# ORDan (npm · ordan-mcp)

ORDan's MCP server: calls, SMS and phone numbers for AI agents, under their owner's spend controls

- Trust score: 56/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `ordan-mcp`: 56/100 (this document), [markdown](https://verifymcp.io/servers/joshluberisse-ordan/ordan-mcp.md), [page](https://verifymcp.io/servers/joshluberisse-ordan/ordan-mcp)

## Channel facts

- Registry: `npm`
- Package: `ordan-mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 6/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (UNLICENSED) isn't a recognized OSI-approved license.
  - Actively maintained (last published 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2042 tokens (~81/item across 25 items; 25 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 92/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 75% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ORDan MCP server?

ORDan runs locally as an npm package, launched with npx -y ordan-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add joshluberisse-ordan -- npx -y ordan-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "joshluberisse-ordan": {
      "command": "npx",
      "args": [
        "-y",
        "ordan-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "joshluberisse-ordan": {
      "command": "npx",
      "args": [
        "-y",
        "ordan-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add joshluberisse-ordan -- npx -y ordan-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "joshluberisse-ordan": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "ordan-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add joshluberisse-ordan --command npx --arg -y --arg ordan-mcp
```

### Hermes

```yaml
mcp_servers:
  joshluberisse-ordan:
    command: "npx"
    args: ["-y", "ordan-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "joshluberisse-ordan": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "ordan-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add joshluberisse-ordan -t stdio -c npx -a -y ordan-mcp
```

### Other

```json
{
  "mcpServers": {
    "joshluberisse-ordan": {
      "command": "npx",
      "args": [
        "-y",
        "ordan-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 56, +3)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] First check of Schema quality: unverified
- [functional] Destructive annotations: All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
- [functional] Package version: 0.1.2 → 0.1.3

### 2026-11-03 (score 53)

First indexed and scored.

## MCP tools (25)

### `ordan.agent.create` (~113 tokens)

Pair with your owner

Register a persistent agent principal. Asks your owner to approve you on ORDan: returns a pairing URL and code for the human. Once approved, this runtime holds your credential (you never see it) and the other ordan.* tools work.

Input parameters:

- `capabilities` (array): Requested capabilities; your owner approves or denies the request as asked
- `monthly_limit_cents` (integer): Requested monthly spend ceiling in cents
- `name` (string, required): Human-readable agent name, e.g. 'Executive Assistant'

### `ordan.agent.status` (~24 tokens)

Connection status

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

### `ordan.line.provision` (~103 tokens)

Get a new Line

Provision a phone identity for an agent: a new Line with its own number, bound to you.

Input parameters:

- `approval` (string): Approved apr_… when provisioning required approval
- `area_code` (string): Preferred US area code, e.g. 212
- `country` (string): ORDan offers US numbers only
- `idempotency_key` (string): Stable key for retrying this exact logical operation
- `name` (string)

### `ordan.line.list` (~21 tokens)

List your Lines

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

### `ordan.line.update` (~78 tokens)

Update a Line

Rename a Line, or set its monthly spend ceiling in cents (spend ceilings are an owner/key decision — an agent credential can only rename).

Input parameters:

- `line` (string, required): line_… id
- `name` (string): New name for the Line
- `spend_limit_cents`: Monthly ceiling in cents; null removes it

### `ordan.line.release` (~34 tokens)

Release a Line

Release one of your Lines and its number (requires numbers.release).

Input parameters:

- `line` (string, required): line_… id

### `ordan.number.list` (~63 tokens)

List your numbers

List your numbers, each with the Line it is attached to: those on your Lines, and any you bought that are not on a Line (requires numbers.provision or numbers.release). Use it to find a number that was bought but not attached to a Line.

### `ordan.number.release` (~59 tokens)

Release a number

Release a number you bought that is not in use on a Line back to the carrier (requires numbers.release). A number on a Line goes with its Line: use ordan.line.release.

Input parameters:

- `number` (string, required): num_… id

### `ordan.call.create` (~191 tokens)

Place a call

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.

Input parameters:

- `approval` (string): apr_… id of an approved request, when retrying
- `category` (string)
- `idempotency_key` (string): Reuse for an identical request after a timeout; adding approval needs a new key
- `line` (string): line_… id, when you have several
- `max_duration_seconds` (integer)
- `objective` (string): What the call should achieve
- `purpose` (string): Why this call is happening (audited)
- `to` (string, required): Destination in E.164, e.g. +12125550123

### `ordan.call.status` (~26 tokens)

Call status

Poll live call state.

Input parameters:

- `call` (string, required): call_… id

### `ordan.call.transfer` (~135 tokens)

Transfer a call

Hand off to a human, mid-call: transfer an in-progress call (policy-checked). If the destination needs your owner's approval, the error carries details.approval_request (apr_…): retry with `approval` once they approve.

Input parameters:

- `approval` (string): apr_… id of an approved request, when retrying
- `call` (string, required): call_… id
- `category` (string)
- `idempotency_key` (string)
- `purpose` (string): What it is for, e.g. escalation
- `to` (string, required): E.164 to transfer to

### `ordan.call.list` (~45 tokens)

List your calls

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

Input parameters:

- `line` (string): line_… id
- `status` (string)

### `ordan.call.answer` (~40 tokens)

Answer a call

Answer a ringing inbound call routed to you (decline with ordan.call.hangup).

