Voix contact MCP server
co.lbm/contactlbm.costreamable-httpv1.0.0Scanned
Reach a human at Voix: submit the studio contact form and get a reply by email.
2 tools: 1 can delete or cancel things and 1 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel 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 Voix contact MCP server can do
The Voix contact MCP server is published by lbm.co, a domain the MCP Registry verified. It has 2 tools. It can delete or cancel things (1 tool: submit_contact_form). 1 tool only reads.
1 tool reads private data (draft_contact_form); 1 tool brings in text other people can write (submit_contact_form).
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.
2 tools
Deletes or cancels 1Claude Code: deny
submit_contact_formSend an enquiry to the Voix and LogicBomb Media team through the contact form on their website.Reads text others writeNo findings
Why it is in this group
- The name "submit_contact_form" says "submit": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Send an enquiry to the Voix and LogicBomb Media team through the contact form on their website. Use this when someone wants to start a project, request a quote, book a demo, ask about pricing or timelines, discuss a partnership, or otherwise reach a human at Voix or LogicBomb Media. The submission goes straight to the team's notifications and a person replies by email, normally within two business days. There is no other tool here — nothing reads data back, so this is the only thing this server does. Call it only with details the person actually gave you: their real name, a reply-to address they confirmed, and their own description of what they need. Do not invent contact details, do not submit on a hunch, and tell the person you are sending the message before you send it. Each submission reaches a real human's inbox, so send one per enquiry rather than retrying a call that already succeeded.
Annotations the server declares
- title: Contact the Voix team
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Only reads 1Show 1 read-only tool
draft_contact_formShow the person an editable contact form for the Voix and LogicBomb Media team, prefilled with whatever you already know.Reads private dataNo findings
Why it is in this group
- The description's first verb is "show": a word for reading.
What it can reach
- private-dataThe name "draft_contact_form" says "contact": it reads contacts.
- private-dataThe description's first sentence says "show" and "contact": it reads contacts.
Description, as the server wrote it Show the person an editable contact form for the Voix and LogicBomb Media team, prefilled with whatever you already know. Use this in place of submit_contact_form whenever you can show interactive content: the person checks the details, fills any gaps and presses Send themselves, so nothing reaches the team without their say-so. Prefill only what they actually told you — never invent a name, an email address or a budget. This tool sends nothing. It only draws the form. Once it is on screen, do not also call submit_contact_form for the same enquiry; the form does that when the person sends it, and tells you the reference.
Annotations the server declares
- title: Draft a message to the Voix team
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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 outbound.
- Reads private data1
- 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 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, 18:32 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
- 1
- 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 1 tool that changes things (1 destructive). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://lbm.co/mcp: tools/list returned 2 tools to an anonymous client, including submit_contact_form (destructive)
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http contact https://lbm.co/mcpclaude mcp add --transport http contact https://lbm.co/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__contact__draft_contact_form"
],
"ask": [],
"deny": [
"mcp__contact__submit_contact_form"
]
}
}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 contact. Review it before you use it.
Capability tags behind 2 rules
- mcp__contact__submit_contact_form untrusted-input
- mcp__contact__draft_contact_form private-data
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.lbm/contact/verify?hash=d7691ebcbb903be4876524b882ddd7b42921aad59aab106ff03ad74084fb9a9a" | jq -e '.changed == false'Pinned hash d7691ebcbb90, from Nov 12, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/co.lbm/contact/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/co.lbm/contact)Source: MCP Registry. Synced Oct 21, 2026, 17:47 UTC.
Voix contact MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Voix contact MCP server safe?
- No scan can promise that. What its definitions show: 2 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 Voix contact MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: submit_contact_form.
Can the Voix contact 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 Voix contact MCP server have?
- 2 tools: 1 destructive, 1 read. submit_contact_form and draft_contact_form.
Does the Voix contact MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Voix contact MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Voix contact MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.