lumbox.co is a remote MCP server that gives an AI agent 103 tools, among them add_contacts, add_domain, add_email_labels. It answers at https://mcp.lumbox.co/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 11 of 11 times since 4 September 2026; the last check, on 25 October 2026, succeeded.
Model Context Protocol server for lumbox.co, exposing 103 tools.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
add_contacts | Add one or many contacts to a contact list. Accepts a single contact or an array. Existing contacts are updated (upsert). Inputs: list_id, contacts |
add_domain | Add a custom domain for agent email addresses. Returns DNS records you need to configure. Inputs: domain |
add_email_labels | Add labels to an email for triage and filtering (e.g. "order", "refund", "vip"). Labels show up in the dashboard and can be used to filter list_emails / search_emails. Inputs: email_id, labels |
add_knowledge | Add a document to the knowledge base (product docs, policies, FAQs). It's chunked and embedded so you can later answer questions from it with ask_knowledge. Requires embeddings to be enabled for the org. Inputs: title, content, source |
add_list_entry | Add an allowlist or blocklist entry. Controls who can send/receive/reply emails. Direction: SEND (outbound control), RECEIVE (inbound from new senders), REPLY (inbound replies only). Use match_type 'EMAIL' for a specific address or 'DOMAIN' Inputs: direction, list, match_type, value, inbox_id, reason |
approve_draft | Approve a pending agent draft and send it as a threaded reply. Optionally pass edited text to send instead of the drafted version. Inputs: draft_id, text |
ask_email | Ask a question about a single email - no retrieval, the email is the entire context. Useful for summarizing one message or pulling structured details out of it. Requires AiConfig but not embeddings. Inputs: email_id, question, max_body_chars |
ask_emails | Ask a natural-language question across every embedded email in the organization. Same RAG pipeline as ask_inbox, no inbox restriction unless inbox_id is set. Inputs: question, inbox_id, k, max_body_chars, min_score |
ask_inbox | Ask a natural-language question about emails in one inbox. Runs retrieval-augmented Q&A: embedding-similarity search → grounded prompt → your BYOK LLM answer with [eml_xxx] citations. Requires both an AiConfig (PUT /v1/ai-config) and embedd Inputs: inbox_id, question, k, max_body_chars, min_score |
ask_knowledge | Answer a question using the organization's knowledge base (docs added via add_knowledge). Returns a grounded answer with source citations. Use this for support/FAQ/policy questions instead of guessing. Inputs: question, k |
assign_thread | Assign an agent to a conversation thread. Agents can be OWNER, PARTICIPANT, or OBSERVER. Inputs: thread_id, agent_id, role |
browser_act | Run an LLM-driven browser task. Lumbox spawns a stealth Chromium session, drives it with browser-use + the configured LLM, and returns when the task is done. Use for sign-ups, form fills, navigation goals, scraping, post-meeting follow-ups, Inputs: goal, inbox_id, llm_provider, llm_model |
browser_click | Click an element by its ref from the last snapshot, then return an updated snapshot. Example: ref='@e3'. Inputs: ref, session_id |
browser_close | Close a browser session and release its resources. Inputs: session_id |
browser_eval | Run JavaScript in the current page and return the result. Useful for reading values or scrolling. Example: 'document.title'. Inputs: script, session_id |
browser_load_state | Restore cookies and localStorage from a saved file so the session is already logged in. Inputs: file_path, session_id |
browser_navigate | Navigate to a URL and return a compact accessibility tree (snapshot) of the page. Elements in the snapshot have refs like @e1, @e2 - use them with browser_click and browser_type. Combine with Lumbox email tools for full sign-up + OTP flows. Inputs: url, session_id |
browser_save_state | Save the session's cookies and localStorage to a file. Use after logging in to persist the session across restarts. Inputs: file_path, session_id |
browser_screenshot | Take a screenshot of the current page. Returns the file path. Inputs: filename, session_id |
browser_select | Select a dropdown option by value or visible label, then return an updated snapshot. Inputs: ref, value, session_id |
browser_snapshot | Get the current page's accessibility tree with element refs. Call this whenever you need to re-read the page state after an action. Inputs: session_id |
browser_type | Type text into an input by ref, then return an updated snapshot. Set press_enter=true to submit a form after typing. Inputs: ref, text, press_enter, session_id |
cancel_agent_task | Cancel a queued or running AgentTask. Terminal tasks return 409. Inputs: task_id |
check_email_safety | Check an email for phishing/spoofing AND prompt-injection before acting on it. Returns a safety score (0-100), risk level, SPF/DKIM/DMARC results, deceptive-link/spoof flags, plus an `injection` report (0-100 risk that the body contains ins Inputs: email_id |
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. Use this to pick the cheapest model that's good enough for a task. Configure Inputs: prompt, providers, max_tokens |
