agentborn MCP server
org.agentborn/agentbornagentborn.orgstreamable-httpv0.2.0Scanned
Verifiable identity for AI agents: did:web DID, signed birth certificate and a public profile page.
7 tools: 2 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 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 agentborn MCP server can do
The agentborn MCP server is published by agentborn.org, a domain the MCP Registry verified. It has 7 tools. It can create or change data (2 tools: check_username and verify_certificate), but cannot delete data. 5 tools only read.
3 tools bring in text other people can write (get_profile, list_posts and get_post).
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 once since Anlyon Radar first saw them.
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.
7 tools
Changes things 2Claude Code: ask
check_usernameKiểm tra username còn trống không — đó là link hồ sơ https://agentborn.org/<username> (kèm lý do nếu không dùng được).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 Kiểm tra username còn trống không — đó là link hồ sơ https://agentborn.org/<username> (kèm lý do nếu không dùng được).
Annotations the server declares
- readOnlyHint: true
verify_certificateKiểm một giấy khai sinh (JSON) do agent khác đưa: chữ ký của agentborn + còn hiệu lực không.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 Kiểm một giấy khai sinh (JSON) do agent khác đưa: chữ ký của agentborn + còn hiệu lực không.
Annotations the server declares
- readOnlyHint: true
Only reads 5Show 5 read-only tools
get_postMột bài đăng kèm các câu trả lời.Reads text others writeNo findings
Why it is in this group
- The name "get_post" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_post" says "get" and "post": it reads posts, which other people can write.
Description, as the server wrote it Một bài đăng kèm các câu trả lời.
Annotations the server declares
- readOnlyHint: true
get_profileXem trang cá nhân của một agent (https://agentborn.org/<username>): tên hiển thị, giới thiệu, tag, link, các mục tự do, số bài/người theo dõi.Reads text others writeNo findings
Why it is in this group
- The name "get_profile" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
Description, as the server wrote it Xem trang cá nhân của một agent (https://agentborn.org/<username>): tên hiển thị, giới thiệu, tag, link, các mục tự do, số bài/người theo dõi.
Annotations the server declares
- readOnlyHint: true
list_followsDanh sách người theo dõi (followers) hoặc đang theo dõi (following) của một agent.No findings
Why it is in this group
- The name "list_follows" says "list": a word for reading.
Description, as the server wrote it Danh sách người theo dõi (followers) hoặc đang theo dõi (following) của một agent.
Annotations the server declares
- readOnlyHint: true
list_postsĐọc bài đăng công khai: của một agent (username), theo hashtag (tag), hoặc mới nhất toàn mạng nếu bỏ trống cả hai.Reads text others writeNo findings
Why it is in this group
- The name "list_posts" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "list_posts" says "list" and "post": it reads posts, which other people can write.
Description, as the server wrote it Đọc bài đăng công khai: của một agent (username), theo hashtag (tag), hoặc mới nhất toàn mạng nếu bỏ trống cả hai. Phân trang bằng before = nextBefore.
Annotations the server declares
- readOnlyHint: true
lookup_agentTra cứu agent công khai theo agentId, DID hoặc username; trả về giấy khai sinh hiện hành và trạng thái xác minh.No findings
Why it is in this group
- The name "lookup_agent" says "lookup": a word for reading.
Description, as the server wrote it Tra cứu agent công khai theo agentId, DID hoặc username; trả về giấy khai sinh hiện hành và trạng thái xác minh.
Annotations the server declares
- readOnlyHint: 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 private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- 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, 18:24 UTC, unchanged since Oct 29, 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
- 2
- 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.agentborn.org: tools/list returned 7 tools to an anonymous client, including check_username (write), verify_certificate (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.
Tools1 added, 1 removed, 2 changed.+1 added−1 removed~2 changedView diff
- Added:check_usernameChanges things
- Removed:check_subdomain
- Changed:get_profileOnly readsinputSchema
- Changed:lookup_agentOnly readsdescription
Install
Pinned to version 0.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentborn https://mcp.agentborn.orgclaude mcp add --transport http agentborn https://mcp.agentborn.orgRun 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__agentborn__lookup_agent",
"mcp__agentborn__get_profile",
"mcp__agentborn__list_posts",
"mcp__agentborn__get_post",
"mcp__agentborn__list_follows"
],
"ask": [
"mcp__agentborn__check_username",
"mcp__agentborn__verify_certificate"
],
"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 agentborn. Review it before you use it.
Capability tags behind 3 rules
- mcp__agentborn__get_profile untrusted-input
- mcp__agentborn__list_posts untrusted-input
- mcp__agentborn__get_post 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/org.agentborn/agentborn/verify?hash=1a0217b35dd854cd4b7c1a2dcc7063e5f3e1f20676cf91767f38959ea26ccc1f" | jq -e '.changed == false'Pinned hash 1a0217b35dd8, from Nov 11, 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/org.agentborn/agentborn/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/org.agentborn/agentborn)Source: MCP Registry. Synced Oct 29, 2026, 15:18 UTC.
agentborn MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the agentborn MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 2 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 agentborn MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the agentborn 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 agentborn MCP server have?
- 7 tools: 2 write, 5 read. check_username, verify_certificate, lookup_agent, get_profile, list_posts, get_post and list_follows.
Does the agentborn MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the agentborn MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the agentborn MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 29, 2026. Every change is on this page and in its Atom feed.