# io.github.anima-labs-ai/anima (remote · mcp.useanima.sh)

Give your AI agent an identity it owns: email inbox, US phone number, SMS, voice, and a vault.

- Trust score: 36/100 (low)
- Change this week: −46
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `mcp.useanima.sh`: 36/100 (this document), [markdown](https://verifymcp.io/servers/anima-labs-ai-anima/mcp.md), [page](https://verifymcp.io/servers/anima-labs-ai-anima/mcp)

## Channel facts

- Endpoint: `https://mcp.useanima.sh/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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 2026-09-21.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
  - 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.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 0/100
  - Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- **Schema Quality & AI Usability**: 0/100
  - Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Tool Safety**: 0/100
  - Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- **Capabilities**: 0/100
  - Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.

**Unverified: 6 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the io.github.anima-labs-ai/anima MCP server?

io.github.anima-labs-ai/anima is a hosted endpoint at https://mcp.useanima.sh/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 anima-labs-ai-anima 'https://mcp.useanima.sh/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "anima-labs-ai-anima": {
      "url": "https://mcp.useanima.sh/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "anima-labs-ai-anima": {
      "type": "http",
      "url": "https://mcp.useanima.sh/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.anima-labs-ai-anima]
url = "https://mcp.useanima.sh/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "anima-labs-ai-anima": {
      "type": "remote",
      "url": "https://mcp.useanima.sh/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add anima-labs-ai-anima --url 'https://mcp.useanima.sh/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  anima-labs-ai-anima:
    url: "https://mcp.useanima.sh/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "anima-labs-ai-anima": {
      "Transport": "http",
      "Url": "https://mcp.useanima.sh/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add anima-labs-ai-anima -t streamable-http -u 'https://mcp.useanima.sh/mcp'
```

### Other

```json
{
  "mcpServers": {
    "anima-labs-ai-anima": {
      "type": "http",
      "url": "https://mcp.useanima.sh/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.

### 2026-09-21 (score 36, −49)

- [security regression] Endpoint reachability: reachable → behind authorisation
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.40 → unverified
- [security regression] Transport: pass → unverified
- [security] Authorization: The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified

### 2026-09-20 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 80, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-09-08 (score 79, +43)

- [security improvement] Transport: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Capabilities: pass
- [functional] First check of Destructive annotations: 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Tool coverage: 100

## MCP tools (67)

### `agent_create` (~314 tokens)

Create Agent

Create a new agent with optional metadata, and optionally attach an initial address. Use this when provisioning a new sending identity or automation actor. To add more addresses later, use agent_update. Pass idempotencyKey to make retries safe — same key + same body returns the original response, same key + different body returns IDEMPOTENCY_BODY_MISMATCH 409.

Input parameters:

- `address` (object): Optional initial postal address to attach to the agent on creation. To add more addresses later, use agent_update.
- `email` (string): Optional email address to provision for this agent
- `idempotencyKey` (string): Optional Idempotency-Key. Send the SAME key on retries of the SAME create payload to guarantee exactly-once provisioning even if the network drops mid-flight. Reuse with a different body returns IDEM…
- `metadata` (object): Optional agent metadata as key-value string pairs
- `name` (string, required): Agent display name
- `provisionPhone` (boolean): Whether to auto-provision a phone number for this agent
- `slug` (string): URL-friendly unique identifier (lowercase alphanumeric + hyphens, 2-64 chars). Auto-derived from name if omitted.

### `agent_get` (~74 tokens)

Get Agent

Fetch full detail for a single agent by ID: settings, metadata, status, and the full addresses[] / emailIdentities[] / phoneIdentities[] lists. Use agent_list to browse multiple agents.

Input parameters:

- `id` (string, required): Agent ID. Returns full agent detail including addresses, emailIdentities, and phoneIdentities.

### `agent_list` (~75 tokens)

List Agents

List agents in the current account context with cursor pagination. Returns a lightweight per-agent record (addresses are NOT included to avoid N+1 round-trips). Use agent_get for full single-agent detail.

Input parameters:

- `cursor` (string): Pagination cursor from a previous list response.
- `limit` (integer): Maximum number of agents to return.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `agent_update` (~157 tokens)

Update Agent

Update an agent's name or metadata, and/or add/update/delete an address. Use addAddress to attach a new address, updateAddress to change fields on an existing one (by addressId), deleteAddressId to remove one. Multiple field-level changes can be combined in a single call.

Input parameters:

- `addAddress` (object): Attach a new postal address to this agent.
- `deleteAddressId` (string): ID of an address to remove from this agent.
- `id` (string, required): Agent ID
- `metadata` (object): Updated metadata as key-value string pairs
- `name` (string): Updated agent display name
- `updateAddress` (object): Update fields on an existing address. Pass addressId + the fields to change.

### `agent_delete` (~51 tokens)

Delete Agent

Delete an agent by ID. Use this to remove deprecated or compromised agents that should no longer send messages. Cascades to attached addresses, email identities, and phone identities.

