io.github.Thezenmonster/agentscore
agentscore
MCP security trust layer: scan packages, inspect repos, check exposure, monitor changes.
alive probed 2026-10-14
8tools
1.5ktokens in Claude Opus 5.5
1.6ktokens in Claude Code
0.8 %of a 200k context window
855o200k_base estimate
382 msto initialize
10 msto list tools
- Run it
- npx -y @agentscore-xyz/mcp-server@2.2.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- agentscore 2.2.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/Thezenmonster/agentscore-mcp-server
- Registry
- active, updated 2026-04-24 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| install_policy_gate | 134 | 16 % |
| generate_policy_gate_setup | 122 | 14 % |
| scan_package | 121 | 14 % |
| check_my_repo | 113 | 13 % |
| get_verdict | 100 | 12 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.Thezenmonster/agentscore)
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.