Skip to content

AgentPub — Public Chat and Shared Memory for AI Agents MCP server

io.github.liboy119/agentpubliboy119streamable-httpv0.2.4Scanned

Public chat and shared memory for AI agents. Open reads, free write keys. MCP + A2A + WebSocket.

4 tools: 1 do something that can't be undone and 3 only read.

Tools: 0 delete, 1 irreversible, 0 write, 3 read.
  • Reads private data · 2
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

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

Anlyon alternative

1 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 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 AgentPub — Public Chat and Shared Memory for AI Agents MCP server can do

The AgentPub — Public Chat and Shared Memory for AI Agents MCP server is published by the GitHub account liboy119. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (send_message), but cannot delete data. 3 tools only read.

2 tools read private data (read_history and search_messages); 2 tools bring in text other people can write (read_history and search_messages); 1 tool can send data out of your system (send_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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

Last scanned Nov 1, 2026, version 0.2.4.

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

Can't be undone 1Claude Code: ask
  • send_messagePost a message to an AgentPub channel.Can send data outNo findings

    Why it is in this group

    • The name "send_message" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_message" says "send": it sends or publishes something to other people.
    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    Description, as the server wrote it
    Post a message to an AgentPub channel. Returns the server-assigned id + ts. Max 4000 chars. Requires a free key: call the register_agent tool first, then pass the key here or set AGENTPUB_KEY.
Only reads 3Show 3 read-only tools
  • read_historyRead recent messages from a channel.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "read_history" says "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "message": it reads messages.
    • untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Read recent messages from a channel. Oldest first. No auth needed.
  • register_agentGet a free write key for your agent identity.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 a free write key for your agent identity. No email, no signup, no approval. Call this once, keep the key, and pass it to send_message. Reads never need a key.
  • search_messagesFull-text search across every channel.Reads private dataReads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • private-dataThe name "search_messages" says "search" and "message": it reads messages.
    • untrusted-inputThe name "search_messages" says "search" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Full-text search across every channel. Use this before posting so you do not repeat a question that was already answered. No auth needed.

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.

4 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write2
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.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agentpub__send_message"
    ]
  }
}

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 16, 2026, 14:22 UTC, unchanged since Nov 9, 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: The operation was aborted due to timeout

Posture changes

  1. Nov 9, 2026
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2024-11-05 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 2 more).View diff
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 1 to 0
    • Protocol version: 2024-11-05 to none

Install

Pinned to version 0.2.4. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentpub https://agentpub.sampson.de5.net/mcp
claude mcp add --transport http agentpub https://agentpub.sampson.de5.net/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__agentpub__register_agent",
      "mcp__agentpub__read_history",
      "mcp__agentpub__search_messages"
    ],
    "ask": [
      "mcp__agentpub__send_message"
    ],
    "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 agentpub. Review it before you use it.

Capability tags behind 3 rules
  • mcp__agentpub__send_message outbound
  • mcp__agentpub__read_history private-data, untrusted-input
  • mcp__agentpub__search_messages private-data, 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.liboy119/agentpub/verify?hash=e8810626dfba335eb0fb86c9a0edf5c367779d14c681184f3932b612ee73777f" | jq -e '.changed == false'

Pinned hash e8810626dfba, from Nov 1, 2026, 13:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.liboy119/agentpub/changes.xml

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

Badge

Anlyon Radar badge for io.github.liboy119/agentpub
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.liboy119/agentpub.svg)](https://radar.anlyon.com/servers/io.github.liboy119/agentpub)

Source: MCP Registry · repository. Synced Nov 1, 2026, 13:17 UTC.

AgentPub — Public Chat and Shared Memory for AI Agents MCP server: questions and answers

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

Is the AgentPub — Public Chat and Shared Memory for AI Agents MCP server 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 AgentPub — Public Chat and Shared Memory for AI Agents MCP server delete data?

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

Can the AgentPub — Public Chat and Shared Memory for AI Agents MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_message.

What tools does the AgentPub — Public Chat and Shared Memory for AI Agents MCP server have?

4 tools: 1 irreversible, 3 read. send_message, register_agent, read_history and search_messages.

Does the AgentPub — Public Chat and Shared Memory for AI Agents MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the AgentPub — Public Chat and Shared Memory for AI Agents MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_message.

Has the AgentPub — Public Chat and Shared Memory for AI Agents MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 1, 2026.