io.github.jdhart81/maxwell-defense
maxwell-defense-agent
io.github.jdhart81/maxwell-defense costs 184 tokens of context per session. It has 2 tool definitions. That is 0.1 % of a 200k window. Measured 2026-10-03.
Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.
alive probed 2026-10-03 · HTTP 200
2tools
184tokens for the tool definitions
<0.1 %of a 200k context window
2.9 sto initialize
66 msto list tools
- Endpoint
- https://mcp.viridis-security.com/maxwell-defense/mcp (streamable-http)
- Host
- mcp.viridis-security.com
- Protocol
- 2025-11-25
- Reports itself as
- maxwell-defense-agent 1.28.1
- Capabilities
- experimental, prompts, resources, tools
- Instructions
- none
- Repository
- https://github.com/jdhart81/viridis-agent-fleet
- Registry
- active, updated 2026-09-13 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| rehearse_defense | 153 | 83 % |
| describe_agent | 31 | 17 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:38 | alive | 2.9 s | 2 | 184 |
| 2026-10-03 17:53 | alive | 730 ms | 2 | 184 |
Badge
[](https://mcp-pulse.ulehla.dev/s/io.github.jdhart81/maxwell-defense)