your coding agent can call you when it gets stuck

how it works

1. 1
   call_me

   rings your locally verified number. no destination input.

2. 2
   you answer

   give direction; hear it read back.

3. 3
   result

   a spoken CONFIRMED after the read-back becomes final_instruction. anything else stays advisory.

the whole surface: 6 tools

• call_me(message, mode?, context?, after_hours_confirmation?, max_duration_seconds?, wait?)

  rings your verified number when your agent needs you. voice only.

• lookup_business(name, location?, phone_number?, utc_offset_minutes?)

  finds the business, mints the dial token make_call requires.

• make_call(dial_token, objective, caller_name, context?, behavior?, greet_first?, after_hours_confirmation?, max_duration_seconds?, wait?)

  the disclosed call, via dial token. returns OUTCOME + transcript.

• call_number(phone_number, objective, caller_name, recipient_name?, context?, behavior?, greet_first?, utc_offset_minutes?, after_hours_confirmation?, max_duration_seconds?, wait?)

  disclosed call to a number you already have.

• get_call(call_id)

  re-check a call by id. never dials.

• check_call_readiness()

  preflight: auth, credits, caller ID. never dials.

every call says it's an AI. no exceptions

enforced server-side - an open npm package can't patch around them.

• owner destination is not an input

  call_me accepts no destination - it dials the owner number verified by one real, disclosed voice-OTP call (NANP +1 numbers today). the person who answers is still not identity-verified, so replies stay untrusted data. every ordinary rail applies; local verification relaxes nothing.

• AI disclosure, composed server-side

  every call opens with "Hi, I'm <name>'s AI assistant..." - built into the opener server-side, not a prompt suggestion. it answers truthfully if asked "are you a robot".

• signed dial tokens

  HMAC-SHA256, account-bound, 15-minute TTL. lookup_business mints them; make_call requires them. raw numbers are rejected on the verified path.

• business-line verification

  on the lookup path, dial tokens only mint for carrier-verified business lines.

• per-number rate caps

  3 calls per hour, 8 per day to the same number. the rejection tells you when the window reopens.

• do-not-call list with auto opt-out

  "stop calling" / "take me off your list" in a callee turn is detected and the number is suppressed automatically. manage it with speko dnc.

• after-hours gate

  calls outside 08:00-21:00 destination-local require typed confirmation - the server records it but cannot attribute it to a speaker, so clients pass the human's own words, never invent them. collection-flavored calls are day-hours-only, no override.

• no-sell, no-spam, no-impersonation

  selling, promotion, surveys, fundraising, campaigning, harassment, and pretending to be someone else are screened on objective, behavior, AND context - blocked intent can't be smuggled sideways.

• hard number blocks

  emergency and premium-rate numbers can never be dialed. no opt-in exists.

• honest failure states

  a call the platform never put on the wire returns not_connected - never a fake success. transcripts and outcomes are returned when captured; no result is ever invented.

they let agents spend money and dial humans blind; we report what happened, what it cost, and refuse the calls that shouldn't happen.

one server. your client

{
  "mcpServers": {
    "speko-calls": {
      "command": "npx",
      "args": ["-y", "@spekoai/mcp-calls@latest"],
      "env": {
        "SPEKO_API_KEY": "${SPEKO_API_KEY}",
        "SPEKO_CLIENT_PROFILE": "claude-code"
      }
    }
  }
}

{
  "mcpServers": {
    "speko-calls": {
      "command": "npx",
      "args": ["-y", "@spekoai/mcp-calls@latest"],
      "env": {
        "SPEKO_API_KEY": "sk_...",
        "SPEKO_CLIENT_PROFILE": "safe-default"
      }
    }
  }
}

any stdio MCP client works. api keys at platform.speko.dev.

faq