# Cuevr (remote · www.cuevr.com)

Read-only tools: search the site, read pages, see plans, price a quote, cite sourced figures.

- Trust score: 86/100 (high trust)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `www.cuevr.com`: 86/100 (this document), [markdown](https://verifymcp.io/servers/com-cuevr-mcp/www.md), [page](https://verifymcp.io/servers/com-cuevr-mcp/www)

## Channel facts

- Endpoint: `https://www.cuevr.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2512 tokens (~193/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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.
  - Structured output schemas are declared (23% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

Cuevr is a hosted endpoint at https://www.cuevr.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-cuevr-mcp 'https://www.cuevr.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

### 2026-11-17 (score 86, 0)

- [security] Stability: 0.97 → pass

### 2026-11-16 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-10 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-08 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-06 (score 81, +1)

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

### 2026-11-04 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `chercher` (~187 tokens)

Search the site

Searches the site's pages and returns the passages that answer, each with its URL and section anchor, and a confidence. Use it for facts about the product: can it do X, a feature, integrations, security, GDPR, a sector. Steps in the app: comment_faire; prices: voir_offres or devis; comparison: comparer. Returns excerpts: read the page with lire_page before stating a detail they lack. Confidence moyenne or faible: first say what the site does not cover, then give the closest page.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `limite` (integer): Maximum number of passages (1 to 10, default 5).
- `requete` (string, required): The buyer's question or its key words, in the language of the answer.

### `lire_page` (~189 tokens)

Read a page

Returns the text of one page of the site, or of one section by its anchor, with its exact URL. Use it before stating a detail that is not in an excerpt returned by another tool: a condition, a limit, a legal point, how a feature works. Give a URL returned by a tool; with its #anchor, only that section is returned, which is shorter. Reads only pages of this site: to find a page, use chercher.

Input parameters:

- `ancre` (string): Anchor of one section of the page (without #): returns that section only.
- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `url` (string, required): URL or path of a page of this site, as returned by a tool. With a #anchor, only that section is returned.

### `resoudre_probleme` (~192 tokens)

Solve a sales problem

Diagnoses a sales problem of the buyer's team: likely causes, what the product does for each with the page proving it, and the pages to quote (sector page first). Use it when the buyer describes their problem or asks how the product would help their company: we lose to cheaper rivals, clients haggle over our fees, prospects go silent. Pass secteur when known. For selling advice without the product, use conseils. Returns summaries: read a page with lire_page for details.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `secteur` (string): Sector of the buyer, when known (agences, conseil, esn, saas).
- `symptome` (string, required): The problem in the buyer's words (e.g. our prospects stop replying after the proposal).

### `conseils` (~218 tokens)

Sales advice

Returns selling advice published on the site (follow-ups, proposal structure, qualification, pricing, negotiation, tenders), each with its page to quote. Use it for a method question that does not depend on the product: how many follow-ups without being pushy, what goes in a proposal, how to qualify a deal. When the buyer describes their own problem and asks how the product helps, use resoudre_probleme; for a product fact, chercher. Returns advice only, no product features or prices.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `requete` (string): Words to look for in the advice.
- `secteur` (string): Sector of the buyer, when known (agences, conseil, esn, saas).
- `sujet` (string): Topic: closing, relances (follow-ups), structure, qualification, prix (pricing), negociation, appels-offres (tenders), cycle.

### `calculer_roi` (~279 tokens)

Estimate the return on investment

Runs the ROI calculator published on the site, with exactly its formulas and bounds. Use it when the buyer asks what the product would bring them: deals won, revenue, time saved. Call it without values to get its inputs (label, bounds, default), ask the buyer for their own figures, then pass x1, x2… Returns each result with its calculation, the inputs used, the published assumptions and the page to quote. For a price, use devis; for a published statistic, citer_chiffre.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `x1` (number): Proposals sent per month, whole team (proposals): 1 to 200, default 10.
- `x2` (number): Current close rate (%): 0 to 100, default 20.
- `x3` (number): Average signed deal value (€ excl. VAT): 0 to 1000000, step 5000, default 10000.
- `x4` (number): Close rate increase (points): 0 to 50, default 10.
- `x5` (number): Number of sales reps (sales reps): 1 to 50, default 1.

Output parameters:

- `avertissement` (string)
- `calculateur` (string)
- `consigne` (string): What to do with the result.
- `entrees` (array)
- `erreur` (string): Why the call was refused and what to fix.
- `hypotheses` (array)
- `langue` (string): Language of the answer.
- `resultats` (array)
- `url` (string): Page of the calculator, to quote.

### `comment_faire` (~172 tokens)

How to do it in the product

Returns the steps from the user documentation for a task in the app, with the app labels as written and the URL of the section to quote. Use it when the buyer asks how to do something in the product: how do I invite a colleague, where do I see why a prospect declined, how do I export a PDF, how do I create an API key. To know whether the product can do something, or what a feature brings, use chercher. Covers the documentation only: no prices, no comparisons.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `question` (string, required): What the person wants to do, in their words (e.g. share a proposal with a decision-maker).

### `atouts` (~171 tokens)

What the product does best

Lists the product's published capabilities with their promise and proof page, the problems it solves, what the plan includes and the published comparison pages, ranked by the need given. Use it when the buyer must choose or asks why this product: what does it do best, is it right for our need. To compare with a named tool, use comparer; for one feature, chercher; for prices, voir_offres. Facts about this product only: about other tools, only what the comparison pages publish.

Input parameters:

- `besoin` (string): The buyer's need or criteria, in their words (e.g. read tracking, tenders). Ranks the capabilities.
- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.

