Prompyai runs on your own machine — the client starts it, so there is no endpoint to ping. 33 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": {
"args": [
"-y",
"prompyai-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.prompyai]
command = "npx"
args = ["-y", "prompyai-mcp"]
{
"mcpServers": {
"prompyai": {
"args": [
"-y",
"prompyai-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"prompyai": {
"args": [
"-y",
"prompyai-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ANTHROPIC_API_KEY (Anthropic API key for AI-powered suggestions (optional — free heuristic scoring works without it)).
The author declared them in the registry entry; get the values from the project itself.
Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
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.
Index your codebase. AI searches instead of re-reading files. 94% token savings.
UK area & property intelligence for AI agents: reports, EPC, comparables, with source provenance.
Answers built from our own checks of this server.