configure_ai | Configure your own AI provider API key (OpenAI, Anthropic, or Google). Used for semantic search, smarter email summaries, and data extraction. The key is encrypted at rest. One config per organization (upsert). Inputs: provider, api_key, model |
configure_smtp | Configure a custom SMTP provider for outbound email delivery (BYOS - Bring Your Own SMTP). Supports Raw SMTP, AWS SES, SendGrid, and Postmark. Inputs: provider, name, host, port, username, password |
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). The agent calls it by name with the inputSchema parameters; Lumbox POSTs/GETs your URL and feeds the response back Inputs: name, description, url, method, headers, input_schema |
create_contact_list | Create a named contact list for sending marketing emails. Inputs: name, description |
create_inbox | Create a new email inbox. Returns the email address you can use to sign up on platforms, receive OTPs, etc. Inputs: name, domain, local_part, metadata |
create_project | Create a project (pod) to group inboxes for one end-customer of your platform. Mint a project-scoped API key with create_project_key - that key only sees this project's inboxes, giving you per-tenant isolation. Requires an org-level key. Inputs: name, slug |
create_project_key | Mint an API key sandboxed to a project - it can only see and act on that project's inboxes. The key is returned once. Use this to give each tenant of your platform an isolated key. Inputs: project_id, name |
create_routing_rule | Create an auto-routing rule that assigns agents to threads based on email properties (sender, subject, category). Inputs: name, conditions, target_agent_id, target_inbox_id, priority |
create_webhook | Register a webhook URL to receive real-time notifications when emails arrive. Inputs: url, events |
delete_agent_tool | Delete a registered external HTTP tool. Inputs: tool_id |
delete_contact_list | Delete a contact list. Contacts are unlinked but not deleted. Inputs: list_id |
delete_credential | Permanently delete a stored credential from the vault. Inputs: credential_id |
delete_inbox | Delete an inbox and all its emails permanently. Inputs: inbox_id |
delete_project | Delete a project. Its inboxes detach to the org root (not deleted); project-scoped keys are revoked. Inputs: project_id |
delete_routing_rule | Delete a routing rule. Inputs: rule_id |
delete_webhook, end_meeting, forward_email, get_agent_task, get_ai_config, get_context, get_inbox, get_list_entry, get_meeting_transcript, get_metrics, get_otp, get_thread, get_totp_code, join_meeting, kb_search, list_agent_actions, list_agent_tasks, list_agent_tools, list_contact_lists, list_contacts, list_credentials, list_domains, list_drafts, list_emails, list_entries, list_inboxes, list_knowledge, list_projects, list_routing_rules, list_smtp_configs, list_thread_agents, list_threads, list_webhooks, login_with_credential, mark_email_spam, pause_inbox, read_email, reject_draft, remove_contact, remove_email_labels, remove_list_entry, reply_to_email, resume_inbox, search_emails, send_bulk_email, send_email, send_marketing_email, set_auto_reply, set_domain_catch_all, set_list_mode, skill_login_with_email, skill_signup_with_email, skill_verify_email, store_credential, test_smtp_config, test_webhook, unassign_thread, unmark_email_spam, update_inbox, update_thread, use_credential_in_browser, verify_domain, wait_for_email
Every block below points at https://mcp.lumbox.co/mcp. Pick your client and copy.
claude mcp add --transport http lumbox-co https://mcp.lumbox.co/mcp
{
"mcpServers": {
"lumbox-co": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.lumbox.co/mcp"]
}
}
}{
"mcpServers": {
"lumbox-co": {
"url": "https://mcp.lumbox.co/mcp"
}
}
}{
"servers": {
"lumbox-co": {
"type": "http",
"url": "https://mcp.lumbox.co/mcp"
}
}
}{
"context_servers": {
"lumbox-co": {
"url": "https://mcp.lumbox.co/mcp"
}
}
}{
"mcpServers": {
"lumbox-co": {
"serverUrl": "https://mcp.lumbox.co/mcp"
}
}
}{
"mcpServers": {
"lumbox-co": {
"url": "https://mcp.lumbox.co/mcp"
}
}
}name: lumbox.co
version: 0.0.1
schema: v1
mcpServers:
- name: lumbox.co
type: streamable-http
url: https://mcp.lumbox.co/mcp{
"mcpServers": {
"lumbox-co": {
"httpUrl": "https://mcp.lumbox.co/mcp"
}
}
}{
"mcpServers": {
"lumbox-co": {
"type": "http",
"url": "https://mcp.lumbox.co/mcp"
}
}
}{
"mcpServers": {
"lumbox-co": {
"url": "https://mcp.lumbox.co/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.lumbox.co%2Fmcp&type=streamable_http&id=lumbox-co&name=lumbox.co
It answered our last check on 25 October 2026 in 154 ms. Over 11 checks since 4 September 2026 it answered 11. Status here comes from Neuronto's own probes, not from the publisher.
103, as returned by the server's own tools/list on 1 September 2026: add_contacts, add_domain, add_email_labels, add_knowledge, add_list_entry, approve_draft, ask_email, ask_emails, and 95 more.
It answered our last check on 25 October 2026 in 154 ms. Over 11 checks since 4 September 2026 it answered 11.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.lumbox.co/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ora.ai. Endpoint host: mcp.lumbox.co. ARD identifier: urn:air:ora.ai:mcp:lumbox.co-mcp-0.
First indexed 1 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.