# Assistable (remote · api.assistable.ai)

Give any AI agent a phone: make and answer calls, get through phone menus, and send texts.

- Trust score: 60/100 (medium)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.assistable.ai`: 60/100 (this document), [markdown](https://verifymcp.io/servers/ai-assistable-assistable/api.md), [page](https://verifymcp.io/servers/ai-assistable-assistable/api)

## Channel facts

- Endpoint: `https://api.assistable.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (assistants_archive).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1336 tokens (~83/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 15/100
  - Stability check failed: schema churn in the 8 days we've observed: 2 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 69/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 8% 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 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 17 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 Assistable MCP server?

Assistable is a hosted endpoint at https://api.assistable.ai/mcp, so there is nothing to install locally. 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 --transport http ai-assistable-assistable 'https://api.assistable.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-assistable-assistable": {
      "url": "https://api.assistable.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-assistable-assistable": {
      "type": "http",
      "url": "https://api.assistable.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-assistable-assistable]
url = "https://api.assistable.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-assistable-assistable": {
      "type": "remote",
      "url": "https://api.assistable.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-assistable-assistable --url 'https://api.assistable.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-assistable-assistable:
    url: "https://api.assistable.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-assistable-assistable": {
      "Transport": "http",
      "Url": "https://api.assistable.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-assistable-assistable -t streamable-http -u 'https://api.assistable.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-assistable-assistable": {
      "type": "http",
      "url": "https://api.assistable.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 8 to 12.

### 2026-11-01 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 2.

### 2026-10-30 (score 58, −2)

- [security regression] Stability: 0.03 → fail
- [security regression] A breaking change shipped without a version bump: still 0.4.0
- [security regression] Tool “assistable_connect” was removed
- [security regression] Tool “assistable_connect_finish” was removed
- [security regression] Tool “assistable_signup” was removed
- [security regression] Tool “assistable_signup_finish” was removed
- [functional regression] Tool coverage: 23% → 8%
- [functional improvement] Schema quality: 95 → 83

### 2026-10-29 (score 60, +1)

- [functional regression] Schema quality: 85 → 95
- [functional improvement] Tool coverage: 11% → 23%
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “assistable_signup”
- [functional] New tool “assistable_signup_finish”

### 2026-10-28 (score 59)

First indexed and scored.

## MCP tools (16)

### `search_tools` (~93 tokens)

Search Assistable's registered MCP tools by the task the user wants to do. Returns up to 5 exact tool definitions with JSON input schemas and annotations. Use this first when you need to choose a tool; the result is not authorization to call it.

Input parameters:

- `limit` (integer): How many matching tools to return. Defaults to 5.
- `query` (string, required): A short description of the task or capability needed.

### `assistants_list` (~71 tokens)

List assistants in a subaccount (excludes archived by default). Note: voice_settings and platform_tools are returned only by assistants_get, not in the list.

Input parameters:

- `cursor` (string)
- `includeArchived` (boolean)
- `limit` (integer)
- `subAccountId` (string, required)

### `assistants_get` (~51 tokens)

Fetch an assistant's full configuration by ID. The response includes voice_settings (greeting mode, opening messages, voicemail) and platform_tools (attached platform-catalog tool names).

Input parameters:

- `assistantId` (string, required)

### `assistants_create` (~236 tokens)

Create an assistant. Required: subAccountId, name. Optional config blocks (llmConfig, voiceConfig, chatConfig) mirror the dashboard create dialog. voice_settings configures call greeting mode, opening messages, and voicemail behavior; platform_tools attaches platform-catalog tools (declarative full-replace — see the field description).

Input parameters:

- `assistantType` (string)
- `chatConfig` (object)
- `description` (string)
- `llmConfig` (object)
- `name` (string, required)
- `platform_tools` (array): Platform tool names to attach, e.g. ["book_appointment", "send_email"]. Declarative within the platform catalog: tools in the list are attached, catalog tools missing from the list are detached, cust…
- `subAccountId` (string, required)
- `voiceConfig` (object)
- `voiceId`
- `voice_settings` (object)

### `assistants_update` (~213 tokens)

Patch an assistant. Only supplied fields change; nested config blocks are upserted. voice_settings updates call greeting mode, opening messages, and voicemail behavior; platform_tools declaratively replaces the attached platform-catalog tools (an empty array detaches all — see the field description).

