mcpcost

io.github.OnChainAIIntel/pqs-mcp-server

pqs-mcp-server

PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.

alive probed 2026-10-05 · HTTP 200

2tools
1.4ktokens in Claude Opus 5.5
1.4ktokens in Claude Code
0.7 %of a 200k context window
825o200k_base estimate
1.6 sto initialize
133 msto list tools
Endpoint
https://promptqualityscore.com/api/mcp (streamable-http)
Host
promptqualityscore.com
Protocol
2024-11-05
Reports itself as
pqs-mcp-server 1.4.0
Capabilities
tools
Instructions
none
Claude count
Claude Opus 5.5, measured 2026-10-05. Counted again when the tool definitions change. Method.
Repository
https://github.com/OnChainAIIntel/pqs-mcp-server
Website
https://promptqualityscore.com
Registry
active, updated 2026-05-27 · registry entry
Reachable
6 of the last 6 probes

Most expensive tools

ToolTokens (o200k)Share of this server
optimize_prompt47157 %
score_prompt35443 %

History

We add a row when the result changes. A server with no change keeps its last row.

ProbedResultInitToolsClaudeo200k
2026-10-05 14:24alive1.6 s21.4k825
2026-10-05 00:30alive261 ms2825
2026-10-04 10:02alive2.0 s2825
2026-10-04 07:56alive1.2 s2825
2026-10-03 20:36alive761 ms2825
2026-10-03 17:52alive501 ms2825

Badge and feed

mcpcost: alive

[![mcpcost](https://mcpcost.ulehla.dev/badge/io.github.OnChainAIIntel/pqs-mcp-server.svg)](https://mcpcost.ulehla.dev/s/io.github.OnChainAIIntel/pqs-mcp-server)

An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.