← Registry

Developer Tools

lumbox.co

Manages temporary email inboxes with CRUD operations, useful for testing and automation.

1 endpoint103 known toolsFirst detected July 6, 2026Last detected September 6, 2026

ENDPOINT 1

https://mcp.lumbox.co/mcp

No auth detected

MCP server metadata

Name
lumbox
Version
0.2.2
Capabilities
resources.listChangedtools.listChanged

Known tools 103

create_inbox

Create a new email inbox.

Potential side effects
list_inboxes

List all email inboxes you have created.

Potential side effects
get_inbox

Get details of a specific inbox including email count.

Potential side effects
update_inbox

Update an inbox's name or metadata.

Potential side effects
delete_inbox

Delete an inbox and all its emails permanently.

Potential side effects
pause_inbox

Pause an inbox so it stops accepting inbound email (senders get a temporary failure).

Potential side effects
resume_inbox

Resume a paused inbox so it accepts inbound email again.

Potential side effects
set_auto_reply

Enable or disable AI auto-reply on an inbox.

Inferred read-only
list_drafts

List agent-drafted replies awaiting human approval (or already approved/rejected).

Inferred read-only
approve_draft

Approve a pending agent draft and send it as a threaded reply.

Potential side effects
reject_draft

Reject a pending agent draft so it is never sent.

Inferred read-only
list_agent_actions

List the tool calls the auto-reply agent made (knowledge base lookups, past-conversation searches, contact lookups) with inputs, outputs, status, and timing.

Inferred read-only
get_metrics

Time-series activity metrics for the org (or one inbox): received, sent, auto_replies, drafts_created, tool_calls, delivered, bounced, complained.

Inferred read-only
create_agent_tool

Register an external HTTP tool the auto-reply agent can call to fetch real data or take actions (order lookup, refund, etc).

Potential side effects
list_agent_tools

List registered external HTTP tools.

Inferred read-only
delete_agent_tool

Delete a registered external HTTP tool.

Potential side effects
create_project

Create a project (pod) to group inboxes for one end-customer of your platform.

Potential side effects
list_projects

List projects (pods) in the organization with inbox counts.

Inferred read-only
create_project_key

Mint an API key sandboxed to a project - it can only see and act on that project's inboxes.

Inferred read-only
delete_project

Delete a project.

Potential side effects
wait_for_email

Wait for an email to arrive in an inbox.

Potential side effects
get_otp

Get the latest OTP/verification code from an inbox.

Inferred read-only
list_emails

List emails in an inbox with optional filters.

Inferred read-only
add_email_labels

Add labels to an email for triage and filtering (e.g.

Potential side effects
remove_email_labels

Remove labels from an email.

Potential side effects
mark_email_spam

Flag an email as spam.

Potential side effects
unmark_email_spam

Remove the spam flag from an email so it appears again in list_emails.

Potential side effects
read_email

Read a specific email.

Potential side effects
check_email_safety

Check an email for phishing/spoofing AND prompt-injection before acting on it.

Potential side effects
search_emails

Search emails across all inboxes by keyword, sender, category, or label.

Inferred read-only
send_email

Send an email from an inbox.

Potential side effects
send_bulk_email

Send multiple emails in a single batch request.

Potential side effects
reply_to_email

Reply to an existing email.

Potential side effects
forward_email

Forward an email to another address.

Potential side effects
list_threads

List email conversation threads.

Potential side effects
get_thread

Get emails in a conversation thread.

Inferred read-only
get_context

Get a clean, model-ready context block for a thread.

Inferred read-only
update_thread

Update a thread's status.

Potential side effects
add_domain

Add a custom domain for agent email addresses.

Potential side effects
verify_domain

Check if DNS records are configured correctly and activate the domain.

Inferred read-only
set_domain_catch_all

Enable or disable catch-all on a verified domain.

Inferred read-only
list_domains

List all custom domains and their verification status.

Inferred read-only
configure_smtp

Configure a custom SMTP provider for outbound email delivery (BYOS - Bring Your Own SMTP).

Potential side effects
list_smtp_configs

List all configured SMTP providers for outbound email.

Potential side effects
test_smtp_config

Send a test email through a configured SMTP provider to verify it works.

Potential side effects
assign_thread

Assign an agent to a conversation thread.

Inferred read-only
unassign_thread

Remove an agent from a conversation thread.

Potential side effects
list_thread_agents

List all agents currently assigned to a conversation thread.

Inferred read-only
create_routing_rule

Create an auto-routing rule that assigns agents to threads based on email properties (sender, subject, category).

Potential side effects
list_routing_rules

List all routing rules for automatic thread assignment.

Inferred read-only
delete_routing_rule

Delete a routing rule.

Potential side effects
add_list_entry

Add an allowlist or blocklist entry.

Inferred read-only
list_entries

List allowlist and blocklist entries.

Inferred read-only
get_list_entry

Get a single allowlist or blocklist entry by ID.

Inferred read-only
remove_list_entry

Remove an allowlist or blocklist entry by ID.

Potential side effects
set_list_mode

Set the list filtering mode.