Input parameters:

- `assistantId` (string, required)
- `chatConfig` (object)
- `description`
- `llmConfig` (object)
- `name` (string)
- `platform_tools` (array): Platform tool names to attach, e.g. ["book_appointment", "send_email"]. Declarative within the platform catalog: tools in the list are attached, catalog tools missing from the list are detached, cust…
- `voiceConfig` (object)
- `voiceId`
- `voice_settings` (object)

### `assistants_archive` (~24 tokens)

Archive (soft-delete) an assistant.

Input parameters:

- `assistantId` (string, required)

### `tools_list` (~65 tokens)

List tools visible to a subaccount. Pass includePrebuilt=false for only custom tools.

Input parameters:

- `cursor` (string)
- `includePrebuilt` (boolean)
- `limit` (integer)
- `search` (string)
- `subAccountId` (string, required)

### `tools_get` (~23 tokens)

Fetch a tool's full configuration.

Input parameters:

- `toolId` (string, required)

### `tools_create_custom` (~93 tokens)

Create a custom tool (toolType=CUSTOM). Name must match /^[a-zA-Z0-9_-]+$/ and be unique in the subaccount.

Input parameters:

- `description` (string)
- `headers` (object)
- `httpMethod` (string)
- `name` (string, required)
- `parameters` (array)
- `subAccountId` (string, required)
- `url` (string)

### `tools_update` (~70 tokens)

Patch a custom tool. Supplying parameters/headers replaces those rows; omit to leave them.

Input parameters:

- `description`
- `headers`
- `httpMethod` (string)
- `name` (string)
- `parameters`
- `toolId` (string, required)
- `url`

### `tools_delete` (~22 tokens)

Soft-delete a custom tool.

Input parameters:

- `toolId` (string, required)

### `contacts_list` (~65 tokens)

List contacts in a subaccount. meta.total is the number of matching contacts, so use it to answer how many contacts there are.

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `search` (string)
- `subAccountId` (string, required)

### `contacts_get` (~22 tokens)

Fetch a contact by ID.

Input parameters:

- `contactId` (string, required)

### `conversations_list` (~38 tokens)

List conversations in a subaccount.

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `subAccountId` (string, required)

### `appointments_list` (~59 tokens)

List appointments in a subaccount within an optional date range.

Input parameters:

- `cursor` (string)
- `endDate` (string)
- `limit` (integer)
- `startDate` (string)
- `subAccountId` (string, required)

### `calls_get` (~42 tokens)

Fetch a call (status, recording, transcript) by ID.

Input parameters:

- `callId` (string): Legacy alias for call_id.
- `call_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-assistable-assistable/api#diagnostics

## Score history

- 2026-11-05: 60
- 2026-11-04: 60
- 2026-11-03: 59
- 2026-11-02: 59
- 2026-11-01: 59
- 2026-10-31: 58
- 2026-10-30: 58
- 2026-10-29: 60
- 2026-10-28: 59

## Common questions

### What is the Assistable MCP server?

Assistable is an MCP server listed in the public MCP registry as ai.assistable/assistable. Give any AI agent a phone: make and answer calls, get through phone menus, and send texts. This page covers its hosted endpoint (https://api.assistable.ai/mcp).

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

Assistable scores 60 out of 100 on VerifyMCP. 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 Assistable MCP server expose?

Assistable exposes 16 tools: search_tools, assistants_list, assistants_get, assistants_create, assistants_update, and 11 more. Their descriptions and schemas cost roughly 1,187 tokens of context every time the server is loaded.

### Does the Assistable MCP server require authentication?

No. We connected to Assistable without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Assistable MCP server still maintained?

Assistable 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.

## Links

- Remote endpoint: https://api.assistable.ai/mcp
- Website: https://docs.assistable.ai/v3/agent-phone
- Changelog RSS feed: https://verifymcp.io/servers/ai-assistable-assistable/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-assistable-assistable/api.json
- HTML version of this page: https://verifymcp.io/servers/ai-assistable-assistable/api