Input parameters:

- `id` (string, required): Agent ID

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `email_send` (~360 tokens)

Send Email

Send a new outbound email from the agent mailbox. Use this when you need to compose and deliver a message with optional CC, threading headers.

Input parameters:

- `agentId` (string, required): Agent ID sending the email.
- `attachments` (array): Optional file attachments (max 20 entries, 25MB total). Each entry must provide either `content` (base64-inline) or `url` (public URL for server-fetch). Use `contentId` for inline images referenced i…
- `bcc` (array): Optional BCC recipient email addresses.
- `body` (string, required): Plain-text body content for the email.
- `bodyHtml` (string): Optional HTML body content for rich email formatting.
- `cc` (array): Optional CC recipient email addresses.
- `fromIdentityId` (string): Optional EmailIdentity ID to send from. Must belong to this agent and be verified. If omitted, the agent's primary identity is used. Use this to route different message types through different identi…
- `headers` (object): Optional custom email headers as key-value pairs (e.g. {"X-Campaign": "onboarding"}). Merged with Anima's own threading/compliance headers, which win on conflict.
- `inReplyTo` (string): Optional message ID to set the In-Reply-To header for threading.
- `references` (array): Optional list of message IDs to include in the References header.
- `subject` (string, required): Subject line for the outgoing email.
- `to` (array, required): List of recipient email addresses.

Output parameters:

- `id` (string)
- `messageId` (string)
- `status` (string)

### `email_get` (~48 tokens)

Get Email

Fetch full detail for a single email by ID, including metadata and body. Use email_list to browse emails in a folder.

Input parameters:

- `id` (string, required): Email ID. Returns full metadata and body.

### `email_list` (~217 tokens)

List Emails

List emails with cursor pagination. Returns lightweight per-email records plus a `pagination` object — pass `pagination.nextCursor` back as `cursor` for the next page. Use email_get for the full body, email_search to find specific messages.

Input parameters:

- `agentId` (string): Filter emails by agent ID. Agent-scoped keys are already limited to their own agent; master keys see the whole workspace unless filtered.
- `cursor` (string): Opaque pagination cursor from a previous response's `pagination.nextCursor`. Omit for the first page.
- `includeSpam` (boolean): Include messages classified as spam on arrival. Excluded by default. Naming `spam` in `labels` also counts as asking for it.
- `labels` (array): Only return messages carrying ALL of these labels. System labels: `unread`, `read`, `archived`, `spam`. Case-insensitive. Use email_label to change them.
- `limit` (integer): Max emails to return per page (1-100, default 20).

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `email_search` (~346 tokens)

Search Emails

Search messages by content. Fulltext mode (default) substring-matches subject/body/addresses of EMAIL messages and returns `{items, pagination}` with cursor paging. Semantic mode ranks by vector-embedding similarity and returns `{results}` scored 0-1 — each result spans ANY channel (check the `channel` field) and includes the message id for email_get / email_thread_get follow-ups.

Input parameters:

- `agentId` (string): Filter results to a specific agent.
- `cursor` (string): Pagination cursor from a previous fulltext response's `pagination.nextCursor`. Fulltext mode only.
- `includeSpam` (boolean): Include messages classified as spam on arrival. Excluded by default. Naming `spam` in `labels` also counts as asking for it.
- `labels` (array): Only return messages carrying ALL of these labels. System labels: `unread`, `read`, `archived`, `spam`. Case-insensitive. Use email_label to change them.
- `limit` (integer): Max results (fulltext: 1-100, default 20; semantic: 1-50, default 10).
- `mode` (string): Search mode. `fulltext` (default) does substring matching over subject/body/addresses of EMAIL messages and supports cursor pagination. `semantic` ranks by vector-embedding similarity — better for me…
- `query` (string, required): Search query text.
- `threshold` (number): Minimum similarity score 0-1 (semantic mode only, default 0.7).

### `email_label` (~170 tokens)

Label Email

Add and/or remove labels on one message — the agent's workflow state. Use this to mark mail read/unread (`read`/`unread`), archive it (`archived`), or apply your own tags, then filter with email_list's `labels`. Supply at least one of addLabels/removeLabels. One message per call: there is no batch form.

Input parameters:

- `addLabels` (array): Labels to add. Adding `read` removes `unread` and vice versa — one state under two names, and a message always carries exactly one of them.
- `id` (string, required): ID of the message to relabel.
- `removeLabels` (array): Labels to remove. Removing `unread` marks the message read (and vice versa); a message is never left with neither.

### `email_reply` (~132 tokens)

Reply Email

Reply to an existing email thread by first loading the original message and setting threading headers. Use this when you need a proper in-thread response.

Input parameters:

- `agentId` (string, required): Agent ID sending the reply.
- `attachments` (array): Optional file attachments on the reply (max 20 entries, 25MB total).
- `html` (string): Optional HTML content for the reply body.
- `originalId` (string, required): Original email ID being replied to.
- `replyAll` (boolean): When true, include additional participants from the original email.
- `text` (string, required): Plain-text content for your reply message.

