Enterprise DNAEnterprise DNA
MMCP ServersDeveloperlow

calllint/calllint

by Various

Pre-flight risk linting for MCP and agent tools — check the blast radius before your agent runs them.

MCP

calllint/calllint

Added 3 Sept 2026

#ai-agents#ai-security#cli#llm#mcp#mcp-server#prompt-injection#security
Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

Calllint is a pre-flight risk linter for MCP and agent tools. It analyzes tools before execution to check their potential blast radius. It helps developers understand and mitigate dangerous operations early.

Best for

Best for
Developers building or deploying MCP servers and agent tools who want an early warning layer before executing tool calls.

Use cases

  • Audit MCP tool permissions before allowing an agent to run them
  • Identify destructive or high-risk operations in agent toolchains
  • Add pre-flight tool checks to CI pipelines for agent projects

How to use

Install

npx calllint scan .cursor/mcp.json

Clients listed in this record (not verified here)

Claude Desktop, Claude Code, Cursor, Windsurf, VS Code

Notes

2 stars on GitHub. Last updated 2026-09-01. Licensed Apache-2.0.

Pros

  • Small and focused on a specific safety gap
  • Written in TypeScript, fitting common agent and MCP stacks
  • Catch risky calls before they execute

Cons

  • Very early project with only 2 stars, little community validation
  • Limited scope, only covers MCP and agent tools
  • Lacks evidence of production readiness or long-term maintenance
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.