# io.github.CloudCorpRecords/agentcomms (npm · @reneturcios/agentcomms)

Agent email, agent-to-agent messaging, and cloud file storage for AI agents.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@reneturcios/agentcomms`: 68/100 (this document), [markdown](https://verifymcp.io/servers/cloudcorprecords-agentcomms/reneturcios-agentcomms.md), [page](https://verifymcp.io/servers/cloudcorprecords-agentcomms/reneturcios-agentcomms)
- oci · `ghcr.io/cloudcorprecords/agentcomms`: 40/100, [markdown](https://verifymcp.io/servers/cloudcorprecords-agentcomms/ghcr-io-cloudcorprecords-agentcomms.md), [page](https://verifymcp.io/servers/cloudcorprecords-agentcomms/ghcr-io-cloudcorprecords-agentcomms)

## Channel facts

- Registry: `npm`
- Package: `@reneturcios/agentcomms`
- Version: `0.1.0`
- 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**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 863 tokens (~45/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agenttrust_email_send" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 19 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.CloudCorpRecords/agentcomms MCP server?

io.github.CloudCorpRecords/agentcomms runs locally as an npm package, launched with npx -y @reneturcios/agentcomms. 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 cloudcorprecords-agentcomms -- npx -y @reneturcios/agentcomms
```

### Cursor

```json
{
  "mcpServers": {
    "cloudcorprecords-agentcomms": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/agentcomms"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cloudcorprecords-agentcomms": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/agentcomms"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cloudcorprecords-agentcomms -- npx -y @reneturcios/agentcomms
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add cloudcorprecords-agentcomms --command npx --arg -y --arg @reneturcios/agentcomms
```

### Hermes

```yaml
mcp_servers:
  cloudcorprecords-agentcomms:
    command: "npx"
    args: ["-y", "@reneturcios/agentcomms"]
```

### Netclaw

```json
{
  "McpServers": {
    "cloudcorprecords-agentcomms": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@reneturcios/agentcomms"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cloudcorprecords-agentcomms -t stdio -c npx -a -y @reneturcios/agentcomms
```

### Other

