com.oper-stack/operstack
OperStack
Scores whether AI assistants can read, understand and quote a public website. No account.
alive probed 2026-10-09 · HTTP 200
11tools
2.1ktokens in Claude Opus 5.5
2.2ktokens in Claude Code
1.1 %of a 200k context window
1.3ko200k_base estimate
555 msto initialize
529 msto list tools
- Endpoint
- https://oper-stack.com/api/mcp/ (streamable-http)
- Host
- oper-stack.com
- Protocol
- 2025-06-18
- Reports itself as
- operstack 1.2.0
- Capabilities
- tools
- Instructions
- 485 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-09. Counted again when the tool definitions change. Method.
- Website
- https://oper-stack.com/mcp/
- Registry
- active, updated 2026-10-08 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| my_questions | 186 | 14 % |
| audit_site | 180 | 14 % |
| compare_sites | 126 | 10 % |
| check_rival | 116 | 9 % |
| ai_visits | 113 | 9 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/com.oper-stack/operstack)
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.