# Vuntum (remote · vuntum.com)

Sourced, dated data on consumer robots and physical AI: specs, prices, availability, evidence.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- remote · `vuntum.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-vuntum-mcp/vuntum.md), [page](https://verifymcp.io/servers/com-vuntum-mcp/vuntum)

## Channel facts

- Endpoint: `https://vuntum.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-10-16.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1650 tokens (~103/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 79% 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.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 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.

## Install

### How do I install the Vuntum MCP server?

Vuntum is a hosted endpoint at https://vuntum.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-vuntum-mcp 'https://vuntum.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

### 2026-10-15 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 27. That category is still filling its 30-day observation window: 6 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.

### 2026-10-09 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 17. That category is still filling its 30-day observation window: 3 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.

### 2026-10-07 (score 76, +3)

- [security improvement] HSTS header: fail → pass
- [security] Tool “find_robots_by_utility” rewrote its description, which is the text the model reads

### 2026-10-06 (score 73, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “compare_robots” rewrote its description, which is the text the model reads
- [security] Tool “find_home_robots” rewrote its description, which is the text the model reads
- [security] Tool “find_programmable_robots” rewrote its description, which is the text the model reads
- [security] Tool “find_robots_by_capability” rewrote its description, which is the text the model reads
- [security] Tool “find_robots_by_utility” rewrote its description, which is the text the model reads
- [security] Tool “get_article” rewrote its description, which is the text the model reads
- [security] Tool “get_methodology” rewrote its description, which is the text the model reads
- [security] Tool “get_recent_changes” rewrote its description, which is the text the model reads
- [security] Tool “get_robot” rewrote its description, which is the text the model reads
- [security] Tool “get_robot_availability” rewrote its description, which is the text the model reads
- [security] Tool “get_robot_claims” rewrote its description, which is the text the model reads
- [security] Tool “get_robot_prices” rewrote its description, which is the text the model reads
- [security] Tool “get_robot_sources” rewrote its description, which is the text the model reads
- [security] Tool “search_open_source_projects” rewrote its description, which is the text the model reads
- [security] Tool “search_robots” rewrote its description, which is the text the model reads
- [security] Tool “search_site” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 73 → 103
- [functional improvement] Tool coverage: 70% → 79%
- [functional improvement] Stability: unverified → 0.07
- [cosmetic] “find_home_robots” added an optional parameter “locale”
- [cosmetic] “find_programmable_robots” added an optional parameter “locale”
- [cosmetic] “find_robots_by_capability” added an optional parameter “locale”
- [cosmetic] “find_robots_by_utility” added an optional parameter “locale”
- [cosmetic] “get_methodology” added an optional parameter “locale”
- [cosmetic] “get_recent_changes” added an optional parameter “locale”
- [cosmetic] “get_robot_availability” added an optional parameter “locale”
- [cosmetic] “get_robot_claims” added an optional parameter “locale”
- [cosmetic] “get_robot_prices” added an optional parameter “locale”
- [cosmetic] “get_robot_sources” added an optional parameter “locale”
- [cosmetic] “search_open_source_projects” added an optional parameter “locale”
- [cosmetic] “get_robot_sources” reworded the description of “slug”
- [cosmetic] “compare_robots” reworded the description of “locale”
- [cosmetic] “find_home_robots” reworded the description of “limit”
- [cosmetic] “find_programmable_robots” reworded the description of “limit”
- [cosmetic] “find_robots_by_capability” reworded the description of “limit”
- [cosmetic] “find_robots_by_utility” reworded the description of “limit”
- [cosmetic] “get_article” reworded the description of “locale”
- [cosmetic] “get_article” reworded the description of “slug”
- [cosmetic] “get_recent_changes” reworded the description of “limit”
- [cosmetic] “get_robot” reworded the description of “locale”
- [cosmetic] “get_robot” reworded the description of “slug”
- [cosmetic] “get_robot_availability” reworded the description of “slug”
- [cosmetic] “get_robot_claims” reworded the description of “slug”
- [cosmetic] “get_robot_prices” reworded the description of “slug”
- [cosmetic] “search_open_source_projects” reworded the description of “limit”
- [cosmetic] “search_robots” reworded the description of “limit”
- [cosmetic] “search_robots” reworded the description of “locale”
- [cosmetic] “search_site” reworded the description of “limit”
- [cosmetic] “search_site” reworded the description of “locale”
- [cosmetic] Tool “compare_robots” changed its title: Comparer des robots → Compare robots
- [cosmetic] Tool “find_home_robots” changed its title: Robots pour la maison → Robots for the home
- [cosmetic] Tool “find_programmable_robots” changed its title: Robots programmables → Programmable robots
- [cosmetic] Tool “find_robots_by_capability” changed its title: Robots par capacité démontrée → Robots by demonstrated capability
- [cosmetic] Tool “find_robots_by_utility” changed its title: Robots par utilité → Robots by utility
- [cosmetic] Tool “get_methodology” changed its title: Méthodologie Vuntum → Vuntum methodology
- [cosmetic] Tool “get_recent_changes” changed its title: Changements récents → Recent changes
- [cosmetic] Tool “get_robot” changed its title: Fiche robot → Robot sheet
- [cosmetic] Tool “get_robot_availability” changed its title: Disponibilité d’un robot → Robot availability
- [cosmetic] Tool “get_robot_claims” changed its title: Affirmations d’un robot → Robot claims
- [cosmetic] Tool “get_robot_prices” changed its title: Prix d’un robot → Robot prices
- [cosmetic] Tool “get_robot_sources” changed its title: Sources d’un robot → Robot sources
- [cosmetic] Tool “search_open_source_projects” changed its title: Projets open source → Open source projects
- [cosmetic] Tool “search_robots” changed its title: Rechercher des robots → Search robots
- [cosmetic] Tool “search_site” changed its title: Rechercher sur Vuntum → Search Vuntum