### `comparer` (~183 tokens)

Compare with another tool

Returns the passages of the published comparison pages that answer, each with its page to quote, and the tools a page covers. Use it when the buyer compares this product with another tool or a kind of tool: Cuevr or PandaDoc, an alternative to Word, Cuevr or an e-signature tool. To know if it works with a tool already in use (keep Docusign, an integration): chercher; without a named tool: atouts. A tool no page covers is listed in nonCouverts: say nothing about it.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `question` (string, required): The buyer's comparison in their words, with the tools named (e.g. Cuevr or PandaDoc for a team of 10).

### `voir_offres` (~142 tokens)

See plans and prices

Returns the plans, the price per user (amount, currency, period, taxes), what each plan includes, the free trial and its conditions, and the trial and demo links, as the pricing page publishes them. Use it for: how much per user, is yearly billing cheaper, is there a free trial, is a card needed, what is included. For any total (a team, several users, one user over a year), call devis: never multiply a price yourself. Returns no total.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.

### `devis` (~208 tokens)

Price a quote

Prices a number of users (1 or more) from the published prices: unit price, total per period and per year, yearly saving, the calculation and the pricing page. Use it for any total: a team, several users, or one user over a year, even as an example; call it as soon as a team size or period is known. Never compute a total yourself. Unit prices and plans: voir_offres.

Input parameters:

- `facturation` (string): Billing: mensuel (monthly) or annuel (yearly). Without it, both.
- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `plan` (string): Key or name of the plan, as returned by voir_offres. Without it, every plan.
- `sieges` (integer, required): Number of users (seats) to price, as the buyer gave it. Ask for it rather than assume one.

Output parameters:

- `consigne` (string): What to do with the result.
- `erreur` (string): Why the call was refused and what to fix.
- `langue` (string): Language of the answer.
- `plans` (array)
- `sieges` (integer): Number of users priced.
- `source` (object)

### `citer_chiffre` (~163 tokens)

Quote a sourced figure

Returns the figures published on the site (statistics, results, market data) with their value, label, source URL, date and the page that publishes them. Use it before quoting any figure that is not a price. Quote the figure exactly as returned, with its source and date; never round or extrapolate it. For prices use voir_offres or devis; for an estimate for the buyer, calculer_roi. Returns only published figures: when none matches, give no figure.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `requete` (string): Words to look for in the figure or its label. Without it, all figures.

Output parameters:

- `chiffres` (array)
- `consigne` (string): What to do with the result.
- `erreur` (string): Why the call was refused and what to fix.
- `langue` (string): Language of the answer.

### `demander_demo` (~202 tokens)

Prepare a demo request link

Returns a link to the demo request form, prefilled with the details given. Use it outside the browser when the buyer wants a demo or to talk to the team. Opening the link shows the filled form: the person, or their browser agent, sends it, then the person picks and confirms the time slot in the calendar. Sends nothing by itself. To try the product alone, use demarrer_essai.

Input parameters:

- `email` (string): Work email address of the person. Personal mailboxes (Gmail, Outlook, Yahoo…) are refused.
- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.
- `nom` (string): Last name of the person.
- `prenom` (string): First name of the person.
- `societe` (string): Company of the person.
- `telephone` (string): Phone number of the person (optional).

### `demarrer_essai` (~99 tokens)

Start a free trial

Returns the sign-up link of the free trial and its conditions. Use it when the buyer wants to start a trial now. Whether a trial exists and its conditions, together with prices, come from voir_offres. Creates no account: the person signs up and accepts the terms.

Input parameters:

- `langue` (string, required): Language of the buyer's question (en, fr, es): always pass it, the pages and answers are in this language.

## Diagnostics

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

## Score history

- 2026-11-21: 86
- 2026-11-20: 86
- 2026-11-19: 86
- 2026-11-18: 86
- 2026-11-17: 86
- 2026-11-16: 86
- 2026-11-15: 85
- 2026-11-14: 85
- 2026-11-13: 84
- 2026-11-12: 84
- 2026-11-11: 83
- 2026-11-10: 83
- 2026-11-09: 82
- 2026-11-08: 82
- 2026-11-07: 81
- 2026-11-06: 81
- 2026-11-05: 80
- 2026-11-04: 80
- 2026-11-03: 79
- 2026-11-02: 79
- 2026-11-01: 79
- 2026-10-31: 78
- 2026-10-30: 78
- 2026-10-29: 77
- 2026-10-28: 77
- 2026-10-27: 76
- 2026-10-26: 76
- 2026-10-25: 75
- 2026-10-24: 75
- 2026-10-23: 74

## Common questions

### What is the Cuevr MCP server?

Cuevr is an MCP server listed in the public MCP registry as com.cuevr/mcp. Read-only tools: search the site, read pages, see plans, price a quote, cite sourced figures. This page covers its hosted endpoint (https://www.cuevr.com/mcp).

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

Cuevr scores 86 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 Cuevr MCP server expose?

Cuevr exposes 13 tools: chercher, lire_page, resoudre_probleme, conseils, calculer_roi, and 8 more. Their descriptions and schemas cost roughly 2,405 tokens of context every time the server is loaded.

### Does the Cuevr MCP server require authentication?

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

### Is the Cuevr MCP server still maintained?

Cuevr 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 Cuevr MCP server?

VerifyMCP ran 13 checks on Cuevr, 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://www.cuevr.com/mcp
- Website: https://www.cuevr.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-cuevr-mcp/www.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-cuevr-mcp/www/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-cuevr-mcp/www.json
- HTML version of this page: https://verifymcp.io/servers/com-cuevr-mcp/www
