# National Capability Benchmark (remote · ncb.envisioning.com)

Country capability scores with their confidence, for 135 countries and nine dimensions. Read-only.

- Trust score: 75/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `ncb.envisioning.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-envisioning-ncb/ncb.md), [page](https://verifymcp.io/servers/com-envisioning-ncb/ncb)

## Channel facts

- Endpoint: `https://ncb.envisioning.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**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 777 tokens (~111/item across 7 items; 7 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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 National Capability Benchmark MCP server?

National Capability Benchmark is a hosted endpoint at https://ncb.envisioning.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-envisioning-ncb 'https://ncb.envisioning.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

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

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "com-envisioning-ncb": {
      "type": "http",
      "url": "https://ncb.envisioning.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.

### 2026-11-21 (score 75, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 638 → 777
- [functional improvement] Tool coverage: 38% → 50%
- [functional] Server version: 1.0.0 → 1.1.0
- [functional] New tool “get_stories”

### 2026-11-20 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 73, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-18 (score 73)

First indexed and scored.

## MCP tools (7)

### `list_dimensions` (~51 tokens)

List the nine dimensions

The nine capability dimensions, the question each one answers, and how many indicators each has: scored, declared gaps, rejected, and conditions published beside it. Also the dataset version and the quoting contract. Start here.

### `get_country` (~92 tokens)

Read one country

One country's nine dimensions, each with score, confidence and its band, indicator count, coverage flag, trend, panel estimate where one exists, and links to the known limits that apply. Takes an ISO3 code or an English country name.

Input parameters:

- `country` (string, required): ISO3 code (BRA) or English name (Brazil)
- `indicators` (boolean): Add every observed indicator row: value, year and source

### `compare_countries` (~62 tokens)

Compare countries side by side

Two to 4 countries side by side on the nine dimensions, in the order you give them. The result is not sorted by score: the benchmark compares shapes and does not rank (D1).

Input parameters:

- `countries` (array, required): ISO3 codes or English names

### `get_stories` (~135 tokens)

Read computed stories for one country

Computed descriptive stories for any country in the frame (D192): shape_mirror (nearest capability profiles across the frame), peer_contrast (farthest shape among the 10 nearest income peers) and peer_standing (each dimension against the income-peer median, keeping thin-evidence dimensions out of headlines). Every score carries its confidence, band, indicator count, coverage flag and known limits.

Input parameters:

- `country` (string, required): ISO3 code (BRA) or English name (Brazil)
- `story` (string): One story id (shape_mirror, peer_contrast, peer_standing); omit for all available stories

### `search_indicators` (~82 tokens)

Search the indicator registry

Search the registry of indicators by words in the name or definition, and filter by dimension or status: scored, gap (no adequate dataset yet), rejected (a dataset exists and the project disqualified it) or condition (published beside a dimension, never scored).

Input parameters:

- `dimension` (string)
- `query` (string)
- `status` (string)

### `get_decision` (~66 tokens)

Read a decision

Read one entry of the decision record by number, for example D1 or D118: the methodological choice, why it was made, what it costs and what evidence would overturn it. Use it to answer "why does the benchmark do X?".

Input parameters:

- `id` (string, required)

### `get_limit` (~71 tokens)

Read a known limit

Read one known limit by id (A1, A2, ...): a place where the model produces a number that is wrong about the world. get_country lists the ids that apply to each score. Without an id, lists every limit with the dimensions and countries it covers.

Input parameters:

- `id` (string)

## Diagnostics

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

## Score history

- 2026-11-21: 75
- 2026-11-20: 74
- 2026-11-19: 73
- 2026-11-18: 73

## Common questions

### What is the National Capability Benchmark MCP server?

National Capability Benchmark is an MCP server listed in the public MCP registry as com.envisioning/ncb. Country capability scores with their confidence, for 135 countries and nine dimensions. Read-only. This page covers its hosted endpoint (https://ncb.envisioning.com/mcp).

### Is the National Capability Benchmark MCP server safe to use?

National Capability Benchmark scores 75 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 National Capability Benchmark MCP server expose?

National Capability Benchmark exposes 7 tools: list_dimensions, get_country, compare_countries, get_stories, search_indicators, and 2 more. Their descriptions and schemas cost roughly 559 tokens of context every time the server is loaded.

### Does the National Capability Benchmark MCP server require authentication?

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

### Is the National Capability Benchmark MCP server still maintained?

National Capability Benchmark 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 National Capability Benchmark MCP server?

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