Input parameters:

- `call` (string, required): call_… id

### `ordan.call.hangup` (~28 tokens)

Hang up

Hang up a call.

Input parameters:

- `call` (string, required): call_… id

### `ordan.call.dtmf` (~107 tokens)

Press keys on a call

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.

Input parameters:

- `call` (string, required): call_… id
- `digits` (string, required): Keys to press: 0-9 * # A-D, w/W to pause
- `sensitive` (boolean)

### `ordan.call.record` (~57 tokens)

Record a call

Start or stop recording a connected call (requires calls.record). Recordings belong to your owner: you see that one exists, not its audio.

Input parameters:

- `action` (string, required)
- `call` (string, required): call_… id

### `ordan.call.report` (~135 tokens)

Report a call's outcome

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.

Input parameters:

- `call` (string, required): call_… id
- `fields` (object): Details of the outcome, e.g. { date, time }
- `outcome` (string): What came of it, as a slug: e.g. appointment_rescheduled
- `summary` (string)
- `transcript` (array): The conversation, turn by turn

### `ordan.sms.send` (~144 tokens)

Send an SMS

Send a message from the agent's line. With several Lines, pass `line`. Approval works as for ordan.call.create.

Input parameters:

- `approval` (string): apr_… id of an approved request, when retrying
- `body` (string, required)
- `category` (string)
- `idempotency_key` (string)
- `line` (string): line_… id, when you have several
- `purpose` (string): What it is for, e.g. scheduling
- `smart_encoding` (boolean): Explicit opt-in for typographic ASCII substitutions; emoji/unknown Unicode is preserved
- `to` (string, required): E.164

### `ordan.sms.read` (~53 tokens)

Read your messages

Read your messages: replies and what you sent. Pass `with` for the whole conversation with one number.

Input parameters:

- `direction` (string)
- `with` (string): E.164 of the other party

### `ordan.policy.check` (~205 tokens)

Check an action against policy

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).

Input parameters:

- `action` (string, required)
- `amount_cents` (integer): purchases: what it would cost, in cents
- `body` (string): sms.send: message content for a segment/cost estimate
- `call` (string): call_… id: the call to hand off (required for calls.transfer)
- `category` (string)
- `line` (string): line_… id the action would use (default: your only Line)
- `merchant` (string): purchases: who you would buy from
- `purpose` (string): What it is for, e.g. scheduling
- `smart_encoding` (boolean)
- `to` (string): E.164

### `ordan.purchase.authorize` (~190 tokens)

Authorize a purchase

Ask before you buy: authorize a purchase on your owner's behalf (requires purchases). Within policy (by default up to $50 each) it is authorized at once; above it your owner approves first (retry with `approval`). ORDan never sees card data: pay the merchant yourself, then call ordan.purchase.complete with what was charged.

Input parameters:

- `amount_cents` (integer, required): The most it will cost, in cents (USD)
- `approval` (string): apr_… id of an approved request, when retrying
- `category` (string): The policy category it falls under (e.g. travel, medical); your owner's rules may block or require approval by category
- `description` (string, required): What you are buying and why
- `merchant` (string, required)
- `purpose` (string): What it is for; classifies the purchase only when no category is given

### `ordan.purchase.complete` (~66 tokens)

Complete a purchase

Record that you made an authorized purchase: what was actually charged (never more than authorized) and the merchant's confirmation number.

Input parameters:

- `amount_cents` (integer, required)
- `purchase` (string, required): pur_… id
- `receipt` (string): Order or confirmation number

### `ordan.purchase.cancel` (~30 tokens)

Cancel a purchase

Give back an authorization you will not use.

Input parameters:

- `purchase` (string, required): pur_… id

### `ordan.usage.get` (~19 tokens)

Usage this month

Read spend against limits for this month.

### `ordan.ledger.read` (~76 tokens)

Read your ledger

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

Input parameters:

- `limit` (integer)
- `since` (string): evt_… cursor: only events after it
- `types` (string): Comma-separated event types, e.g. call.completed,message.received

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/joshluberisse-ordan/ordan-mcp#diagnostics

## Score history

- 2026-11-05: 56
- 2026-11-04: 56
- 2026-11-03: 53

## Common questions

### What is the ORDan MCP server?

ORDan is an MCP server listed in the public MCP registry as io.github.joshluberisse/ordan. ORDan's MCP server: calls, SMS and phone numbers for AI agents, under their owner's spend controls. This page covers its npm package (ordan-mcp).

### Is the ORDan MCP server safe to use?

ORDan scores 56 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ORDan MCP server expose?

ORDan exposes 25 tools: ordan.agent.create, ordan.agent.status, ordan.line.provision, ordan.line.list, ordan.line.update, and 20 more. Their descriptions and schemas cost roughly 2,042 tokens of context every time the server is loaded.

### Is the ORDan MCP server still maintained?

ORDan is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the ORDan MCP server under?

ORDan declares the UNLICENSED licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/ordan-mcp
- Socket report: https://socket.dev/npm/package/ordan-mcp
- Website: https://ordan.io/
- Changelog RSS feed: https://verifymcp.io/servers/joshluberisse-ordan/ordan-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/joshluberisse-ordan/ordan-mcp.json
- HTML version of this page: https://verifymcp.io/servers/joshluberisse-ordan/ordan-mcp