PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.
Connect Remote server
claude mcp add --transport http pqs-mcp-server https://promptqualityscore.com/api/mcp
{
"mcpServers": {
"pqs-mcp-server": {
"url": "https://promptqualityscore.com/api/mcp"
}
}
}
{
"servers": {
"pqs-mcp-server": {
"type": "http",
"url": "https://promptqualityscore.com/api/mcp"
}
}
}
Settings > Connectors > Add custom connector
URL: https://promptqualityscore.com/api/mcp
Tools 2 found in our last check
score_promptScore a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension.…
optimize_promptRewrite a prompt to score higher on the PQS rubric, AND show before/after output comparisons so the user can see the impact. Returns the optimized prompt, the original PQS score, the optimized PQS score, and side-by-side sample outputs from a frontier model using both versions.…
Details
| Endpoint | https://promptqualityscore.com/api/mcp (Streamable HTTP) |
| Package | [email protected] (NPM, stdio) |
| First published | 27 May 2026 |
| Last updated | 27 May 2026 |
| Registry name | io.github.OnChainAIIntel/pqs-mcp-server |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
