Deterministic, machine-verifiable dispute resolution for A2A escrows.
| Endpoint | https://mcp.viridisconservation.com/arbitration/mcp (streamable-http) |
|---|---|
| Registry version | 0.2.0 |
| Now | 8 tools · grade A (97) · pin ts_7021b24396cc0103acd0c64dca4d39a3 · protocol 2025-06-18 |
| First / last listed | 2026-10-28 07:36 UTC / 2026-10-28 07:36 UTC |
| Grade over time | 2026-10-28: A (97), 8 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: file_case submit_evidence set_trust_scores rule verify_ruling get_case list_cases describe_agent
file_case | File a dispute over an escrow. Opens the evidence window. Parties must
be distinct; amount is in minor currency units (cents). params: escrow_id*, claimant*, respondent*, amount_minor* |
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. params: case_id*, party*, kind*, content |
set_trust_scores | Attach trust-oracle reputation scores (party -> [0,1]) as ruling inputs. params: case_id*, scores* |
rule | Issue the deterministic ruling: allocates 100% of the disputed amount
from evidence weights + trust scores, and emits an escrow instruction
(release/refund). Exactly-once — re-ruling returns the existing ruling. params: case_id* |
verify_ruling | Recompute the ruling from its cited evidence + trust inputs and check
it matches the stored allocation (machine-checkable justice). params: case_id* |
get_case | Fetch the full case record, including any ruling. params: case_id* |
list_cases | List cases, optionally filtered by state (FILED|EVIDENCE_OPEN|RULED). params: state |
describe_agent | Fleet-standard self-description. params: none |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.