# Jdhart81 Agent Arbitration MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.jdhart81%2Fagent-arbitration
Registry id: `mcp-registry/io.github.jdhart81/agent-arbitration`
Status: live (checked 2026-11-22T16:02:59.277Z)

## Verdict

Jdhart81 Agent Arbitration MCP server answered 99.98% of Glimind's liveness checks over 30 days, better than 37% of MCP servers, with 233 ms median handshake and 11 outages in 90 days. Its agent-readiness grade is A (99/100) across 8 tools, costing an agent about 1,064 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.98% | 37% of MCP servers |
| Median handshake latency | 233 ms | 52% of MCP servers |
| p95 handshake latency | 310 ms | — |
| Checks in 30 days | 6,882 | — |
| Outages, 90 days | 11 | — |
| Median recovery | 7 min | — |
| Agent-readiness score | 99/100 (A) | 90% of MCP servers |
| Tools | 8 | — |
| Tool-list size for an agent | ~1,064 tokens | 66% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "jdhart81-agent-arbitration-mcp-server": {
      "type": "http",
      "url": "https://mcp.viridisconservation.com/arbitration/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http jdhart81-agent-arbitration-mcp-server https://mcp.viridisconservation.com/arbitration/mcp
```

## Tools (21)

- `agent-arbitration`: Dispute-resolution oracle consuming trust signals
- `agent-compute-ledger`: Compute is carbon cost/energy accounting for agent work
- `agent-covenant`: Deny-by-default authority leases for agents wielding real power
- `agent-escrow`: Trustless escrow with an exactly-once state machine + audit hash chain
- `agent-identity-registry`: Content-addressed agent DIDs + capability discovery — the passport + directory
- `agent-metering`: Usage metering + SLA accounting — the meter behind x402
- `agent-offset-clearinghouse`: Verified-credit carbon accountability — the conservation flywheel
- `agent-provenance`: Genesis certificates, lineage, cascading recalls
- `agent-trust-oracle`: Decay-weighted reputation + tamper-evident trust attestations
- `describe_agent`: Describe this agent: name, version, purpose, every action it supports and the inputs each one takes. Read-only and free; call it first to learn how to use this 
- `file_case`: File a dispute over an escrow. Opens the evidence window. Parties must be distinct; amount is in minor currency units (cents).
- `get_case`: Fetch the full case record, including any ruling.
- `list_cases`: List cases, optionally filtered by state (FILED|EVIDENCE_OPEN|RULED).
- `narrative-engine`: Grant / investor / policy narrative generation
- `protogen`: MCP CAD services; bundles with SmartScale (measure → CAD)
- `regulatory-radar`: CSRD/TNFD compliance-as-a-service
- `rule`: Issue the deterministic ruling: allocates 100% of the disputed amount from evidence weights + trust scores, and emits an escrow instruction (release/refund). Ex
- `set_trust_scores`: Attach trust-oracle reputation scores (party -> [0,1]) as ruling inputs.
- `smartscale`: Credit-card-calibrated measurement — the first sellable service
- `submit_evidence`: Submit evidence while the case is open. kind: delivery_proof (weight 3), log (2), or statement (1). Only the named parties may submit.
- `verify_ruling`: Recompute the ruling from its cited evidence + trust inputs and check it matches the stored allocation (machine-checkable justice).

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
