TrueList for AI agents
TrueList validates email addresses in bulk, used by marketing and sales teams that want to remove invalid emails before a campaign sends. 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 TrueList.
Validate a single email address
Check whether an email address is valid and deliverable before sending to it.
Create a batch validation job
Submit a list of email addresses for bulk validation in one batch job.
Confirm before deleting a batch
Check with the user before deleting a completed validation batch, since its results go with it.
8 TrueList actions, graded by risk.
Every TrueList action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- truelist.get_batchGet Batch
- truelist.get_accountGet Account
- truelist.list_batchesList Batches
- truelist.list_validation_historyList Validation History
- truelist.estimate_batchEstimate Batch
- truelist.validate_emailValidate Email
write
1Create and change things. Allow, or ask the user first.
- truelist.create_batchCreate Batch
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- truelist.delete_batchDelete Batch
TrueList in three steps.
- 01Your users connect TrueListThey add their TrueList api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Batch” can wait for the user, and “delete Batch” can be denied outright.
- 03Any agent can actYour agent calls TrueList through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('truelist', { read: 'allow', write: 'ask', // create_batch destructive: 'deny', // delete_batch }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How TrueList connects.
Users add their TrueList 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 TrueList 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 TrueList from any agent.
TrueList and Arc0, answered.
Can I use TrueList with Claude, ChatGPT or Cursor?
Yes. Connect TrueList 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 TrueList actions you allow.
How do users connect TrueList?
Users add their TrueList 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 TrueList actions can my agent take?
8 in total: 6 read, 1 write and 1 destructive, such as “create Batch”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in TrueList?
Yes. Actions like “delete Batch” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call TrueList too?
Yes. The same TrueList connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug TrueList into your agent.
Your users connect TrueList once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan