Promptlint MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 53 installs a week from npm. Last commit 25 Apr 2026.
Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.
Today is the operative word: we check Promptlint MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add promptlint-mcp -- npx -y promptlint-mcp
{
"mcpServers": {
"promptlint-mcp": {
"command": "npx",
"args": [
"-y",
"promptlint-mcp"
]
}
}
}
[mcp_servers.promptlint-mcp]
command = "npx"
args = ["-y", "promptlint-mcp"]
{
"mcpServers": {
"promptlint-mcp": {
"command": "npx",
"args": [
"-y",
"promptlint-mcp"
]
}
}
}
{
"servers": {
"promptlint-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"promptlint-mcp"
]
}
}
}
Deterministic MCP for statistical classifications and survey codelists with provenance.
Static dataflow analysis, program slicing, linting, and dependency extraction for R code.
MCP server for Solhint — lint and autofix Solidity smart contracts from any MCP client
AI visibility analytics for brands across citations, prompts, competitors, research, and reports.
Research-backed lint + generation for agent context files (CLAUDE.md, AGENTS.md) + prompt enhancer.
Zero-cost MCP server for local code inspection and best-practice recommendations
Lint MCP tool schemas for client compatibility and agent recovery.
Acting direction for AI video and voice: state-based behaviour kits and a free prompt linter.
Answers built from our own checks of this server.