KarmaDue
Provides pre-install checks for npm packages: agents can call check_install with ecosystem "npm" (or the karmadue-guard shim can intercept npm/npx installs) to get a verdict on a target package—a known trap with tested fix steps (fix_first), a warn, a deny for a malicious-package report, no_known_issues, or unknown—along with dated test records and supporting fix recipes.
Provides pre-install checks for pnpm installs via the karmadue-guard shell shim, which wraps pnpm so that a package is evaluated against known install traps and malicious-package reports before it is installed, returning tested fix steps or a warn/deny/no_known_issues/unknown verdict.
Provides pre-install checks for yarn installs via the karmadue-guard shell shim, which wraps yarn so that a package is evaluated against known install traps and malicious-package reports before it is installed, returning tested fix steps or a warn/deny/no_known_issues/unknown verdict.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
KarmaDue
A pre-install check for AI agents. Before your agent runs npm install, pip install, uv add, npx/uvx, or adds an MCP server, it calls check_install and gets one answer: a known trap with tested fix steps (fix_first), a warn, a deny for a malicious-package report, no_known_issues, or unknown (no evidence; not safety clearance).
Read-only. Nothing runs your command.
No account or key for reads. Anonymous limit: 30 requests/hour per IP.
Every fix cites a dated test record. Seed records are labeled "Founder-operated assessment, not independent".
Honest limits: lockfile installs (
npm ci,pip install -r) and transitive dependencies are not covered.
Try it (no account)
curl -s -X POST https://ogogoizwsfaduzehkshb.supabase.co/functions/v1/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_install","arguments":{"target":"tailwindcss@4","ecosystem":"npm","runtime_env":"node 20 linux"}}}'Related MCP server: package-truth
MCP server
Endpoint (Streamable HTTP) | Auth | Tools |
| none for reads |
|
| OAuth 2.1 (Claude, ChatGPT) | same, plus |
| OAuth 2.1 mirror (strict clients) | same as connector |
Claude Code: claude mcp add --transport http karmadue https://karmadue--mcp.expo.app/mcp
What is in this repository
Path | What |
| |
Claude Code PreToolUse hook ( | |
The agent docs as published at https://karmadue.expo.app/docs/ (quick start, tools, permissions, security, changelog) | |
The published seed records (tested install traps and fixes), snapshot of https://karmadue.expo.app/docs/seed-records.json |
The server and database are hosted and are not part of this repository.
Links
Quick start: https://karmadue.expo.app/docs/mcp.md
Official MCP Registry name:
io.github.ashadow07/karmadue
License
MIT, see LICENSE. Seed records describe third-party packages and are provided as dated observations, not guarantees.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Package verdicts for AI coding agents: check npm, PyPI, Go and NuGet installs before they run.
Check before your agent installs, connects or pays. install_check: before installing an npm or PyPI package, a GitHub repo, a skill, an editor extension or an MCP server, it answers allow / hold / block (known malicious packages from OSV, typosquats of official MCP servers, names that do not exist, install scripts, maintainer changes). check_repo_config: before opening a repository someone sent you, it reads its agent configuration (MCP servers, hooks, editor tasks, instruction files) and runs nothing. check_service and verify_tools: live status of any MCP server or x402 endpoint, real price and payTo vs the catalogue listing, OFAC and stablecoin-freeze screening, tool-set changes, an open Trust Score. find_service finds working services. preflight_payment decides allow / hold / block right before an x402 payment is signed; payment_status prevents paying twice; report_purchase records what a paid call delivered. Verdicts are signed into a public transparency log. Free, no account. Every other tool (evidence packs, agent identities, boards, mail) is at https://alalanet.com/mcp/full; install and MCP-server checks alone are at https://alalanet.com/mcp/guard. Claude Code plugin: alalanet-guard.
Free MCP security tools for AI coding agents. Check npm/PyPI package versions, identify known OSV vulnerabilities, compare with the latest releases, and review up to 3 dependencies before deployment.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP-compatible AI applications to perform read-only npm package and project dependency safety scans, returning proceed, caution, or block verdicts without executing package code.64 npmMIT
- AlicenseAqualityBmaintenanceEnables checking packages across npm, PyPI, Go, Maven, Cargo, NuGet, and RubyGems for existence, deprecation, known vulnerabilities, and license issues before installation, providing verdicts like does_not_exist, risky, verify, or ok.31MIT
- AlicenseNot gradedqualityBmaintenanceLets a coding agent check a dependency or lockfile before adding it, tracing the exact chain by which a compromised package, maintainer account, or unpinned MCP server could reach the project. It answers supply-chain questions against a FalkorDB graph of npm, PyPI, and AI-tool MCP configs, showing the queries and evidence behind each result.MIT
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to check npm packages, GitHub Action refs, and remote scripts before execution, returning deterministic ALLOW/DENY/REVIEW verdicts with evidence and a re-checkable manifest.MIT