Maxwell Defense
Server Details
Model proof-of-work policy and latency for AI agents. $1 USDC rehearsal; no runtime protection.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- jdhart81/viridis-agent-fleet
- GitHub Stars
- 0
- Server Listing
- viridis-agent-fleet
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools sit at different stages: describe_agent is free scope/price discovery, while rehearse_defense is a paid bounded rehearsal that returns a model and hash measurement. The verbs and cost signals separate them well, though 'describe_agent' is a slightly odd framing for a defense server and an agent could initially expect it to describe the endpoint rather than the engagement scope.
Both names follow a strict verb_noun snake_case pattern (describe_agent, rehearse_defense). No mixing of conventions or vague single-word verbs.
Two tools is thin for anything called a defense surface, even a deliberately bounded one. The free-discovery-plus-paid-rehearsal pair is coherent, but the set sits at the borderline where an agent has almost no room to operate.
The stated scope (discovery, then a $1 rehearsal yielding a model and local hash) is internally covered, and the description explicitly disclaims activation or energy-savings claims. However, there is no tool to retrieve or verify a prior rehearsal's result, and the workflow dead-ends after rehearsal with no path to apply or re-check anything.
Available Tools
2 toolsdescribe_agentDescribe this serviceCRead-onlyIdempotentInspect
Free scope and price discovery.
Inputs: no named parameters. Returns: result
rehearse_defenseRehearse defenseCInspect
$1 bounded policy rehearsal. Returns a model and local hash measurement.
Does not activate endpoint protection or establish energy savings.
Inputs: backend_cost_ms (required), client_p95_budget_ms (required), client_hashes_per_second (required), peak_requests_per_secon… Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Paid agent work and paid verification, settled in USDC. Verified outcomes get signed receipts.
Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.
AI agents trade general work for test USDC on Base Sepolia, with escrow and signed evidence.
15 paid AI agent primitives via x402 (USDC on Base). Pay-per-call MCP server.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceAI agents hire people for work they can't finish alone (data curation, red-teaming, scraping, transcription), paid via non-custodial USDC escrow on Base. Returns unsigned transactions and holds no keys.1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceAutonomous Cloud GPU Spot Bursts (rent_gpu_burst_arbitrage): Scans wholesale spot orderbooks (RTX 3090, RTX 4090, A100, H100) and provisions on-demand 3-minute compute bursts ($0.0500 USDC) with an automated 180-second idle deadman destruction switch and warm-pool multi-agent reuse.MIT

AgentRelayofficial
AlicenseNot gradedqualityDmaintenanceTurns idle AI quota into verified microtask output by coordinating agents to publish, claim, and submit tasks with machine validation.42 PyPI67Apache 2.0
cyberdyne-mcpofficial
AlicenseAqualityDmaintenanceLets an AI agent hire and pay a verified human: post real-world tasks (voice, observation, judgment) and pay in USDC via a non-custodial x402 auth-capture escrow on Base, budget frozen at deploy. Humans verify their X identity before submitting.881 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.