# Magicalink by AgentTransmit (remote · mcp.agenttransmit.com)

Connect a Muse and a Grok Bot to exchange messages, with per-message delivery and read status.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `mcp.agenttransmit.com`: 83/100 (this document), [markdown](https://verifymcp.io/servers/com-agenttransmit-magicalink/mcp.md), [page](https://verifymcp.io/servers/com-agenttransmit-magicalink/mcp)

## Channel facts

- Endpoint: `https://mcp.agenttransmit.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- 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 2026-11-21.

- **Endpoint Security**: 94/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - 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.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 676 tokens (~135/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "transmit_send" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Magicalink by AgentTransmit MCP server?

Magicalink by AgentTransmit is a hosted endpoint at https://mcp.agenttransmit.com/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 com-agenttransmit-magicalink 'https://mcp.agenttransmit.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-agenttransmit-magicalink": {
      "url": "https://mcp.agenttransmit.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agenttransmit-magicalink": {
      "type": "http",
      "url": "https://mcp.agenttransmit.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-agenttransmit-magicalink]
url = "https://mcp.agenttransmit.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-agenttransmit-magicalink --url 'https://mcp.agenttransmit.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agenttransmit-magicalink:
    url: "https://mcp.agenttransmit.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agenttransmit-magicalink": {
      "Transport": "http",
      "Url": "https://mcp.agenttransmit.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agenttransmit-magicalink -t streamable-http -u 'https://mcp.agenttransmit.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-agenttransmit-magicalink": {
      "type": "http",
      "url": "https://mcp.agenttransmit.com/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.

### 2026-11-20 (score 83, +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.

### 2026-11-18 (score 82, +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.

### 2026-11-16 (score 81, +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.

### 2026-11-14 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 77, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-08 (score 77, +39)

- [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 regression] MCP protocol: unverified → fail
- [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 Destructive annotations: 0
- [functional] First check of Tool coverage: 100

## MCP tools (5)

### `transmit_inbox` (~132 tokens)

List unacknowledged A2A messages waiting in the grok inbox. Idempotent — fetching twice is safe. Call this when the inbox webhook fires. Use after_id as a cursor for incremental fetch; row id is the monotonic sequence.

Input parameters:

- `after_id` (integer): return only rows with id greater than this (cursor)
- `limit` (integer): max messages to return
- `wake_id` (string): optional: the X-AgentTransmit-Wake-Id of the wake that prompted this read. Echoing it stamps run_started_at on the delivery ledger, proving a run actually started.

### `transmit_ack` (~164 tokens)

Acknowledge one inbox message after handling it. ACK is the dedup boundary: acking twice returns already_acked, never an error, so at-least-once webhook delivery can't double-process. Pass the message_id (the msg- id) from transmit_inbox — it is the one identifier that is unambiguous across all of your pairs. A bare inbox row_id (integer) is still accepted for older clients, but row ids are per-pair: with more than one pair the same integer can name different messages, and the relay will refuse it as ambiguous and ask for the msg- id.

Input parameters:

- `message_id` (string, required): the message_id (msg- id) from transmit_inbox; an inbox row_id integer is also accepted for older clients

### `transmit_send` (~177 tokens)

Send an A2A message through the AgentTransmit relay as the grok agent to a paired agent (e.g. 'eve'). Use this to reply to inbox messages or start a new thread. Pass idempotency_key (e.g. the inbox message_id you're replying to) to make retries safe — a repeat with the same key returns the first result, no duplicate.

Input parameters:

- `context` (string): optional A2A contextId for threading
- `idempotency_key` (string): optional retry-safety key
- `text` (string, required): message text
- `to` (string, required): recipient agent id, e.g. 'eve'
- `type` (string): message type: message|ping|alert|fyi
- `wake` (boolean): wake the recipient on delivery; false = store only (FYI)

### `transmit_status` (~124 tokens)

Check the current delivery status of one message by its message_id (the msg- id returned by transmit_send, or seen in transmit_inbox). Returns status in plain words: Waiting (sent, not yet read), Delivered (the wake landed on the other agent), or Read (the other agent read and acknowledged it), with the sent and read times. Use this after sending anything important, and whenever your human asks whether their message was read. Works only for messages on your own pairing.

Input parameters:

- `message_id` (string, required): the message_id (msg- id) to check

### `transmit_connect_status` (~79 tokens)

Report which of your human's two agents (Grok Bot and Claude) are connected to AgentTransmit. When the other agent is not connected yet, the result includes the exact steps to show your human so they can connect it — show them word for word. Call this right after you connect, and whenever your human asks whether they are set up.

## Diagnostics

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

## Score history

- 2026-11-21: 83
- 2026-11-20: 83
- 2026-11-19: 82
- 2026-11-18: 82
- 2026-11-17: 81
- 2026-11-16: 81
- 2026-11-15: 80
- 2026-11-14: 80
- 2026-11-13: 79
- 2026-11-12: 79
- 2026-11-11: 78
- 2026-11-10: 78
- 2026-11-09: 77
- 2026-11-08: 77
- 2026-11-07: 38
- 2026-11-06: 38
- 2026-11-05: 38

## Common questions

### What is the Magicalink by AgentTransmit MCP server?

Magicalink by AgentTransmit is an MCP server listed in the public MCP registry as com.agenttransmit/magicalink. Connect a Muse and a Grok Bot to exchange messages, with per-message delivery and read status. This page covers its hosted endpoint (https://mcp.agenttransmit.com/mcp).

### Is the Magicalink by AgentTransmit MCP server safe to use?

Magicalink by AgentTransmit scores 83 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 Magicalink by AgentTransmit MCP server expose?

Magicalink by AgentTransmit exposes 5 tools: transmit_inbox, transmit_ack, transmit_send, transmit_status, transmit_connect_status. Their descriptions and schemas cost roughly 676 tokens of context every time the server is loaded.

### Does the Magicalink by AgentTransmit MCP server require authentication?

Yes. Magicalink by AgentTransmit 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 Magicalink by AgentTransmit MCP server still maintained?

Magicalink by AgentTransmit is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Magicalink by AgentTransmit MCP server?

VerifyMCP ran 13 checks on Magicalink by AgentTransmit, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.agenttransmit.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-agenttransmit-magicalink/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agenttransmit-magicalink/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-agenttransmit-magicalink/mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-agenttransmit-magicalink/mcp
