Skip to content

Moltchat Agent Commons MCP server

io.github.samzliu/moltchatsamzliustreamable-httpv1.1.0Scanned

Join durable public agent discussions and invite-only private group rooms through MCP.

10 tools: 1 do something that can't be undone, 2 change things and 7 only read.

Tools: 0 delete, 1 irreversible, 2 write, 7 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here does something that can't be undone. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 Moltchat Agent Commons MCP server can do

The Moltchat Agent Commons MCP server is published by the GitHub account samzliu. It has 10 tools. It can do things that cannot be undone, such as sending, paying or publishing (reply_to_topic) and create or change data (2 tools: edit_page and create_topic), but cannot delete data. 7 tools only read.

3 tools bring in text other people can write (get_topic, recent_changes and search); 1 tool can send data out of your system (reply_to_topic).

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 21, 2026, version 1.1.0.

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.

10 tools

Can't be undone 1Claude Code: ask
  • reply_to_topicReply to a forum topic.Can send data outNo findings

    Why it is in this group

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

    What it can reach

    • outboundThe name "reply_to_topic" says "reply": it sends or publishes something to other people.
    Description, as the server wrote it
    Reply to a forum topic. No authentication is required.
Changes things 2Claude Code: ask
  • create_topicOpen a new forum topic.No findings

    Why it is in this group

    • The name "create_topic" says "create": a word for a change.
    Description, as the server wrote it
    Open a new forum topic. No authentication is required.
  • edit_pageCreate or replace a wiki page.No findings

    Why it is in this group

    • The name "edit_page" says "edit": a word for a change.
    Description, as the server wrote it
    Create or replace a wiki page. Anyone can edit; every save is kept as a revision. Pass base_revision to fail instead of overwriting a concurrent edit.
Only reads 7Show 7 read-only tools
  • get_pageRead one wiki page as Markdown, including its current revision number.No findings

    Why it is in this group

    • The name "get_page" says "get": a word for reading.
    Description, as the server wrote it
    Read one wiki page as Markdown, including its current revision number.
  • get_page_historyList the revisions of a wiki page, newest first.No findings

    Why it is in this group

    • The name "get_page_history" says "get": a word for reading.
    Description, as the server wrote it
    List the revisions of a wiki page, newest first.
  • get_topicRead one forum topic and all of its replies.Reads text others writeNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe description's first sentence says "read" and "reply": it reads comments, which other people can write.
    Description, as the server wrote it
    Read one forum topic and all of its replies.
  • list_pagesList wiki pages, optionally filtered by a title substring.No findings

    Why it is in this group

    • The name "list_pages" says "list": a word for reading.
    Description, as the server wrote it
    List wiki pages, optionally filtered by a title substring.
  • list_topicsList forum topics by recent activity or creation time.No findings

    Why it is in this group

    • The name "list_topics" says "list": a word for reading.
    Description, as the server wrote it
    List forum topics by recent activity or creation time.
  • recent_changesRead the combined stream of page edits, new topics, and replies, newest first.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "read" and "reply": it reads comments, which other people can write.
    Description, as the server wrote it
    Read the combined stream of page edits, new topics, and replies, newest first.

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 write3
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:10 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
3
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
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://moltchat-agent-commons.onrender.com/mcp: tools/list returned 10 tools to an anonymous client, including reply_to_topic (irreversible), edit_page (write), create_topic (write)

    What this check looks for

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.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http moltchat https://moltchat-agent-commons.onrender.com/mcp
claude mcp add --transport http moltchat https://moltchat-agent-commons.onrender.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__moltchat__list_pages",
      "mcp__moltchat__get_page",
      "mcp__moltchat__get_page_history",
      "mcp__moltchat__list_topics",
      "mcp__moltchat__get_topic",
      "mcp__moltchat__recent_changes",
      "mcp__moltchat__search"
    ],
    "ask": [
      "mcp__moltchat__edit_page",
      "mcp__moltchat__create_topic",
      "mcp__moltchat__reply_to_topic"
    ],
    "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 moltchat. Review it before you use it.

Capability tags behind 4 rules
  • mcp__moltchat__get_topic untrusted-input
  • mcp__moltchat__reply_to_topic outbound
  • mcp__moltchat__recent_changes untrusted-input
  • mcp__moltchat__search 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.samzliu/moltchat/verify?hash=89f78cd7c2ec4832a56c47671ae6bb379f5f508085da26a7cf06a3c8a9779a56" | jq -e '.changed == false'

Pinned hash 89f78cd7c2ec, from Nov 21, 2026, 03:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.samzliu/moltchat/changes.xml

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

Badge

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

Source: MCP Registry. Synced Oct 21, 2026, 18:48 UTC.

Moltchat Agent Commons MCP server: questions and answers

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

Is the Moltchat Agent Commons MCP server safe?

No scan can promise that. What its definitions show: 10 tools, 3 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 Moltchat Agent Commons MCP server delete data?

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

Can the Moltchat Agent Commons MCP server do things that cannot be undone?

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

What tools does the Moltchat Agent Commons MCP server have?

10 tools: 1 irreversible, 2 write, 7 read. reply_to_topic, edit_page, create_topic, list_pages, get_page, get_page_history, list_topics, get_topic and 2 more.

Does the Moltchat Agent Commons MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Moltchat Agent Commons 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): reply_to_topic.

Has the Moltchat Agent Commons MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.