Inferred read-only
create_webhook

Register a webhook URL to receive real-time notifications when emails arrive.

Inferred read-only
list_webhooks

List all registered webhooks.

Inferred read-only
test_webhook

Send a test payload to a webhook to verify it's working.

Potential side effects
delete_webhook

Delete a registered webhook.

Potential side effects
configure_ai

Configure your own AI provider API key (OpenAI, Anthropic, or Google).

Inferred read-only
get_ai_config

Get the currently configured AI provider (key is masked).

Inferred read-only
create_contact_list

Create a named contact list for sending marketing emails.

Potential side effects
list_contact_lists

List all contact lists with their contact counts.

Inferred read-only
add_contacts

Add one or many contacts to a contact list.

Inferred read-only
list_contacts

List contacts in a contact list, optionally filtered by status.

Inferred read-only
remove_contact

Remove a contact from a contact list.

Potential side effects
delete_contact_list

Delete a contact list.

Potential side effects
send_marketing_email

Send a marketing email to all ACTIVE contacts in a contact list, using a chosen inbox as the sender.

Potential side effects
browser_navigate

Navigate to a URL and return a compact accessibility tree (snapshot) of the page.

Inferred read-only
browser_snapshot

Get the current page's accessibility tree with element refs.

Inferred read-only
browser_click

Click an element by its ref from the last snapshot, then return an updated snapshot.

Inferred read-only
browser_type

Type text into an input by ref, then return an updated snapshot.

Inferred read-only
browser_select

Select a dropdown option by value or visible label, then return an updated snapshot.

Inferred read-only
browser_screenshot

Take a screenshot of the current page.

Inferred read-only
browser_eval

Run JavaScript in the current page and return the result.

Inferred read-only
browser_save_state

Save the session's cookies and localStorage to a file.

Inferred read-only
browser_load_state

Restore cookies and localStorage from a saved file so the session is already logged in.

Inferred read-only
skill_signup_with_email

SKILL: Navigate to a signup page, fill the email field with an Lumbox inbox address, submit the form, then wait for a verification email and return the OTP code and/or verification link - all in one tool call.

Potential side effects
skill_login_with_email

SKILL: Navigate to a login page, enter an inbox email address, submit, then wait for the magic link or OTP and return it - all in one call.

Potential side effects
skill_verify_email

SKILL: Wait for a verification email and automatically click the verification link in the browser - all in one call.

Potential side effects
browser_close

Close a browser session and release its resources.

Inferred read-only
store_credential

Securely store a credential (password, API key, TOTP secret) in the encrypted vault.

Inferred read-only
login_with_credential

MOST SECURE LOGIN: Navigate to a login page and let Steel auto-inject credentials.

Inferred read-only
use_credential_in_browser

FALLBACK: Fill a stored credential into a browser form field WITHOUT exposing the value.

Inferred read-only
list_credentials

List stored credentials.

Inferred read-only
get_totp_code

Generate a current 6-digit 2FA/MFA code from a stored TOTP_SECRET credential, so you can complete a login that requires an authenticator app.

Inferred read-only
delete_credential

Permanently delete a stored credential from the vault.

Potential side effects
add_knowledge

Add a document to the knowledge base (product docs, policies, FAQs).

Inferred read-only
ask_knowledge

Answer a question using the organization's knowledge base (docs added via add_knowledge).

Inferred read-only
list_knowledge

List documents in the knowledge base (titles, sources, chunk counts).

Inferred read-only
compare_models

Run the same prompt across the LLM providers configured for this org and get each answer back with latency and estimated cost, plus which was cheapest and fastest.

Inferred read-only
ask_inbox

Ask a natural-language question about emails in one inbox.

Inferred read-only
ask_emails

Ask a natural-language question across every embedded email in the organization.

Potential side effects
ask_email

Ask a question about a single email - no retrieval, the email is the entire context.

Potential side effects
browser_act

Run an LLM-driven browser task.

Inferred read-only
get_agent_task

Fetch the current state of an AgentTask (browser or meeting).

Inferred read-only
list_agent_tasks

List recent AgentTasks for this organization, newest first.

Inferred read-only
cancel_agent_task

Cancel a queued or running AgentTask.

Inferred read-only
join_meeting

Have a Lumbox agent join a Google Meet, Zoom, or Teams call as a bot.

Inferred read-only
get_meeting_transcript

Fetch the joined meeting transcript + recording URL once the call is done.

Inferred read-only
end_meeting

Tell the bot to leave the call right now.

Inferred read-only
kb_search

Semantic search over previously-received and previously-sent emails.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.lumbox]
url = "https://mcp.lumbox.co/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "lumbox": {
      "type": "http",
      "url": "https://mcp.lumbox.co/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: lumbox
Remote MCP URL: https://mcp.lumbox.co/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "lumbox": {
      "url": "https://mcp.lumbox.co/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "lumbox": {
      "type": "http",
      "url": "https://mcp.lumbox.co/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "lumbox",
  "transport": "streamable-http",
  "url": "https://mcp.lumbox.co/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for lumbox.co was fetched 2026-08-24T03:10:08.040Z.

Trust status Neutral

lumbox.co is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.