Skip to content

ArcID MCP server

io.github.arcusid/arcid-mcparcusidstreamable-httpv0.2.0Scanned

Look up AI agents on Arc: ERC-8004 identity, feedback, validations and USDC-backed trust scores.

6 tools: 6 only read.

Tools: 0 delete, 0 irreversible, 0 write, 6 read.
  • Reads private data · 1
  • Reads text others write · 6
  • Can send data out · 0
  • No findings

The remote endpoint did not answer the last look. Remote posture

Anlyon alternative

Run the operations that matter 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 Radar 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 →

What the ArcID MCP server can do

The ArcID MCP server is published by the GitHub account arcusid. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

1 tool reads private data (search_agents); 6 tools bring in text other people can write (search_agents, get_agent, get_agent_feedback and 3 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Nov 3, 2026, version 0.2.0.

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.

6 tools

Only reads 6Show 6 read-only tools
  • get_agentFull ArcID record for one agent: profile, owner, agent wallet, reputation summary, validations, trust score and the USDC settlement evidence behind it.Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Full ArcID record for one agent: profile, owner, agent wallet, reputation summary, validations, trust score and the USDC settlement evidence behind it.

    Annotations the server declares

    • title: Get agent
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_agent_feedbackFeedback left for an agent in the ERC-8004 Reputation Registry, newest first.Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent_feedback" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Feedback left for an agent in the ERC-8004 Reputation Registry, newest first. Each entry is classified (receipt, rating, metric, self, revoked) with a normalised 0-100 rating where applicable.

    Annotations the server declares

    • title: Get agent feedback
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_agent_validationsThe latest 100 validation requests and responses for an agent from the ERC-8004 Validation Registry.Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent_validations" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    The latest 100 validation requests and responses for an agent from the ERC-8004 Validation Registry.

    Annotations the server declares

    • title: Get agent validations
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_indexer_healthHow far the ArcID indexer is behind the Arc chain head.Reads text others writeNo findings

    Why it is in this group

    • The name "get_indexer_health" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    How far the ArcID indexer is behind the Arc chain head. Check this when results look empty or stale.

    Annotations the server declares

    • title: Get indexer health
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_registry_statsTotals across the ArcID index: agents, owners, feedback, validations and settled USDC.Reads text others writeNo findings

    Why it is in this group

    • The name "get_registry_stats" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Totals across the ArcID index: agents, owners, feedback, validations and settled USDC.

    Annotations the server declares

    • title: Get registry stats
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • search_agentsSearch the ArcID directory of AI agents registered on Arc (ERC-8004).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "search_agents" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "search" and "directory": it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Search the ArcID directory of AI agents registered on Arc (ERC-8004). Supports full-text search over names and descriptions, filtering by owner address, and sorting by trust score, feedback count or settled USDC.

    Annotations the server declares

    • title: Search agents
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

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 outbound.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
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.

The remote endpoint did not answer the last look

Looked at Nov 20, 2026, 19:02 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
no
HTTP status of an anonymous initialize
not observed
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
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

The probe stopped: mcp.arcusid.com does not resolve.

Posture changes

  1. Nov 13, 2026
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none

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.

  1. PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 1 more).View diff
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Protocol version: 2025-06-18 to none

Install

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

claude mcp add --transport http arcid https://mcp.arcusid.com/mcp
claude mcp add --transport http arcid https://mcp.arcusid.com/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__arcid__search_agents",
      "mcp__arcid__get_agent",
      "mcp__arcid__get_agent_feedback",
      "mcp__arcid__get_agent_validations",
      "mcp__arcid__get_registry_stats",
      "mcp__arcid__get_indexer_health"
    ],
    "ask": [],
    "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 arcid. Review it before you use it.

Capability tags behind 6 rules
  • mcp__arcid__search_agents private-data, untrusted-input
  • mcp__arcid__get_agent untrusted-input
  • mcp__arcid__get_agent_feedback untrusted-input
  • mcp__arcid__get_agent_validations untrusted-input
  • mcp__arcid__get_registry_stats untrusted-input
  • mcp__arcid__get_indexer_health untrusted-input

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.arcusid/arcid-mcp/verify?hash=7bade6184ca09ac943f80803b150012b2a737e2f0f00217bac268298867e6c54" | jq -e '.changed == false'

Pinned hash 7bade6184ca0, from Nov 3, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.arcusid/arcid-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.arcusid/arcid-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.arcusid/arcid-mcp.svg)](https://radar.anlyon.com/servers/io.github.arcusid/arcid-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:23 UTC.

ArcID MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the ArcID MCP server safe?

No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the ArcID MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the ArcID 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 ArcID MCP server have?

6 tools: 6 read. search_agents, get_agent, get_agent_feedback, get_agent_validations, get_registry_stats and get_indexer_health.

Does the ArcID MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the ArcID MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the ArcID MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 3, 2026.