# Calllint

> Evidence-backed security verdicts for MCP servers and agent tools. Lint agent tool-call risk before tools run — SAFE / REVIEW / BLOCK / UNKNOWN, with evidence. Never executes the server it judges.

## Facts
- Page: https://tashan.sh/capability/pkg-calllint
- tashan id: pkg:calllint
- Source: https://github.com/calllint/calllint
- npm: https://www.npmjs.com/package/calllint
- Type: npm
- Category: security
- tashan score: 52.0 / 100
- Adoption: 24.0
- Upkeep: 70.0
- Freshness: 92.0
- Evidence coverage: 100% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- npm downloads: 53/week
- Official: no

## Install

```sh
claude mcp add calllint -- npx -y calllint
```

## Security audit
- Known advisories: 0
- Install-time script: none declared
- Build provenance: attested

Permissions are read from DECLARED dependencies only. Nothing is executed, so an empty result means "nothing declared", never "nothing possible".

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.