MCP App Store
by KeenEthics
ORDan icon

ORDan MCP Server for Claude and ChatGPT

By Neuromorph Systems, LLC

Overview

ORDan connects Claude to the account-specific communications oversight layer for AI agents. Once authorized, Claude can check an ORDan agent's granted permissions, list available communications Lines, inspect monthly usage and spending, review recent audit events and ledger charges, and evaluate a proposed communication against an organization's existing policy without executing it. This initial connector is read-only. It does not place phone calls, send SMS messages, provision phone numbers, purchase services, modify policies, or change account permissions. Policy checks are simulations: no call is initiated and no message is delivered. ORDan uses OAuth account linking and organization-level agent grants. Account owners and administrators review permissions during authorization and can revoke access through the ORDan console. An ORDan account and authorized organization are required. Available information depends on configured Lines and existing account activity.

How to connect

  1. Claude: Open the ORDan listing in the Claude connectors directory and choose Connect. Claude listing ORDan exposes 5 tools here.
  2. ChatGPT: Open the ORDan listing in the ChatGPT app directory and choose Connect. ChatGPT listing ORDan exposes 14 tools here.

Tools

ordan.agent.status

ChatGPT
Whether your owner has approved you yet, and what you may do.

ordan.call.create

ChatGPT
Place a policy-checked outbound call. If you have one Line it is used; with several, pass line. If policy needs a human, the error carries details.approval_request (apr_…): retry with approval set to it once your owner approves. On a Line with ORDan voice on, ORDan speaks a fixed opening when the call is answered (who is calling, for whom, the callback number, that the voice is automated); then you hold the conversation with ordan.call.listen and ordan.call.speak. The first such call to a number waits for your owner to confirm the person agreed to calls in an automated voice.

ordan.call.dtmf

ChatGPT
Navigate a phone menu: press keys (DTMF) on a connected call you hold, e.g. "1" or "2w123#" (w = half-second pause). Set sensitive for PINs or account numbers: your owner's ledger shows them masked.

ordan.call.hangup

ChatGPT
Hang up a call.

ordan.call.list

ChatGPT
List your recent calls. status=ringing shows inbound calls waiting to be answered.

ordan.call.listen

ChatGPT
ORDan voice: the call's live transcript after after (a seq; 0 from the start), waiting up to wait seconds (default 10) for something new while the call is live. Each segment has a role (human: the other party; agent: what ORDan said for you, including its opening), text, is_final and seq. Pass the returned next as after to keep listening. A final human segment usually means they finished speaking: answer with ordan.call.speak. The status says when the call is over.

ordan.call.report

ChatGPT
Report what happened on a call you made or answered: its transcript and/or its structured outcome (e.g. outcome: appointment_rescheduled, fields: { date, time }). Each is recorded once, in your ledger; ORDan adds the call's measured duration.

ordan.call.speak

ChatGPT
ORDan voice: say this text on a connected call, in your Line's voice, exactly as written. It is queued behind anything still being said; interrupt: true stops that and says this instead. If the other party talks over it, ORDan stops (the transcript shows it). Follow what they say with ordan.call.listen. Fails with conflict while ORDan is still speaking its opening (retry in a moment) or when the Line's ORDan voice is off.

ordan.call.speak.stop

ChatGPT
ORDan voice: stop what is being said on the call now, and everything queued behind it.

ordan.call.status

ChatGPT
Poll live call state.

ordan.ledger.read

ChatGPT
Read the agent's event history: what happened (calls, texts, approvals) and what it cost.

ordan.line.list

ChatGPT
List your Lines, with each one's spend this month.

ordan.policy.check

ChatGPT
Evaluate an action before execution: would policy allow it right now? The action is the capability it uses: voice.outbound (a call), sms.send (a text), calls.transfer (a hand-off) or purchases (a purchase: pass merchant and amount_cents).

ordan.usage.get

ChatGPT
Read spend against limits for this month.

ordan.agent.status

Claude

ordan.ledger.read

Claude

ordan.line.list

Claude

ordan.policy.check

Claude

ordan.usage.get

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/ordan"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/ordan)