
Promptlint MCP
Lints AI prompts like a code quality tool. Exposes a single MCP resource that analyzes system prompts, agent instructions, and tool descriptions for contradictions (like "be concise" paired with "be thorough"), redundant sentences, ambiguous pronouns, oversized code examples, and politeness fluff that wastes tokens. Returns a scored report with line numbers and actionable suggestions. Also includes a CLI mode with JSON output and a trim flag that strips fluff while preserving fenced code blocks and quoted strings. Useful when you're iterating on complex system prompts and want to catch silent breaking issues before they burn tokens on every request. Runs purely static analysis, no LLM calls.
- GitHub stars
- 1
- tools
- 2
- transport
- STDIO
- last updated
- Apr 25, 2026
Tools
2 toolsPublic tool metadata for what this MCP can expose to an agent.
lint_promptLints a prompt and returns a human one-line summary plus the full JSON lint result.
Lints a prompt and returns a human one-line summary plus the full JSON lint result.
No parameter schema in public metadata yet.
trim_promptReturns the trimmed prompt with a savings footer; does not resolve contradictions, redundancy, or ambiguity.
Returns the trimmed prompt with a savings footer; does not resolve contradictions, redundancy, or ambiguity.
No parameter schema in public metadata yet.
Sponsors
Readme
promptlint-mcp
Lint AI prompts like code. Save tokens. Catch contradictions.
A static analyzer for AI prompts — system prompts, agent instructions, tool descriptions — that runs as a CLI and as an MCP server so Claude Code (or any MCP-aware agent) can lint prompts before sending them.
Quick demo
Run promptlint on a typical (silently broken) system prompt:
Details
- Repository
- github.com/sean-sunagaku/promptlint-mcp
- Category
- Developer Tools
- Package
promptlint-mcp- Transport
- STDIO
- Registry
- MCP registry, active