Output parameters:

- `id` (string)
- `messageId` (string)
- `status` (string)

### `email_forward` (~133 tokens)

Forward Email

Forward an existing email to another recipient by loading the original content first. Use this to share a prior message while preserving context.

Input parameters:

- `agentId` (string, required): Agent ID forwarding the email.
- `attachments` (array): Optional additional file attachments on the forward (max 20 entries, 25MB total). Original email's attachments are NOT auto-included — pass them explicitly if you want them forwarded.
- `originalId` (string, required): Original email ID being forwarded.
- `text` (string): Optional introductory text to prepend before forwarded content.
- `to` (array, required): Recipient email address(es) for the forwarded message.

Output parameters:

- `id` (string)
- `messageId` (string)
- `status` (string)

### `email_thread_get` (~133 tokens)

Get Email Thread(s)

Fetch all email messages in one or more threads. Pass `id` for a single thread or `ids` for multiple. Returns messages ordered within each thread. Uses the messages endpoint filtered by threadId + channel=EMAIL under the hood.

Input parameters:

- `agentId` (string): Optional agent scope filter (only return messages owned by this agent).
- `id` (string): Single thread ID to fetch. Pass either `id` or `ids`.
- `ids` (array): Multiple thread IDs to fetch in parallel. Pass either `id` or `ids`.
- `limit` (integer): Optional max messages per thread.

### `email_attachment_get` (~47 tokens)

Get Email Attachment

Get a temporary download URL for an email attachment. Use this when you need direct file access for preview or download.

Input parameters:

- `id` (string, required): Attachment ID. Returns a temporary download URL.

### `email_draft_create` (~230 tokens)

Create Email Draft

Create a new email draft (composed but not sent). Drafts can be incomplete — missing recipients, subject, or body. Use email_draft_send later to actually deliver, or email_draft_delete to discard.

Input parameters:

- `agentId` (string, required): Owning agent ID.
- `bcc` (array): BCC recipients.
- `body` (string): Plain-text body.
- `bodyHtml` (string): HTML body.
- `cc` (array): CC recipients.
- `fromIdentityId` (string): Optional EmailIdentity ID to send from. Must belong to this agent and be verified. If omitted, the agent's primary identity is used at send time. Discover available IDs from the `emailIdentities` arr…
- `inReplyTo` (string): Optional In-Reply-To Message-ID for threading on send.
- `metadata` (object): Arbitrary metadata.
- `references` (array): Optional References chain for threading.
- `subject` (string): Subject line.
- `to` (array): Recipient email addresses (may be empty for an incomplete draft).

### `email_draft_get` (~38 tokens)

Get Email Draft

Fetch full detail for a single draft by ID. Use email_draft_list to browse drafts.

Input parameters:

- `id` (string, required): Draft ID.

### `email_draft_list` (~78 tokens)

List Email Drafts

List email drafts with optional filters. Returns lightweight draft records — use email_draft_get for full detail.

Input parameters:

- `agentId` (string): Filter drafts by agent ID.
- `cursor` (string): Pagination cursor from a previous list response.
- `limit` (integer): Max drafts when listing. Ignored when `id` is provided.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `email_draft_send` (~60 tokens)

Send Email Draft

Send a draft. Atomically converts the draft to a delivered Message + deletes the draft row. The draft must have at least one recipient, a subject, and a body. Returns the newly-created Message.

Input parameters:

- `id` (string, required): Draft ID.

Output parameters:

- `id` (string)
- `messageId` (string)
- `status` (string)

### `email_draft_delete` (~47 tokens)

Delete Email Draft

Discard a draft. Use this to remove drafts that are no longer needed. Use email_draft_send if you want to deliver instead.

Input parameters:

- `id` (string, required): Draft ID.

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `domain_create` (~53 tokens)

Create Domain

Register a custom sending domain in the workspace so it can be configured for email traffic. Use this before DNS setup and verification.

Input parameters:

- `domain` (string, required): Domain name to add, such as mail.example.com or example.com.

### `domain_verify` (~43 tokens)

Verify Domain

Trigger a verification check for a domain after DNS records are configured. Use this to re-run DNS validation and update verification status.

Input parameters:

- `id` (string, required): Unique domain ID.

### `domain_get` (~42 tokens)

Get Domain

Fetch full detail for a single domain by ID, including verification and configuration state. Use domain_list to browse all domains.

Input parameters:

- `id` (string, required): Unique domain ID.

### `domain_list` (~32 tokens)

List Domains

List all domains connected to the current workspace. Use this to audit configured sender domains and choose one for follow-up actions.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `domain_delete` (~41 tokens)

Delete Domain

Delete a domain from the workspace when it is no longer needed. Use this to remove old or incorrect domain configurations.

Input parameters:

- `id` (string, required): Unique domain ID.

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `domain_update` (~73 tokens)

Update Domain

Update mutable configuration on a domain. Currently the only updatable field is `feedbackEnabled` — toggle SES bounce and complaint feedback processing on or off without re-verifying the domain.

Input parameters:

- `feedbackEnabled` (boolean): Enable or disable bounce + complaint feedback processing for this domain.
- `id` (string, required): Unique domain ID.

### `domain_zone_file` (~44 tokens)

Domain Zone File

Get the full DNS zone file for a domain. Use this for complete DNS export or to verify all records are correctly configured.

Input parameters:

- `id` (string, required): Unique domain ID.

### `inbox_create` (~179 tokens)

Create Inbox

Create a new email inbox (mailbox) that can receive mail immediately at its address. Choose a username and domain or let the platform generate them. Requires master key access.

Input parameters:

- `agentId` (string): Agent ID to associate with this inbox. Inbound mail to the inbox is attributed to this agent.
- `displayName` (string): Human-readable display name for the inbox (max 128 characters).
- `domain` (string): Domain for the inbox address. Uses the platform default (agents.useanima.sh) when omitted. Custom domains must already be registered and verified — see domain_list.
- `username` (string): Local part of the inbox email address (letters, numbers, dots, hyphens, underscores; normalized to lowercase; must not start/end with a dot or hyphen). A random local part is generated when omitted.

### `inbox_get` (~49 tokens)

Get Inbox

Fetch full detail for a single inbox by ID, including its email address, display name, and associated agent. Use inbox_list to browse all inboxes.

Input parameters:

- `id` (string, required): Unique inbox ID.

### `inbox_list` (~96 tokens)

List Inboxes

List inboxes in the workspace with cursor pagination and optional free-text search. Returns the address, display name, and agent association for each inbox.

Input parameters:

- `cursor` (string): Pagination cursor from a previous list response (pagination.nextCursor).
- `limit` (integer): Max inboxes to return per page (1-100, default 20).
- `query` (string): Free-text search filter matched against inbox email addresses and display names.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `inbox_update` (~124 tokens)

Update Inbox

Update the display name or agent association of an inbox. Pass null for a field to clear it (unlink the agent / remove the display name); omitted fields are left unchanged. The email address itself cannot be changed. Requires master key access.

Input parameters:

- `agentId` (string|null): Agent ID to associate with the inbox. Pass null to unlink the current agent. Omit to leave unchanged.
- `displayName`: New human-readable display name (max 128 characters). Pass null to clear it. Omit to leave unchanged.
- `id` (string, required): Unique inbox ID.

### `inbox_delete` (~47 tokens)

Delete Inbox

Permanently delete an inbox and its mailbox. Mail sent to the address after deletion bounces. This cannot be undone. Requires master key access.

Input parameters:

- `id` (string, required): Unique inbox ID.

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `phone_number_list` (~45 tokens)

List Phone Numbers

List phone numbers assigned to an agent. Each result includes status and capability flags (sms/mms/voice).

Input parameters:

- `agentId` (string, required): Agent whose phone numbers to list.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `phone_number_provision` (~137 tokens)

Provision Phone Number

Provision a new phone number from the carrier pool and assign it to an agent. Note: provisioning a number costs money on the underlying carrier; do not call speculatively. Use countryCode / areaCode / capabilities to constrain selection.

Input parameters:

- `agentId` (string, required): Agent ID to assign the provisioned phone number to.
- `areaCode` (string): Preferred area code for the phone number.
- `capabilities` (array): Optional capability list (sms, mms, voice) the number must support.
- `countryCode` (string): ISO 3166-1 alpha-2 country code for number selection (default US).

### `phone_number_release` (~68 tokens)

Release Phone Number

Release a previously provisioned phone number back to the carrier pool. Use this when cleaning up unused numbers. Released numbers cannot be recovered.

Input parameters:

- `agentId` (string, required): Agent ID that currently owns the phone number.
- `phoneNumber` (string, required): E.164 formatted phone number to release.

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `sms_get` (~48 tokens)

Get SMS

Fetch full detail for a single SMS by ID (includes its `threadId` for joining the conversation). Use sms_list to browse multiple SMS messages.

Input parameters:

- `id` (string, required): SMS message ID.

### `sms_list` (~76 tokens)

List SMS

List SMS messages with optional filters. Each result includes its `threadId` for joining the conversation. Use sms_get for full single-message detail.

Input parameters:

- `agentId` (string): Filter SMS by agent ID.
- `cursor` (string): Pagination cursor from a previous list response.
- `limit` (integer): Max SMS messages to return.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `sms_thread_list` (~121 tokens)

List SMS Threads

List SMS/MMS conversations, most recently active first. A conversation is one agent number talking to one external contact. Returns summaries (participant, last message snippet, message count) — use sms_thread_get for the full history. Optionally filter by agentId.

Input parameters:

- `agentId` (string): Filter conversations by agent ID. Omit to see threads across all agents you have access to.
- `limit` (integer): Max thread summaries to return. Defaults to 20.
- `offset` (integer): Pagination offset (skip this many threads from the start).

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `sms_thread_get` (~94 tokens)

Get SMS Thread

Get one SMS/MMS conversation with its message history, oldest first. Use sms_thread_list to find thread IDs (or take `threadId` off any SMS). For a conversation longer than `limit`, returns its most recent messages; page deeper history with sms_list.

Input parameters:

- `id` (string, required): Thread ID (use sms_thread_list to find IDs).
- `limit` (integer): Max messages to return in the thread.

### `sms_send` (~144 tokens)

Send SMS

Send an SMS to a phone number, or an MMS by passing `mediaUrls`. The agent must have a provisioned phone number. Use this for transactional texts or conversational messaging.

Input parameters:

- `agentId` (string, required): Agent ID sending the SMS. The agent must have a provisioned phone number.
- `body` (string, required): Message body. SMS character limits apply (~160 chars per segment).
- `mediaUrls` (array): Optional array of media URLs for MMS. Pass one URL for a single image/file; multiple for multi-part MMS. Carrier limits apply.
- `to` (string, required): Recipient phone number in E.164 format (e.g. +14155551234).

Output parameters:

- `id` (string)
- `messageId` (string)
- `status` (string)

### `phone_call_create` (~507 tokens)

Phone Call (Live)

Place a live phone call and have a real conversation. The tool stays open for the entire call duration. As the caller speaks, you receive live transcript chunks via progress notifications; when the caller finishes a turn (server emits isFinal: true), an elicitation prompt asks you what the agent should say next. You respond with `say` (the exact text to speak) and optional `endCallAfterSpoken: true` to hang up after the line. Returns the full transcript when the call ends. Requires the connecting MCP client to support elicitation — without it, the tool errors out immediately.

Input parameters:

- `agentConfig` (object): Opt in to the server-side conversation loop. When present (even as `{}`), the Anima API runs the LLM-backed conversation loop on each caller turn and speaks the reply — the MCP tool just records both…
- `agentId` (string): Required when the API key / OAuth grant is user-bound (no agentId in the auth context, e.g. a master key or a user-consented Anima Connect grant) — picks which of the org's agents places the call. Ig…
- `firstMessage` (string, required): Opening line the agent speaks when the call is answered. Be natural — this is what the human hears first.
- `fromNumber` (string): Optional source phone in E.164. Default: the calling agent's primary phone identity.
- `maxDurationSec` (integer): Hard cap on total call duration in seconds. Default 600 (10 min). Max 1800 (30 min).
- `silenceTimeoutSec` (integer): If no caller utterance arrives within this many seconds (measured from the last agent utterance), the call hangs up automatically. Default 30.
- `to` (string, required): Destination phone number in E.164 format.
- `voiceId` (string): Optional voice override. Use voice_list for valid IDs; the catalog is multilingual and each entry carries an audio preview.

Output parameters:

- `callId` (string|null): ID of the placed call. `null` if the call ended before the carrier assigned an ID (e.g. WS auth failure or pre-ring termination) — use `endedReason` to understand why.
- `durationSec` (number): Total call duration in seconds.
- `endedReason` (string): Why the call ended (hangup, timeout, error, etc.).
- `error` (object): Present when `endedReason` is `error` or `elicitation_unsupported` — carries the underlying code+message so callers can distinguish capability gaps from real failures.
- `latencyTurns` (array): Per-turn latency breakdown captured by the API's LatencyTracker. Each entry is a turn; the t_*_ms fields are absolute millisecond timestamps. Diff adjacent marks to compute stage durations — common o…
- `transcript` (array): Full transcript with role labels in chronological order.

### `phone_call_list` (~108 tokens)

List Phone Calls

List phone calls with optional filters. Returns lightweight call records — for full call detail including summary and score, use phone_call_get.

Input parameters:

- `agentId` (string): Filter by agent ID.
- `direction` (string): Filter by call direction.
- `limit` (integer): Max results (default: 20).
- `offset` (integer): Offset for pagination.
- `status` (string): Filter by call state (INITIATING, RINGING, ACTIVE, ENDED, etc.).

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `phone_call_get` (~74 tokens)

Get Phone Call

Get full detail for a single phone call: status, duration, participants, AI-generated summary (one-liner, topics, action items, decisions, open questions, next steps), and quality score. The summary is generated once on first read after post-call processing and cached.

Input parameters:

- `id` (string, required): The call ID.

### `phone_call_transcript_get` (~48 tokens)

Get Phone Call Transcript

Get the full transcript of a phone call with speaker labels, timestamps, and confidence scores. Available after the call ends and transcription completes.

Input parameters:

- `id` (string, required): The call ID.

### `phone_call_recording_get` (~54 tokens)

Get Phone Call Recording

Get a time-limited download URL for a call recording (WAV format). The URL expires after 1 hour. Recording must have been enabled during the call.

Input parameters:

- `id` (string, required): The call ID.

### `voice_list` (~131 tokens)

List AI Voices

List available AI voices for placing phone calls. The catalog is multilingual — filter by language or gender. Each voice includes descriptive metadata and a vendor-neutral audio preview URL (sampleUrl), plus the voice ID needed for phone_call_create.

Input parameters:

- `gender` (string): Filter by voice gender.
- `language` (string): Filter by BASE language code — the bare two-letter code, e.g. 'en' or 'fr'. Matching is a prefix test against the catalog's own base codes, so a region tag like 'en-US' matches nothing. Call without…

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `account_overview` (~129 tokens)

Account Overview

Single-call workspace snapshot: organization context, credential identity, send-capability flags (canSendEmail / canSendSms), inventory counts (agents, domains, phones), active blockers (each carrying the canonical MCP tool that resolves it), and the running MCP server's deploy identity (commitSha, revision, buildId, startedAt). Strict superset of the legacy whoami + workspace_health pair. Use before any non-trivial workflow to answer 'who am I, can I do X right now, and which deploy is serving me?' in one round-trip — no real send needed to find out.

### `usage_overview` (~133 tokens)

Usage Overview

Usage rollup for a billing period. Returns counters keyed by usage type (e.g. 'email_sent', 'sms_sent', 'voice_call_minutes') plus the latest update timestamp. Defaults to the current calendar month in UTC when `period` is omitted. Read-only, callable by any authenticated credential — scoped to the caller's org. Use to answer 'where am I against my tier limits?' without paying for per-event detail (UsageEvent is operator-tier).

Input parameters:

- `period` (string): Billing period in YYYY-MM format (e.g. '2026-05'). Defaults to the current calendar month in UTC.

### `webhook_get` (~40 tokens)

Get Webhook

Get a webhook subscription by ID. Returns the full configuration (URL, subscribed events, active state, description).

Input parameters:

- `id` (string, required): Webhook ID

### `webhook_list` (~62 tokens)

List Webhooks

List webhook subscriptions for the calling org with cursor pagination. Use to enumerate existing webhooks before set/delete operations.

Input parameters:

- `cursor` (string): Pagination cursor from a previous list call
- `limit` (integer): Maximum number of webhooks to return (1-100)

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `webhook_set` (~275 tokens)

Set Webhook

Create or update a webhook subscription (upsert). If `id` is provided the call updates that webhook (PUT). If omitted it creates a new one (POST) — `url` and `events` are then required. Use this for declarative 'ensure webhook X exists' workflows.

Input parameters:

- `active` (boolean): Whether the webhook is active. Defaults to true on create.
- `authConfig`: Auth the platform presents to your endpoint IN ADDITION to the always-on X-Anima-Signature HMAC — a bearer token, HTTP basic, or a custom header. Pass { type: 'none' } to remove it.
- `description` (string): Optional human-readable label
- `events` (array): List of event types to subscribe to (e.g. 'message.received', 'email.bounced'). Required on create; optional on update.
- `id` (string): Webhook ID. Present → updates that webhook (PUT). Omitted → creates a new one (POST).
- `maxAttempts` (integer): Max delivery attempts before dead-lettering (default 3)
- `rateLimitPerMinute` (integer): Max deliveries per minute to this endpoint; omit for unlimited
- `url` (string): HTTPS endpoint URL that will receive event payloads. Required on create; optional on update.

### `webhook_delete` (~53 tokens)

Delete Webhook

Delete a webhook subscription by ID. Permanently removes the configuration and stops future deliveries. To temporarily pause without deleting, use webhook_set with { id, active: false }.

Input parameters:

- `id` (string, required): Webhook ID

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `webhook_test` (~86 tokens)

Test Webhook

Send a test event payload to a webhook to verify the endpoint is reachable and signature verification works. Returns a deliveryId you can correlate with your endpoint's logs.

Input parameters:

- `event` (string): Event type to simulate in the test payload (e.g. 'message.received'). Defaults to 'message.received'.
- `id` (string, required): Webhook ID to send a test delivery to

### `vault_provision` (~78 tokens)

Provision Vault

Provision a credential vault for an agent. Required before vault_credential_create can be called against a freshly-created agent — without a vault, credentials have nowhere to live. Idempotent: returns the existing vault if one already exists. Master-key only.

Input parameters:

- `agentId` (string, required): Agent ID to provision a vault for. Master-key only.

### `vault_credential_list` (~82 tokens)

List Vault Credentials

List credentials in an agent vault with optional type filter. Use to browse stored secrets before reading, updating, or deleting entries. Sensitive fields are masked.

Input parameters:

- `agentId` (string): Agent ID whose vault to list. Optional when using an agent-bound credential (ak_* or oat_* with agentId).
- `type` (string): Optional credential type filter.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `vault_credential_get` (~97 tokens)

Get Vault Credential

Get a single vault credential by ID. Sensitive fields (passwords, tokens, SSNs, CVV) are masked. To use the plaintext for autofill or as an upstream credential, mint a vault token at the credential broker — the LLM never sees the secret directly.

Input parameters:

- `agentId` (string): Agent ID that owns the credential. Optional when using an agent-bound credential.
- `id` (string, required): Credential ID.

### `vault_credential_create` (~380 tokens)

Create Vault Credential

Create a new credential in an agent vault. Pass `type` plus the matching payload block (login / card / identity / oauthToken / apiKey / certificate / notes). For login credentials, prefer `generatePassword` over supplying `login.password` — the vault generates and stores the password server-side and returns only the credential reference, so the secret never enters the conversation. For api_key/oauth_token credentials, set `allowedHosts` so the credential can be exercised through vault_credential_use.

Input parameters:

- `agentId` (string): Agent ID that owns the new credential. Optional when using an agent-bound credential.
- `apiKey` (object): API key payload for api_key-type.
- `card` (object): Card payload for card-type.
- `certificate` (object): Certificate payload for certificate-type.
- `favorite` (boolean): Optional favorite flag.
- `fields` (array): Optional custom fields.
- `generatePassword` (object): Generate the login password server-side instead of supplying login.password. Preferred for login credentials: the password is created and stored inside the vault and never enters the conversation. On…
- `identity` (object): Identity payload for identity-type.
- `login` (object): Login payload for login-type.
- `name` (string, required): Human-readable credential name.
- `notes` (string): Optional secure note text.
- `oauthToken` (object): OAuth token payload for oauth_token-type.
- `revealPolicy` (string): Reveal policy. 'brokered' means the plaintext is never returned by any read/reveal/export path — not even to the org master key; the secret is only usable via vault_credential_use (recovery = rotatio…
- `type` (string, required): Credential type.

### `vault_credential_update` (~223 tokens)

Update Vault Credential

Update an existing vault credential by ID, including optional structured sections and metadata flags. Use to rotate passwords or revise stored details.

Input parameters:

- `agentId` (string): Agent ID that owns the credential. Optional when using an agent-bound credential.
- `apiKey` (object): Optional updated API key payload. Changing allowedHosts requires a master key.
- `card` (object): Optional updated card payload.
- `certificate` (object): Optional updated certificate payload.
- `favorite` (boolean): Optional updated favorite flag.
- `fields` (array): Optional updated custom fields.
- `id` (string, required): Credential ID to update.
- `identity` (object): Optional updated identity payload.
- `login` (object): Optional updated login payload.
- `name` (string): Optional updated name.
- `notes` (string): Optional updated note text.
- `oauthToken` (object): Optional updated OAuth token payload.
- `revealPolicy` (string): Optional reveal-policy change. Upgrading standard → brokered needs UPDATE access; downgrading brokered → standard is master-key-only.

### `vault_credential_delete` (~58 tokens)

Delete Vault Credential

Delete a credential from vault storage by ID. Use to remove obsolete or compromised secrets.

Input parameters:

- `agentId` (string): Agent ID that owns the credential. Optional when using an agent-bound credential.
- `id` (string, required): Credential ID.

Output parameters:

- `deleted` (boolean)
- `id` (string)

### `vault_exchange_token_for_injection` (~130 tokens)

Exchange Vault Token (injection)

Exchange a vtk_ vault token for the PLAINTEXT credential, to inject into a trusted client process (a CLI, the browser extension) — NOT to read it yourself. The API gates this to injector credentials: it only succeeds for a master key or a key carrying the `vault:inject` scope; a plain agent key gets 403. If you are an agent that needs to USE a secret, do NOT use this — use vault_credential_use (the server-side broker), which never reveals the secret.

Input parameters:

- `token` (string, required): The vtk_ vault token to exchange.

### `vault_credential_use` (~231 tokens)

Use Vault Credential

Make an outbound HTTPS call with a stored credential attached SERVER-SIDE, and get the upstream response. Use this to act with a secret (call an API, hit an authed endpoint) WITHOUT ever seeing the plaintext — the platform injects the credential on the wire. The target host must be on the credential's allowlist. Works even for `brokered` credentials that can never be revealed. Prefer this over trying to read a secret: you can use it, you cannot see it.

Input parameters:

- `agentId` (string): Agent ID that owns the credential. Optional when using an agent-bound credential.
- `body` (string): Raw request body (encode JSON yourself).
- `headers` (object): Extra request headers. Any Authorization / auth header you set is IGNORED and replaced by the real credential.
- `id` (string, required): Credential ID to broker the call with.
- `method` (string, required): HTTP method for the outbound call.
- `url` (string, required): Absolute https:// URL to call. Its host MUST be on the credential's allowlist (allowedHosts / login URIs).

### `vault_credential_search` (~108 tokens)

Search Vault

Search vault credentials by keyword across names and content. Use when you know part of the name, URL, or username but not the exact credential ID. Different access pattern from vault_credential_list — list is paginated browsing, search is text-query lookup.

Input parameters:

- `agentId` (string): Agent ID whose vault to search. Optional when using an agent-bound credential.
- `search` (string, required): Search text matched against names and content.
- `type` (string): Optional credential type filter.

Output parameters:

- `count` (number)
- `cursor` (string|null)
- `has_more` (boolean)
- `items` (array)
- `next_offset` (number)
- `total` (number)

### `vault_credential_get_totp` (~80 tokens)

Get Vault TOTP

Get the current TOTP code for a credential that has a TOTP secret configured. Returns the live 6-digit code derived from the stored secret — the secret itself is never disclosed.

Input parameters:

- `agentId` (string): Agent ID that owns the credential. Optional when using an agent-bound credential.
- `id` (string, required): Credential ID.

