io.github.RealSpap/authority-risk-mcp
authority-risk-mcp
Read-only tools for AI agents: who can change a smart contract, how fast. Signed data, testnet.
alive probed 2026-10-15
4tools
819tokens in Claude Opus 5.5
875tokens in Claude Code
0.4 %of a 200k context window
474o200k_base estimate
594 msto initialize
4 msto list tools
- Run it
- uvx authority-risk-mcp==0.1.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- authority-risk-mcp 0.1.0
- Capabilities
- tools
- Instructions
- 367 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/RealSpap/authority-risk-oracle-showcase
- Registry
- active, updated 2026-10-14 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| getScore | 135 | 28 % |
| listTargets | 129 | 27 % |
| whoControls | 109 | 23 % |
| checkProtocol | 101 | 21 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.RealSpap/authority-risk-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.