MXToolbox for AI agents
MXToolbox provides network diagnostic and monitoring tools, including DNS lookups, blacklist checks, and email deliverability analysis for IT and email teams. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in MXToolbox.
Check a domain's DNS records
Look up a domain's MX or SPF records before troubleshooting mail delivery, read-only.
Check blacklist status
Check whether a sending IP or domain appears on a spam blacklist.
Monitor a domain's health
Check the current monitor status for a domain to confirm nothing has broken.
13 MXToolbox actions, graded by risk.
Every MXToolbox action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
12Look things up. Allowed by default.
- mxtoolbox.lookup_mxLookup MX Records
- mxtoolbox.lookup_dnsLookup DNS Records
- mxtoolbox.lookup_spfLookup SPF Record
- mxtoolbox.lookup_dkimLookup DKIM Record
- mxtoolbox.lookup_httpHTTP Lookup
- mxtoolbox.lookup_pingPing Lookup
- mxtoolbox.lookup_smtpSMTP Lookup
- mxtoolbox.lookup_dmarcLookup DMARC Record
- mxtoolbox.monitor_statusMonitor Status
- mxtoolbox.lookup_blacklistLookup Blacklist
- mxtoolbox.lookup_bimi_recordLookup BIMI Record
- mxtoolbox.lookup_mta_sts_recordLookup MTA-STS Record
write
1Create and change things. Allow, or ask the user first.
- mxtoolbox.usage_checkCheck Usage
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
MXToolbox in three steps.
- 01Your users connect MXToolboxThey add their MXToolbox api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “check Usage” can wait for the user to approve.
- 03Any agent can actYour agent calls MXToolbox through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mxtoolbox', { read: 'allow', write: 'ask', // usage_check destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How MXToolbox connects.
Users add their MXToolbox api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same MXToolbox connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use MXToolbox from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
MXToolbox and Arc0, answered.
Can I use MXToolbox with Claude, ChatGPT or Cursor?
Yes. Connect MXToolbox to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the MXToolbox actions you allow.
How do users connect MXToolbox?
Users add their MXToolbox api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which MXToolbox actions can my agent take?
13 in total: 12 read, 1 write and 0 destructive, such as “check Usage”. Your policies decide which of them each agent may call.
Can I make my agent read-only in MXToolbox?
Yes. Allow read actions and deny writes in the MXToolbox policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call MXToolbox too?
Yes. The same MXToolbox connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug MXToolbox into your agent.
Your users connect MXToolbox once, under your brand. Your agent gets 13 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan