Tpscheck for AI agents
TPSCheck verifies whether a UK phone number is registered on the Telephone Preference Service, used by marketing and sales teams to stay compliant before calling. 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 Tpscheck.
Check a number against the TPS list
Look up whether a number is registered with the TPS or CTPS before it's called.
Screen a calling list before a campaign
Check each number on an outbound list, a read-only compliance check.
Confirm before removing flagged numbers
Review numbers flagged as registered with a person before they're dropped from a calling list.
1 Tpscheck actions, graded by risk.
Every Tpscheck action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- tpscheck.check_phone_numberCheck Phone Number (TPS/CTPS)
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Tpscheck in three steps.
- 01Your users connect TpscheckThey add their Tpscheck api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Tpscheck through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('tpscheck', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Tpscheck connects.
Users add their Tpscheck 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 Tpscheck 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 Tpscheck from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Tpscheck and Arc0, answered.
Can I use Tpscheck with Claude, ChatGPT or Cursor?
Yes. Connect Tpscheck 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 Tpscheck actions you allow.
How do users connect Tpscheck?
Users add their Tpscheck 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 Tpscheck actions can my agent take?
1 in total: 1 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Tpscheck?
Yes. Allow read actions and deny writes in the Tpscheck policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Tpscheck too?
Yes. The same Tpscheck connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Tpscheck into your agent.
Your users connect Tpscheck once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan