com.brydge-ai/brydge
BRYDGE
Checks whether an agent's actions actually happened, against the destination's own records.
alive probed 2026-10-15
5tools
1.6ktokens in Claude Opus 5.5
1.6ktokens in Claude Code
0.8 %of a 200k context window
980o200k_base estimate
186 msto initialize
21 msto list tools
- Run it
- npx -y brydge-mcp@0.2.0 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- brydge 0.2.0
- Capabilities
- tools
- Instructions
- 922 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/contactkontey-dotcom/brydge-mcp
- Website
- https://www.brydge-ai.com
- Registry
- active, updated 2026-10-02 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| brydge_supervise | 357 | 36 % |
| brydge_report_outcome | 214 | 22 % |
| brydge_verify | 167 | 17 % |
| brydge_get_headroom | 125 | 13 % |
| brydge_get_finding | 117 | 12 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/com.brydge-ai/brydge)
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.