Browser Automation Agent by Nova (CIVAI) MCP server
co.civai.nova/browsergpt-agentnova.civai.costreamable-httpv1.0.0Scanned
I do everything related to Browser Automation & Management
4 tools: 1 do something that can't be undone, 2 change things and 1 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 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.
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 Browser Automation Agent by Nova (CIVAI) MCP server can do
The Browser Automation Agent by Nova (CIVAI) MCP server is published by nova.civai.co, a domain the MCP Registry verified. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (converse) and create or change data (2 tools: submit_task and track_task), but cannot delete data. 1 tool only reads.
1 tool brings in text other people can write (get_session_history); 1 tool can send data out of your system (converse).
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 12, 2026, version 1.0.0.
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
Can't be undone 1Claude Code: ask
converseReply conversationally when the request is ambiguous or needs clarification.Can send data outNo findings
Why it is in this group
- The description's first verb is "reply": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe description's first verb is "reply": it sends or publishes something to other people.
Description, as the server wrote it Reply conversationally when the request is ambiguous or needs clarification.
Changes things 2Claude Code: ask
submit_task🤖 BrowserGPT Agent: submit taskNo findings
Why it is in this group
- The name "submit_task" says "submit": a word for a change.
Description, as the server wrote it 🤖 BrowserGPT Agent: submit task
track_task🤖 BrowserGPT Agent: track taskNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 🤖 BrowserGPT Agent: track task
Only reads 1Show 1 read-only tool
get_session_history🤖 BrowserGPT Agent: get session historyReads text others writeNo findings
Why it is in this group
- The name "get_session_history" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "browser": it reads web pages, which anyone can write.
Description, as the server wrote it 🤖 BrowserGPT Agent: get session history
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, 18:32 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
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/browsergpt-agent
- Authorization servers
- https://nova.civai.co
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- 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.
What this check looks forMatched text
https://nova.civai.co/mcp/agents/browsergpt-agent: tools/list returned 4 tools to an anonymous client, including converse (irreversible), submit_task (write), track_task (write)
Posture changes
- Oct 29, 2026
- HTTP status of an anonymous initialize: 502 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
- RFC 9728 protected resource metadata: none to https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/browsergpt-agent
- Authorization servers: none to https://nova.civai.co
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
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. HTTP status of an anonymous initialize: 502 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 3 (and 5 more).View diff
- HTTP status of an anonymous initialize: 502 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
- RFC 9728 protected resource metadata: none to https://nova.civai.co/.well-known/oauth-protected-resource/mcp/agents/browsergpt-agent
- Authorization servers: none to https://nova.civai.co
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http browsergpt-agent https://nova.civai.co/mcp/agents/browsergpt-agentclaude mcp add --transport http browsergpt-agent https://nova.civai.co/mcp/agents/browsergpt-agentRun 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__browsergpt-agent__get_session_history"
],
"ask": [
"mcp__browsergpt-agent__submit_task",
"mcp__browsergpt-agent__track_task",
"mcp__browsergpt-agent__converse"
],
"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 browsergpt-agent. Review it before you use it.
Capability tags behind 2 rules
- mcp__browsergpt-agent__get_session_history untrusted-input
- mcp__browsergpt-agent__converse 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/co.civai.nova/browsergpt-agent/verify?hash=658033719f33cb7b021eef8b0c83e7d84869898f6e9e0424d8bfabbb99398550" | jq -e '.changed == false'Pinned hash 658033719f33, from Nov 12, 2026, 09:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/co.civai.nova/browsergpt-agent/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/co.civai.nova/browsergpt-agent)Source: MCP Registry. Synced Oct 21, 2026, 17:46 UTC.
Browser Automation Agent by Nova (CIVAI) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Browser Automation Agent by Nova (CIVAI) MCP server safe?
- No scan can promise that. What its definitions show: 4 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 Browser Automation Agent by Nova (CIVAI) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Browser Automation Agent by Nova (CIVAI) MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: converse.
What tools does the Browser Automation Agent by Nova (CIVAI) MCP server have?
- 4 tools: 1 irreversible, 2 write, 1 read. converse, submit_task, track_task and get_session_history.
Does the Browser Automation Agent by Nova (CIVAI) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Browser Automation Agent by Nova (CIVAI) 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): converse.
Has the Browser Automation Agent by Nova (CIVAI) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.