Prompyai runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm. Last commit 13 Mar 2026.
Scores your prompts against your real codebase — context-aware prompt intelligence
Today is the operative word: we check Prompyai 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 prompyai -- npx -y prompyai-mcp
{
"mcpServers": {
"prompyai": {
"command": "npx",
"args": [
"-y",
"prompyai-mcp"
]
}
}
}
[mcp_servers.prompyai]
command = "npx"
args = ["-y", "prompyai-mcp"]
{
"mcpServers": {
"prompyai": {
"command": "npx",
"args": [
"-y",
"prompyai-mcp"
]
}
}
}
{
"servers": {
"prompyai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prompyai-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ANTHROPIC_API_KEY (Anthropic API key for AI-powered suggestions (optional — free heuristic scoring works without it)).
Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent
Strapi codebase intelligence for AI agents (not content CRUD): real UIDs, schemas, refs, refactors.
Codex-native codebase intelligence context compiler and query-only MCP server.
Local-first codebase intelligence MCP server for AI coding agents.
Local-first codebase intelligence: cited answers, audits, reports. EN/FR.
Codebase intelligence MCP — index any repo into a property graph; 26 tools for agents.
Codebase intelligence MCP server — index any repo into a property graph; 26 tools for agents.
Answers built from our own checks of this server.