io.github.jdhart81/agent-arbitration

by jdhart81 · remote · no sign-in to list tools · v0.2.0 · published by GitHub user jdhart81

Deterministic, machine-verifiable dispute resolution for A2A escrows.

Changes · 5

Compare Registry entry

8 tools: 5 change things and 3 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things5Claude Code: ask: see these tools
Only reads3Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http agent-arbitration https://mcp.viridisconservation.com/arbitration/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

8 tools

Changes things 5Creates or changes something that can be changed back.Claude Code: ask

file_caseFile a dispute over an escrow.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
File a dispute over an escrow. Opens the evidence window. Parties must be distinct; amount is in minor currency units (cents).
ruleIssue the deterministic ruling: allocates 100% of the disputed amount from evidence weights + trust scores, and emits an escrow instruction (release/refund).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
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.
set_trust_scoresAttach trust-oracle reputation scores (party -> [0,1]) as ruling inputs.No findings
Why it is in this group
- The name "set_trust_scores" says "set": a word for a change.
Description, as the server wrote it
Attach trust-oracle reputation scores (party -> [0,1]) as ruling inputs.
submit_evidenceSubmit evidence while the case is open.No findings
Why it is in this group
- The name "submit_evidence" says "submit": a word for a change.
Description, as the server wrote it
Submit evidence while the case is open. kind: delivery_proof (weight 3), log (2), or statement (1). Only the named parties may submit.
verify_rulingRecompute the ruling from its cited evidence + trust inputs and check it matches the stored allocation (machine-checkable justice).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
Recompute the ruling from its cited evidence + trust inputs and check it matches the stored allocation (machine-checkable justice).

Only reads 3Looks things up and changes nothing.Claude Code: allow

describe_agentFleet-standard self-description.No findings
Why it is in this group
- The name "describe_agent" says "describe": a word for reading.
Description, as the server wrote it
Fleet-standard self-description.
get_caseFetch the full case record, including any ruling.No findings
Why it is in this group
- The name "get_case" says "get": a word for reading.
Description, as the server wrote it
Fetch the full case record, including any ruling.
list_casesList cases, optionally filtered by state (FILED|EVIDENCE_OPEN|RULED).No findings
Why it is in this group
- The name "list_cases" says "list": a word for reading.
Description, as the server wrote it
List cases, optionally filtered by state (FILED|EVIDENCE_OPEN|RULED).

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 15:00 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 5
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://mcp.viridisconservation.com/arbitration/mcp: tools/list returned 8 tools to an anonymous client, including file_case (write), submit_evidence (write), set_trust_scores (write), rule (write), verify_ruling (write)
What this check looks for

Install

Pinned to version 0.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-arbitration https://mcp.viridisconservation.com/arbitration/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__agent-arbitration__get_case",
      "mcp__agent-arbitration__list_cases",
      "mcp__agent-arbitration__describe_agent"
    ],
    "ask": [
      "mcp__agent-arbitration__file_case",
      "mcp__agent-arbitration__submit_evidence",
      "mcp__agent-arbitration__set_trust_scores",
      "mcp__agent-arbitration__rule",
      "mcp__agent-arbitration__verify_ruling"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-arbitration. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.jdhart81/agent-arbitration/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

5 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:36 UTC.

For agents: Markdown · JSON · report this listing