Arclan MCP Registry
ai.arclan/registryarclan.aistreamable-httpv0.2.0Scanned
MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.
4 tools: 1 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 1
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 Arclan MCP Registry can do
The Arclan MCP Registry is published by arclan.ai, a domain the MCP Registry verified. It has 4 tools. It can create or change data (1 tool: report_server), but cannot delete data. 3 tools only read.
1 tool brings in text other people can write (get_server); 1 tool can send data out of your system (get_server).
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.
Last scanned Nov 11, 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.
4 tools
Changes things 1Claude Code: ask
report_serverSubmit an agent usage report for an MCP server.No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit an agent usage report for an MCP server. Reports are aggregated and influence registry trust scores. Call this after using an MCP server so the registry can track real-world reliability. Supports both a simple outcome report and a structured scoring report (criterion + component_score).
Only reads 3Show 3 read-only tools
get_serverGet full details for a specific MCP server.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_server" says "get": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get full details for a specific MCP server. Pass the server name (e.g. "GitHub", "Brave Search"), registry ID slug, or endpoint URL. Returns score, state, tools list, latency, and recent test history.
query_registrySearch the Arclan registry for MCP servers.No findings
Why it is in this group
- The name "query_registry" says "query": a word for reading.
Description, as the server wrote it Search the Arclan registry for MCP servers. By default returns only connectable servers (active, mcp_partial, auth_gated). Use status=stdio to browse local-only servers available for installation. Use status=all to query the full index. Use production_safe=true to restrict to servers with uptime > 97% and handshake success > 95%. Use read_only=true to restrict to servers with no write or exec tools. Use this before connecting to an MCP server to check its validation status and score. After using a server, call report_server to contribute reliability data.
recommend_serverGet ranked MCP server recommendations for a task.No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get ranked MCP server recommendations for a task. Returns servers scored by production safety, keyword relevance, registry score, latency, and freshness. Each result includes a reason code array explaining why it was ranked. Use this instead of query_registry when you want an opinionated ranked list rather than a filtered search.
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.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- 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, 18:24 UTC, unchanged since Nov 20, 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
- 3
- Protocol version
- 2024-11-05
- 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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://arclan.ai/mcp: tools/list returned 6 tools to an anonymous client, including report_server (write), sign_in (write), complete_sign_in (write)
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 1 to 3
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.
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 3.View diff
- Tools that change things, listed without credentials: 1 to 3
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http registry https://arclan.ai/mcpclaude mcp add --transport http registry https://arclan.ai/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__registry__query_registry",
"mcp__registry__recommend_server"
],
"ask": [
"mcp__registry__get_server",
"mcp__registry__report_server"
],
"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 registry. Review it before you use it.
Capability tags behind 1 rule
- mcp__registry__get_server untrusted-input, outbound
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/ai.arclan/registry/verify?hash=60d213d2248995111407ed1d0767e25f56c4af7ca15a0df125d1e2608b17e154" | jq -e '.changed == false'Pinned hash 60d213d22489, from Nov 11, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.arclan/registry/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.arclan/registry)Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.
Arclan MCP Registry: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Arclan MCP Registry safe?
- No scan can promise that. What its definitions show: 4 tools, 1 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 Arclan MCP Registry delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Arclan MCP Registry 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 Arclan MCP Registry have?
- 4 tools: 1 write, 3 read. report_server, query_registry, get_server and recommend_server.
Does the Arclan MCP Registry need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Arclan MCP Registry send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_server.
Has the Arclan MCP Registry changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.