### 2026-10-04 (score 72, +66)

- [security regression] HSTS header: unverified → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] TLS certificate: unverified → pass
- [security improvement] Transport: fail → pass
- [security] First check of Judged manipulation: pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Tool coverage: 70
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass

### 2026-10-03 (score 6)

First indexed and scored.

## MCP tools (16)

### `get_methodology` (~82 tokens)

Vuntum methodology

Definitions of the levels of evidence, the statuses, the freshness limits and the confidence score that come with every Vuntum value, as written on the methodology page. `locale: "fr"` for French.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.

### `search_robots` (~117 tokens)

Search robots

Full-text search over the published robot sheets: accents ignored, word starts, synonyms, close spelling, ranked by relevance. `matchQuality` says whether all the words, some of them or a close spelling were found. `locale: "fr"` for French texts and addresses.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `query` (string, required)

### `search_site` (~110 tokens)

Search Vuntum

The site search: robots, manufacturers and articles (full article text included). Can be filtered by type. Returns the type, title, summary and address of each result. `locale: "fr"` for French.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `query` (string, required)
- `types` (array)

### `get_article` (~96 tokens)

Article

A published article (text, date, sources) from its URL identifier (the `slug` of an article result, in the same language). `locale: "fr"` for French.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `slug` (string, required): URL identifier of the robot sheet, for example "g1".

### `get_robot` (~90 tokens)

Robot sheet

Full sheet of a published robot: summary, form, use, utilities, characteristics, prices, availability, sources. `locale: "fr"` for French.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `slug` (string, required): URL identifier of the robot sheet, for example "g1".

### `get_robot_claims` (~92 tokens)

Robot claims

All the validated claims of a robot, with evidence, source and quote. `locale: "fr"` for French values.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `predicate` (string)
- `slug` (string, required): URL identifier of the robot sheet, for example "g1".

### `get_robot_sources` (~79 tokens)

Robot sources

Sources behind the published claims of a robot. `locale: "fr"` for French source names.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `slug` (string, required): URL identifier of the robot sheet, for example "g1".

