Wu Wei Router
Server Details
Plan agent workload routes from evaluation and cost data. $1 USDC per plan; modeled savings only.
- 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 have distinct primary actions: describe_agent for free scope/price discovery and plan_workload for a paid routing plan. There is slight conceptual overlap because plan_workload also references inspecting the schema and a free quote, but the free/paid distinction and different outputs make selection clear.
Both names follow a consistent snake_case verb_noun pattern: describe_agent and plan_workload. There are no mixed conventions or vague standalone verbs.
Only two tools are exposed, which feels thin even for a narrow router/planning service. Each tool does have a clear role, but the surface is at the borderline of being under-scoped.
The core workflow of free discovery followed by paid workload planning is covered, and task execution is explicitly out of scope. Minor gaps remain around retrieving or reviewing previously generated plans or separate quote validation, but these are workable for the stated purpose.
Available Tools
2 toolsdescribe_agentDescribe this serviceCRead-onlyIdempotentInspect
Free scope and price discovery.
Inputs: no named parameters. Returns: result
plan_workloadPlan workloadAInspect
$1 workload routing plan from declared costs and representative evaluation counts.
Up to 20 profiles and 50 task groups. Inspect the public service schema and a free unpaid quote first. Does not execute tasks or establish actual savings.
Inputs: tasks (required), profiles (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agentic-AI route optimization for delivery fleets, capacity- and time-window-safe.
Outcome-first agent fallback: free discovery, minimal routing, declared costs, verified execution.
Plan vehicle routes, job assignments and load packing from stops, fleet and constraints.
Agent FinOps Spend Guard, Deterministic Budget Passport, LLM Token Cost Router & VIP Discounts.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables users to plan cost-aware task decomposition and model assignment by capability and credit multiplier, with optional execution through an OpenAI-compatible endpoint and relative credit reporting.MIT
- FlicenseNot gradedqualityDmaintenanceEnables buyer-side spend-routing preflights before larger paid agent tool calls, with bounded planning and public-data evidence.-

ComputeGauge MCPofficial
AlicenseNot gradedqualityDmaintenanceProvides cost intelligence and a reputation scoring system to help AI agents optimize spending through smart model selection and local-to-cloud routing. It enables real-time cost tracking and rewards agents for making efficient, high-credibility decisions across various LLM providers.Apache 2.0- FlicenseNot gradedqualityBmaintenanceIntelligently routes AI tool calls (search, extract, browse) to the cheapest capable provider by default with automatic failover and audit receipts, enabling cost-effective agent workflows.2-
Glama MCP Gateway
Add one secure layer between your agents and this server.