# io.github.SergioRico1/thrd (npm · thrd-mcp)

Thrd MCP: agent email tools for events/threads, safe send/reply, usage, trust and security.

- Trust score: 59/100 (low)
- Change this week: +17
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `thrd-mcp`: 59/100 (this document), [markdown](https://verifymcp.io/servers/sergiorico1-thrd/thrd-mcp.md), [page](https://verifymcp.io/servers/sergiorico1-thrd/thrd-mcp)

## Channel facts

- Registry: `npm`
- Package: `thrd-mcp`
- Version: `0.1.5`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 166 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 67/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 797 tokens (~44/item across 18 items; 16 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (19% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add sergiorico1-thrd -- npx -y thrd-mcp
```

### Codex

```bash
codex mcp add sergiorico1-thrd -- npx -y thrd-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sergiorico1-thrd": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "thrd-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sergiorico1-thrd --command npx --arg -y --arg thrd-mcp
```

### Hermes

```yaml
mcp_servers:
  sergiorico1-thrd:
    command: "npx"
    args: ["-y", "thrd-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "sergiorico1-thrd": {
      "command": "npx",
      "args": [
        "-y",
        "thrd-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.

### 2026-08-04 (score 59, 0)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail

### 2026-08-02 (score 59, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Dependency health: unverified → partial

### 2026-08-01 (score 33, +24)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 9, −58)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-29 (score 67, +25)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-27 (score 42)

First indexed and scored.

## MCP tools (16)

### `thrd.health` (~23 tokens)

Health

Get MCP server and Thrd API configuration info (no auth required).

Output parameters:

- `apiBaseUrl` (string)
- `hasApiKey` (boolean)
- `ok` (boolean)

### `thrd.poll_events` (~46 tokens)

Poll Events

Long-poll for inbound events (email received, security signals, etc.).

Input parameters:

- `cursor` (string)
- `limit` (integer)
- `timeout` (integer)

Output parameters:

- `events` (array)
- `next_cursor` (string)

### `thrd.ack_events` (~38 tokens)

Ack Events

Acknowledge processed events by event IDs or by cursor.

Input parameters:

- `cursor` (string)
- `eventIds` (array)

### `thrd.list_threads` (~46 tokens)

List Threads

List recent threads for the authenticated agent (optionally filtered by inbox).

Input parameters:

- `cursor` (string)
- `inboxId` (string)
- `limit` (integer)

Output parameters:

- `threads` (array)

### `thrd.get_thread_messages` (~33 tokens)

Get Thread Messages

Fetch all stored messages for a given thread (inbound + outbound).

Input parameters:

- `threadId` (string, required)

### `thrd.reply` (~93 tokens)

Reply

Reply in an existing thread. Requires idempotency. May return security_ack_required when inbound risk is high.

Input parameters:

- `attachments` (array)
- `cc` (array)
- `html` (string)
- `idempotencyKey` (string)
- `securityAckToken` (string)
- `text` (string)
- `threadId` (string, required)
- `to` (string)

### `thrd.send` (~144 tokens)

Send

Initiate a new outbound email. Requires idempotency. Tier 3 cold outbound may return por_required. High-risk inbound context may require security_ack_token.

Input parameters:

- `attachments` (array)
- `consentToken` (string)
- `grantToken` (string)
- `html` (string)
- `idempotencyKey` (string)
- `inboxId` (string, required)
- `porAnswer` (string)
- `porToken` (string)
- `securityAckToken` (string)
- `sourceMessageId` (string)
- `subject` (string, required)
- `text` (string)
- `to` (string, required)

### `thrd.outbound_status` (~31 tokens)

Outbound Status

Get status for an outbound request_id from send/reply.

Input parameters:

- `requestId` (string, required)

### `thrd.usage` (~23 tokens)

Usage

Get plan/tier and monthly quota usage for the authenticated tenant.

### `thrd.trust_score` (~21 tokens)

Trust Score

Get trust score and factors for the authenticated tenant.

### `thrd.message_security` (~30 tokens)

Message Security

Get Prompt Shield / security analysis for a specific message_id.

Input parameters:

- `messageId` (string, required)

### `thrd.create_security_ack` (~59 tokens)

Create Security ACK

Create a short-lived security_ack_token to approve replying/sending in a high-risk context.

Input parameters:

- `action` (string, required)
- `messageId` (string, required)
- `reason` (string, required)
- `threadId` (string)

### `thrd.billing_checkout_self` (~31 tokens)

Checkout (Self)

Create a Stripe checkout session for the authenticated tenant to upgrade plan.

Input parameters:

- `plan` (string, required)

### `thrd.claim_x_start` (~27 tokens)

Start X Human Claim

Start the X (Twitter) human-claim verification flow for the authenticated tenant.

### `thrd.claim_x_status` (~26 tokens)

X Human Claim Status

Check X (Twitter) human-claim verification status for the authenticated tenant.

### `thrd.instant_onboarding` (~85 tokens)

Instant Onboarding (Public)

Provision a new tenant + agent + inbox + API key via Thrd's public instant onboarding endpoint. Disabled unless ALLOW_THRD_INSTANT_ONBOARDING=1.

Input parameters:

- `agentName` (string, required)
- `contactEmail` (string)
- `inboxPrefix` (string)
- `source` (string)
- `tenantName` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/sergiorico1-thrd/thrd-mcp#diagnostics

## Score history

- 2026-08-04: 59
- 2026-08-03: 59
- 2026-08-02: 59
- 2026-08-01: 33
- 2026-07-30: 9
- 2026-07-29: 67
- 2026-07-28: 42
- 2026-07-27: 42

## Links

- npm package: https://www.npmjs.com/package/thrd-mcp
- Socket report: https://socket.dev/npm/package/thrd-mcp
- Website: https://thrd.email/
- Changelog RSS feed: https://verifymcp.io/servers/sergiorico1-thrd/thrd-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/sergiorico1-thrd/thrd-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/sergiorico1-thrd/thrd-mcp