net.agentutil/think-mcp
think-mcp
Intent security pre-flight checks for autonomous AI agents.
alive probed 2026-10-14
4tools
919tokens in Claude Opus 5.5
959tokens in Claude Code
0.5 %of a 200k context window
500o200k_base estimate
226 msto initialize
7 msto list tools
- Run it
- npx -y @agentutil/think-mcp@1.0.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- think-mcp 1.0.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Registry
- active, updated 2026-02-28 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| check_intent | 183 | 37 % |
| review_action | 140 | 28 % |
| expand_intent | 124 | 25 % |
| list_actions | 53 | 11 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/net.agentutil/think-mcp)
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.