# Gruvi (npm · @agent-gruvi/gruvi-mcp-server)

Publish social videos and photo carousels, bulk schedule posts, and read analytics with Gruvi.

- Trust score: 57/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@agent-gruvi/gruvi-mcp-server`: 57/100 (this document), [markdown](https://verifymcp.io/servers/com-agentgruvi-gruvi/agent-gruvi-gruvi-mcp-server.md), [page](https://verifymcp.io/servers/com-agentgruvi-gruvi/agent-gruvi-gruvi-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@agent-gruvi/gruvi-mcp-server`
- Version: `2.1.0`
- 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**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 73/100
  - 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 1564 tokens (~55/item across 28 items; 26 tools + 2 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**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 28 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 Gruvi MCP server?

Gruvi runs locally as an npm package, launched with npx -y @agent-gruvi/gruvi-mcp-server. 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 com-agentgruvi-gruvi -- npx -y @agent-gruvi/gruvi-mcp-server
```

### Cursor

```json
{
  "mcpServers": {
    "com-agentgruvi-gruvi": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-gruvi/gruvi-mcp-server"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agentgruvi-gruvi": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-gruvi/gruvi-mcp-server"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-agentgruvi-gruvi -- npx -y @agent-gruvi/gruvi-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agentgruvi-gruvi": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@agent-gruvi/gruvi-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agentgruvi-gruvi --command npx --arg -y --arg @agent-gruvi/gruvi-mcp-server
```

### Hermes

```yaml
mcp_servers:
  com-agentgruvi-gruvi:
    command: "npx"
    args: ["-y", "@agent-gruvi/gruvi-mcp-server"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-agentgruvi-gruvi": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@agent-gruvi/gruvi-mcp-server"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agentgruvi-gruvi -t stdio -c npx -a -y @agent-gruvi/gruvi-mcp-server
```

### Other