### `get_robot_prices` (~80 tokens)

Robot prices

Observed prices by market, price type and date. `locale: "fr"` for French notes.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `slug` (string, required): URL identifier of the robot sheet, for example "g1".

### `get_robot_availability` (~79 tokens)

Robot availability

Availability state by market, with observation date. `locale: "fr"` for French notes.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `slug` (string, required): URL identifier of the robot sheet, for example "g1".

### `compare_robots` (~112 tokens)

Compare robots

Comparison of 2 to 4 published robots on the columns of the Vuntum comparison. Each row says whether the values differ (`differs`); `differingPredicates` lists what sets the robots apart, `missingByRobot` what is not disclosed. `locale: "fr"` for French.

Input parameters:

- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `slugs` (array, required)

### `find_home_robots` (~75 tokens)

Robots for the home

Robots with a validated claim that they handle household tasks. `locale: "fr"` for French.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.

### `find_robots_by_utility` (~166 tokens)

Robots by utility

Published robots that have a given utility (the keys are the site's French slugs): menage, jardin, cuisine, compagnie, education, loisirs, aide-personne, medical, reeducation, recherche, logistique, livraison, accueil, nettoyage-pro, inspection, construction, agriculture, industrie, exploration, telepresence, secours, defense-securite, polyvalent, autres. A robot often has several (`utilities` field of each sheet). `locale: "en"` gives the English label and page.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `utility` (string, required)

### `find_robots_by_capability` (~128 tokens)

Robots by demonstrated capability

Published robots with a validated claim behind each requested capability: marcher, courir, escaliers, se-relever, saisir, plier-linge, ranger, navigation, parler. Never inferred from a category: each capability returns the claim, its source and its level of evidence. `locale: "fr"` for French.

Input parameters:

- `capabilities` (array, required)
- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.

### `find_programmable_robots` (~83 tokens)

Programmable robots

Robots with a public SDK, Python API, ROS or MCP, by deterministic criteria. `locale: "fr"` for French.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.

### `get_recent_changes` (~75 tokens)

Recent changes

Public change log: publications, corrections, price changes. `locale: "fr"` for French sentences.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.

### `search_open_source_projects` (~99 tokens)

Open source projects

Open source repositories related to robotics listed by Vuntum. No English description is written for a repository: with `locale: "en"` only the repository's own words are returned.

Input parameters:

- `limit` (integer): Maximum number of results (50 max).
- `locale` (string): Language of the texts and addresses: "fr" (default) or "en". The figures and the sources are identical.
- `query` (string)

## Diagnostics

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

## Score history

- 2026-10-16: 80
- 2026-10-15: 80
- 2026-10-14: 79
- 2026-10-13: 79
- 2026-10-12: 78
- 2026-10-10: 77
- 2026-10-09: 77
- 2026-10-07: 76
- 2026-10-06: 73
- 2026-10-04: 72
- 2026-10-03: 6

## Common questions

### What is the Vuntum MCP server?

Vuntum is an MCP server listed in the public MCP registry as com.vuntum/mcp. Sourced, dated data on consumer robots and physical AI: specs, prices, availability, evidence. This page covers its hosted endpoint (https://vuntum.com/mcp).

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

Vuntum scores 80 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 Vuntum MCP server expose?

Vuntum exposes 16 tools: get_methodology, search_robots, search_site, get_article, get_robot, and 11 more. Their descriptions and schemas cost roughly 1,563 tokens of context every time the server is loaded.

### Does the Vuntum MCP server require authentication?

No. We connected to Vuntum without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Vuntum MCP server still maintained?

Vuntum is still listed as active in the MCP registry. We last reached this channel on 16 October 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://vuntum.com/mcp
- Repository: https://github.com/RAAAAAGEEEEE/vuntum-mcp
- Website: https://vuntum.com/fr/donnees
- Changelog RSS feed: https://verifymcp.io/servers/com-vuntum-mcp/vuntum.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-vuntum-mcp/vuntum.json
- HTML version of this page: https://verifymcp.io/servers/com-vuntum-mcp/vuntum