead: more than 15 million concepts, refreshed daily from NVD,
OSV, GitHub security advisories, MITRE ATT&CK, OWASP and framework releases.
It comes three ways:
An MCP server for Claude Code, Cursor, Codex, Windsurf and any other MCP client.
A CLI that checks every pinned version in your lockfiles against known CVEs.
A GitHub Action that fails a pull request when it adds a vulnerable dependency.
The code is open source (MIT). The graph is a paid API: you need a key from youraris.com/account, and each call is billed to your Aris credits.
Call | Price |
CVE, knowledge or code search | 1¢ |
Dependency check | 1¢ per package |
Web search | 2¢ |
Every account is limited to 120 calls a minute.
MCP server
The server gives your agent five tools, and tells it to use them without being asked: before adding a dependency, for any CVE, when picking a library version, and before writing auth, crypto, SQL or file-path code.
Tool | What it does |
| Checks exact package versions: CVE ids, severity, CVSS, affected and fixed versions, and whether a CVE is exploited in the wild |
| Finds CVEs and GitHub advisories by id or description |
| Current major versions and setup patterns, attack techniques, mitigations and known pitfalls |
| Reference code from published packages |
| Anything newer than the graph, with source URLs |
Claude Code
claude mcp add aris -e ARIS_API_KEY=your-key -- npx -y aris-kg mcpCursor, Windsurf and other JSON-configured clients
{
"mcpServers": {
"aris": {
"command": "npx",
"args": ["-y", "aris-kg", "mcp"],
"env": { "ARIS_API_KEY": "your-key" }
}
}
}Codex
In ~/.codex/config.toml:
[mcp_servers.aris]
command = "npx"
args = ["-y", "aris-kg", "mcp"]
env = { ARIS_API_KEY = "your-key" }Related MCP server: agentseed
CLI
export ARIS_API_KEY=your-key
npx aris-kg audit # lockfiles in the current folder
npx aris-kg audit ./service --fail-on critical
npx aris-kg audit --json > report.json
npx aris-kg search cve CVE-2024-3094audit reads package-lock.json, pnpm-lock.yaml, yarn.lock, poetry.lock, requirements.txt
(pinned == lines), Cargo.lock and go.mod. It only checks exact versions, so use a lockfile
rather than a manifest with ranges.
It exits with 1 when a vulnerability is at or above --fail-on (default high), or is exploited in
the wild at any severity. --fail-on none never fails. Errors exit with 2.
GitHub Action
name: Dependency audit
on: [pull_request]
jobs:
aris:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: kennysarnoski-jarvis/aris-kg@v0
with:
api-key: ${{ secrets.ARIS_API_KEY }}
fail-on: highAs a library
import { ArisClient } from "aris-kg";
const aris = new ArisClient({ apiKey: process.env.ARIS_API_KEY! });
const report = await aris.checkDependencies([{ name: "lodash", version: "4.17.20", ecosystem: "npm" }]);Development
npm install
npm test
npm run build
node dist/bin.js --helpSet ARIS_BASE_URL to point the client at another server.
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Security tools for coding agents: dependency advisory audits and evidence for remediation.
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Codebase intelligence for agents: 152 structured artifacts across 21 programs, one call.
Lets coding agents check their own code for leaked secrets, risky dependencies and AI-code mistakes
Related MCP Servers
- AlicenseAqualityBmaintenanceVulnerability intelligence for AI agents that enables CVE lookup, package vulnerability checks, and dependency auditing without API keys.5MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding agents to enforce spec-driven development and verify code before it is marked done, using six tools that catch invented APIs, scan for hallucinated content, check plugin conformance, sandbox-run tests, validate schemas, and record audit evidence.771 npm8PolyForm Noncommercial 1.0.0
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to retrieve maintainer-written release notes and compare installed versus target dependency versions, search packages, and report on projects pushed to a dashboard.MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to list functions, scan for risky patterns offline, and generate plain-language explanations of Python, JavaScript, and TypeScript code, including summaries for only the functions affected by recent changes.6 npmMIT