```json
{
  "mcpServers": {
    "com-agentgruvi-gruvi": {
      "command": "npx",
      "args": [
        "-y",
        "@agent-gruvi/gruvi-mcp-server"
      ]
    }
  }
}
```

## 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 57, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 42)

First indexed and scored.

## MCP tools (26)

### `gruvi_login` (~36 tokens)

Authenticate using a Gruvi agent key. Prefer GRUVI_API_KEY in the client environment.

Input parameters:

- `apiKey` (string, required)

### `gruvi_get_plans` (~24 tokens)

Read the current monthly publishing plans before asking the user to choose.

### `gruvi_create_checkout` (~76 tokens)

Create a Stripe-hosted checkout link for the plan the user selected. Does not charge a card or activate a plan. Keep the same requestId if the response is uncertain. Return the checkout URL for secure payment; never collect card details in chat.

Input parameters:

- `planId` (string, required)
- `requestId` (string, required)

### `gruvi_get_billing_status` (~30 tokens)

Read current subscription status after checkout. A redirect or checkout URL alone does not prove payment.

### `gruvi_get_user_info` (~19 tokens)

Verify the authenticated account and current membership.

### `gruvi_get_social_accounts` (~24 tokens)

List connected social accounts. Use their exact account IDs for publishing.

### `gruvi_list_videos` (~32 tokens)

List existing media before uploading again.

Input parameters:

- `limit` (integer)
- `page` (integer)

### `gruvi_get_video` (~26 tokens)

Inspect one video in your media library.

Input parameters:

- `videoId` (string, required)

### `gruvi_get_video_upload_url` (~61 tokens)

Request a direct upload URL. PUT file bytes with the same Content-Type, without the Gruvi Authorization header, then finalize.

Input parameters:

- `fileName` (string, required)
- `fileSize` (integer, required)
- `fileType` (string, required)

### `gruvi_finalize_video_upload` (~78 tokens)

Save a completed direct upload. Keep videoId and videoKey to avoid duplicate uploads if a response is uncertain.

Input parameters:

- `aspectRatio` (string)
- `description` (string)
- `tags` (array)
- `title` (string, required)
- `videoId` (string, required)
- `videoKey` (string, required)

### `gruvi_upload_video` (~81 tokens)

Upload a local finished video (up to 512 MB), finalize it and optionally attach a JPEG thumbnail. Does not publish.

Input parameters:

- `aspectRatio` (string)
- `description` (string)
- `filePath` (string, required)
- `tags` (array)
- `thumbnailFilePath` (string)
- `title` (string, required)

### `gruvi_upload_thumbnail` (~45 tokens)

Attach your own JPEG thumbnail (up to 5 MB). Does not generate or publish content.

Input parameters:

- `filePath` (string, required)
- `videoId` (string, required)

### `gruvi_update_post_metadata` (~59 tokens)

Set the title, caption and tags on an existing video. Does not generate copy or publish.

Input parameters:

- `description` (string)
- `tags` (array)
- `title` (string, required)
- `videoId` (string, required)

### `gruvi_publish_post` (~103 tokens)

Publish an existing video to selected accounts. Requires a paid plan and user-authorized content/destinations. Check status after submission. Do not blindly retry.

Input parameters:

- `addThumbnailIntro` (boolean)
- `description` (string)
- `platforms` (array, required)
- `tags` (array)
- `tiktokSettings` (object)
- `title` (string)
- `videoId` (string, required)
- `youtubeSettings` (object)

### `gruvi_get_post_status` (~35 tokens)

Inspect per-platform status for an immediate post. Upload acceptance is not confirmed publication.

Input parameters:

- `videoId` (string, required)

### `gruvi_schedule_post` (~135 tokens)

Schedule an existing video for future delivery. Requires a paid plan and user-authorized content/destinations. A returned scheduleId confirms scheduling, not publication.

Input parameters:

- `addThumbnailIntro` (boolean)
- `description` (string)
- `platforms` (array, required)
- `requestId` (string)
- `scheduledTime` (string, required)
- `tags` (array)
- `thumbnailKey` (string)
- `thumbnailUrl` (string)
- `tiktokSettings` (object)
- `title` (string, required)
- `videoId` (string, required)
- `youtubeSettings` (object)

### `gruvi_list_scheduled_posts` (~22 tokens)

List the calendar, post history and scheduling allowance.

### `gruvi_get_scheduled_post` (~29 tokens)

Inspect one scheduled post and its delivery results.

Input parameters:

- `scheduleId` (string, required)

### `gruvi_delete_scheduled_post` (~30 tokens)

Cancel a scheduled post after the user requests cancellation.

Input parameters:

- `scheduleId` (string, required)

### `gruvi_get_analytics` (~46 tokens)

Read supported TikTok or YouTube account summary/trend analytics.

Input parameters:

- `accountId` (string)
- `kind` (string)
- `platform` (string, required)

### `gruvi_bulk_schedule_videos` (~67 tokens)

Schedule up to 20 existing videos. Supply a stable requestId and exact account targets. Reuse the unchanged request after an uncertain response; results report each item separately. Scheduling is not confirmed publication.

Input parameters:

- `posts` (array, required)
- `requestId` (string, required)

### `gruvi_list_carousels` (~22 tokens)

List saved photo carousels before uploading again.

### `gruvi_upload_carousel` (~77 tokens)

Upload 2 to 10 owner-approved local JPEG, PNG or WebP images, in their supplied order, up to 5 MB each. Saves without publishing. Images fit a 4:5 canvas without cropping.

Input parameters:

- `caption` (string)
- `filePaths` (array, required)
- `title` (string, required)

### `gruvi_publish_carousel` (~98 tokens)

Publish to one Instagram or TikTok account. Requires owner-authorized content and an active plan or trial. Reuse requestId after uncertainty and check status. TikTok defaults to creator-inbox review.

Input parameters:

- `accountId` (string, required)
- `caption` (string)
- `carouselId` (string, required)
- `platform` (string, required)
- `requestId` (string, required)
- `tiktokSettings` (object)

### `gruvi_schedule_carousel` (~102 tokens)

Schedule a saved carousel for one exact Instagram or TikTok account. Reuse requestId after uncertainty. TikTok defaults to creator-inbox review.

Input parameters:

- `accountId` (string, required)
- `caption` (string)
- `carouselId` (string, required)
- `platform` (string, required)
- `requestId` (string, required)
- `scheduledTime` (string, required)
- `tiktokSettings` (object)
- `title` (string)

### `gruvi_get_carousel_publication` (~53 tokens)

Check before retrying. Processing or accepted does not mean live. TikTok inbox drafts require the creator to finish posting.

Input parameters:

- `carouselId` (string, required)
- `requestId` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-agentgruvi-gruvi/agent-gruvi-gruvi-mcp-server#diagnostics

## Score history

- 2026-11-05: 57
- 2026-11-04: 57
- 2026-11-03: 42

## Common questions

### What is the Gruvi MCP server?

Gruvi is an MCP server listed in the public MCP registry as com.agentgruvi/gruvi. Publish social videos and photo carousels, bulk schedule posts, and read analytics with Gruvi. This page covers its npm package (@agent-gruvi/gruvi-mcp-server).

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

Gruvi scores 57 out of 100 on VerifyMCP. We recorded 1 known advisory against 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 Gruvi MCP server expose?

Gruvi exposes 26 tools: gruvi_login, gruvi_get_plans, gruvi_create_checkout, gruvi_get_billing_status, gruvi_get_user_info, and 21 more. Their descriptions and schemas cost roughly 1,410 tokens of context every time the server is loaded.

### Is the Gruvi MCP server still maintained?

Gruvi 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 Gruvi MCP server under?

Gruvi 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/@agent-gruvi/gruvi-mcp-server
- Socket report: https://socket.dev/npm/package/@agent-gruvi/gruvi-mcp-server
- Website: https://agentgruvi.com/docs/agent-integration
- Changelog RSS feed: https://verifymcp.io/servers/com-agentgruvi-gruvi/agent-gruvi-gruvi-mcp-server.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agentgruvi-gruvi/agent-gruvi-gruvi-mcp-server.json
- HTML version of this page: https://verifymcp.io/servers/com-agentgruvi-gruvi/agent-gruvi-gruvi-mcp-server