Agent Arbitration MCP server
io.github.jdhart81/agent-arbitrationjdhart81streamable-httpv0.2.1Scanned
Deterministic, machine-verifiable dispute resolution for A2A escrows.
8 tools: 5 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Agent Arbitration MCP server can do
The Agent Arbitration MCP server is published by the GitHub account jdhart81. It has 8 tools. It can create or change data (5 tools: file_case, submit_evidence, set_trust_scores, rule and 1 more), but cannot delete data. 3 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 0.2.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 5Claude 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).
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: File case
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Rule
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Set trust scores
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
- readOnlyHint: false
- title: Submit evidence
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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Verify ruling
Only reads 3Show 3 read-only tools
describe_agentDescribe this agent: name, version, purpose, every action it supports and the inputs each one takes.No findings
Why it is in this group
- The name "describe_agent" says "describe": a word for reading.
Description, as the server wrote it 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 server.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Describe this service
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: Get case
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).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
- title: List cases
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 Nov 20, 2026, 19:06 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
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- 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.
What this check looks forMatched 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)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools7 changed.~7 changedView diff
- Changed:file_caseChanges thingsinputSchema
- Changed:get_caseOnly readsinputSchema
- Changed:list_casesOnly readsinputSchema
- Changed:ruleChanges thingsinputSchema
- Changed:set_trust_scoresChanges thingsinputSchema
- Changed:submit_evidenceChanges thingsinputSchema
- Changed:verify_rulingChanges thingsinputSchema
Tools8 changed.~8 changedView diff
- Changed:describe_agentOnly readstitledescriptionannotations
- Changed:file_caseChanges thingstitleannotations
- Changed:get_caseOnly readstitleannotations
- Changed:list_casesOnly readstitleannotations
- Changed:ruleChanges thingstitleannotations
- Changed:set_trust_scoresChanges thingstitleannotations
- Changed:submit_evidenceChanges thingstitleannotations
- Changed:verify_rulingChanges thingstitleannotations
Install
Pinned to version 0.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-arbitration https://mcp.viridisconservation.com/arbitration/mcpclaude mcp add --transport http agent-arbitration https://mcp.viridisconservation.com/arbitration/mcpRun 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.
{
"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.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.jdhart81/agent-arbitration/verify?hash=7392e8ecdcc6eb5be380cf5340d1ef84744012ce2cc3d96d424ed07a95bf9b9d" | jq -e '.changed == false'Pinned hash 7392e8ecdcc6, from Nov 16, 2026, 02:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.jdhart81/agent-arbitration/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.jdhart81/agent-arbitration)Source: MCP Registry · repository. Synced Nov 16, 2026, 02:17 UTC.
Agent Arbitration MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Arbitration MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agent Arbitration MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Arbitration MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Agent Arbitration MCP server have?
- 8 tools: 5 write, 3 read. file_case, submit_evidence, set_trust_scores, rule, verify_ruling, get_case, list_cases and describe_agent.
Does the Agent Arbitration MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Arbitration MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Arbitration MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.