### `vault_credential_request_create` (~275 tokens)

Request Credential From Human

Request a credential from a HUMAN without the agent or LLM ever seeing the secret. When the connecting MCP client supports inline elicitation, the human is shown a form to type the secret directly — the tool returns `status: FULFILLED` with the `credentialId` in one call, no link needed. Otherwise it returns a single-use fill link (`fillUrl`, emailed to the org owner); poll vault_credential_request_status until `status` is FULFILLED, then use the returned `credentialId` as a normal vault credential. Use this when a flow needs a secret the agent doesn't hold and can't safely be given (passwords, API keys, card numbers).

Input parameters:

- `agentId` (string): Agent ID whose vault the requested credential lands in. Optional when using an agent-bound credential.
- `name` (string, required): Human-readable name for the requested credential.
- `notifyOwner` (boolean): Whether to email the single-use fill link to the org owner. Defaults to true.
- `reason` (string, required): Plain-language reason shown to the human explaining why the credential is needed.
- `ttlSeconds` (number): Optional fill-link lifetime in seconds before the request expires.
- `type` (string, required): Credential type the human will be asked to fill: login, secure_note, or card.

### `vault_credential_request_status` (~85 tokens)

Get Credential Request Status

Get the status of a pending credential request by ID. Poll this after vault_credential_request_create until `status` is FULFILLED, then use `credentialId` as a normal vault credential. `maskedPreview` shows a redacted hint of the filled value once available — the plaintext is never returned.

Input parameters:

- `requestId` (string, required): Credential-request ID.

### `vault_credential_request_cancel` (~61 tokens)

Cancel Credential Request

Cancel a pending credential request by ID. Invalidates the single-use fill link so the human can no longer submit a value. Use when the request is no longer needed or was created in error.

Input parameters:

- `requestId` (string, required): Credential-request ID.

### `vault_credential_request_fill` (~66 tokens)

Submit Credential (widget)

Internal: submit a credential-request secret from the Anima UI widget. Not for direct agent use.

Input parameters:

- `fillToken` (string, required): Single-use fill token from the ui-tier render-data.
- `values` (object, required): The secret field values the human entered in the widget.

### `extension_connect` (~196 tokens)

Connect Browser Extension

Create a short-lived, single-use connect URL that links a browser extension (or a headless Puppeteer worker) to an Anima agent. Returns `connectUrl` — hand it to the extension to complete the handshake before `exchangeExpiresAt`. The response carries no token or secret. Auth: with a master key you MUST pass `agentId`; with an agent key OMIT `agentId` (the server resolves it from the key). `ttl` is optional; a value above the org's maximum is rejected.

Input parameters:

- `agentId` (string): Agent to connect the extension to. REQUIRED when authenticating with a master key (mk_); OMIT when using an agent key (ak_/oat_) — the server resolves the agent from the key.
- `ttl` (string): Requested lifetime of the connection. A value longer than the org's policy maximum is rejected (not silently shortened); omit to use the policy default.

Output parameters:

- `agentId` (string)
- `connectUrl` (string)
- `exchangeExpiresAt` (string)
- `expiresAt` (string|null)
- `policy` (string)

## Diagnostics

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

## Score history

- 2026-09-21: 36
- 2026-09-20: 85
- 2026-09-19: 84
- 2026-09-18: 84
- 2026-09-17: 83
- 2026-09-16: 83
- 2026-09-15: 82
- 2026-09-14: 82
- 2026-09-13: 82
- 2026-09-12: 81
- 2026-09-11: 81
- 2026-09-10: 80
- 2026-09-09: 80
- 2026-09-08: 79
- 2026-09-07: 36
- 2026-09-06: 36
- 2026-09-05: 36
- 2026-09-04: 36

## Common questions

### What is the io.github.anima-labs-ai/anima MCP server?

io.github.anima-labs-ai/anima is an MCP server listed in the public MCP registry as io.github.anima-labs-ai/anima. Give your AI agent an identity it owns: email inbox, US phone number, SMS, voice, and a vault. This page covers its hosted endpoint (https://mcp.useanima.sh/mcp).

### Is the io.github.anima-labs-ai/anima MCP server safe to use?

io.github.anima-labs-ai/anima scores 36 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 io.github.anima-labs-ai/anima MCP server expose?

io.github.anima-labs-ai/anima exposes 67 tools: agent_create, agent_get, agent_list, agent_update, agent_delete, and 62 more. Their descriptions and schemas cost roughly 8,116 tokens of context every time the server is loaded.

### Does the io.github.anima-labs-ai/anima MCP server require authentication?

Yes. io.github.anima-labs-ai/anima asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the io.github.anima-labs-ai/anima MCP server still maintained?

io.github.anima-labs-ai/anima is still listed as active in the MCP registry. We last reached this channel on 21 September 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://mcp.useanima.sh/mcp
- Repository: https://github.com/anima-labs-ai/mcp-server
- Website: https://useanima.sh/
- Changelog RSS feed: https://verifymcp.io/servers/anima-labs-ai-anima/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/anima-labs-ai-anima/mcp.json
- HTML version of this page: https://verifymcp.io/servers/anima-labs-ai-anima/mcp