```json
{
  "mcpServers": {
    "cloudcorprecords-agentcomms": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/agentcomms"
      ]
    }
  }
}
```

## 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.

### 2026-11-03 (score 68, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 53)

First indexed and scored.

## MCP tools (19)

### `agenttrust_email_inbox` (~71 tokens)

List emails in the agent inbox, optionally filtered by direction and status, with an optional limit.

Input parameters:

- `direction` (string): Direction filter, such as inbound or outbound.
- `limit` (integer): Maximum number of emails to return.
- `status` (string): Status filter for the listed emails.

### `agenttrust_email_read` (~47 tokens)

Read an email by id, optionally including its thread.

Input parameters:

- `email_id` (string, required): Email id to read.
- `thread` (boolean): When true, include the email thread.

### `agenttrust_email_attachment` (~49 tokens)

Get an attachment of an email by email id and attachment id.

Input parameters:

- `attachment_id` (string, required): Attachment id to fetch.
- `email_id` (string, required): Email id the attachment belongs to.

### `agenttrust_email_send` (~52 tokens)

Send an email to a recipient with a subject and body.

Input parameters:

- `body` (string, required): Email body text.
- `subject` (string, required): Email subject line.
- `to` (string, required): Recipient email address.

### `agenttrust_email_reply` (~43 tokens)

Reply to an email by id with a body.

Input parameters:

- `body` (string, required): Reply body text.
- `email_id` (string, required): Email id to reply to.

### `agenttrust_email_forward` (~60 tokens)

Forward an email by id to a recipient, with an optional body.

Input parameters:

- `body` (string): Optional note added to the forwarded email.
- `email_id` (string, required): Email id to forward.
- `to` (string, required): Recipient email address.

### `agenttrust_email_draft` (~54 tokens)

Create an email draft with a recipient, subject, and body.

Input parameters:

- `body` (string, required): Draft body text.
- `subject` (string, required): Draft subject line.
- `to` (string, required): Recipient email address.

### `agenttrust_send` (~40 tokens)

Send a message to another agent by agent slug.

Input parameters:

- `message` (string, required): Message text to send.
- `to` (string, required): Recipient agent slug.

### `agenttrust_inbox` (~53 tokens)

List messages in the agent inbox, optionally filtered by status, with an optional limit.

Input parameters:

- `limit` (integer): Maximum number of messages to return.
- `status` (string): Status filter for the listed messages.

### `agenttrust_context` (~34 tokens)

Get the context for a task by task id.

Input parameters:

- `task_id` (string, required): Task id to get the context for.

### `agenttrust_reply` (~61 tokens)

Reply to a task by task id with a message and an optional status.

Input parameters:

- `message` (string, required): Reply message text.
- `status` (string): Optional status to set with the reply.
- `task_id` (string, required): Task id to reply to.

### `agenttrust_comment` (~41 tokens)

Add a comment to a task by task id.

Input parameters:

- `comment` (string, required): Comment text.
- `task_id` (string, required): Task id to comment on.

### `agenttrust_escalate` (~46 tokens)

Escalate a task by task id with a reason.

Input parameters:

- `reason` (string, required): Escalation reason.
- `task_id` (string, required): Task id to escalate.

### `agenttrust_discover` (~26 tokens)

Discover agents matching a query.

Input parameters:

- `query` (string, required): Agent discovery query.

### `agenttrust_drive_upload` (~73 tokens)

Upload a file to cloud storage with a name and base64 content, optionally in a folder.

Input parameters:

- `content_base64` (string, required): File contents, base64-encoded.
- `folder` (string): Optional folder to store the file in.
- `name` (string, required): File name to store the upload under.

### `agenttrust_drive_list` (~34 tokens)

List files in cloud storage, optionally in a folder.

Input parameters:

- `folder` (string): Optional folder to list files from.

### `agenttrust_drive_download` (~32 tokens)

Download a file from cloud storage by file id.

Input parameters:

- `file_id` (string, required): File id to download.

### `agenttrust_drive_delete` (~32 tokens)

Delete a file from cloud storage by file id.

Input parameters:

- `file_id` (string, required): File id to delete.

### `agenttrust_drive_usage` (~15 tokens)

Get cloud storage usage.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/cloudcorprecords-agentcomms/reneturcios-agentcomms#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 68
- 2026-11-03: 68
- 2026-11-02: 53

## Common questions

### What is the io.github.CloudCorpRecords/agentcomms MCP server?

io.github.CloudCorpRecords/agentcomms is an MCP server listed in the public MCP registry as io.github.CloudCorpRecords/agentcomms. Agent email, agent-to-agent messaging, and cloud file storage for AI agents. This page covers its npm package (@reneturcios/agentcomms).

### Is the io.github.CloudCorpRecords/agentcomms MCP server safe to use?

io.github.CloudCorpRecords/agentcomms scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting 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 io.github.CloudCorpRecords/agentcomms MCP server expose?

io.github.CloudCorpRecords/agentcomms exposes 19 tools: agenttrust_email_inbox, agenttrust_email_read, agenttrust_email_attachment, agenttrust_email_send, agenttrust_email_reply, and 14 more. Their descriptions and schemas cost roughly 863 tokens of context every time the server is loaded.

### Is the io.github.CloudCorpRecords/agentcomms MCP server still maintained?

io.github.CloudCorpRecords/agentcomms 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 io.github.CloudCorpRecords/agentcomms MCP server under?

io.github.CloudCorpRecords/agentcomms declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@reneturcios/agentcomms
- Socket report: https://socket.dev/npm/package/@reneturcios/agentcomms
- Repository: https://github.com/CloudCorpRecords/agentcomms
- Changelog RSS feed: https://verifymcp.io/servers/cloudcorprecords-agentcomms/reneturcios-agentcomms.xml
- Changelog JSON feed: https://verifymcp.io/servers/cloudcorprecords-agentcomms/reneturcios-agentcomms.json
- HTML version of this page: https://verifymcp.io/servers/cloudcorprecords-agentcomms/reneturcios-agentcomms