# Mozilladatacollective Datasets MCP server

Source: https://glimind.com/server/mcp-registry%2Fcom.mozilladatacollective%2Fdatasets
Registry id: `mcp-registry/com.mozilladatacollective/datasets`
Status: live (checked 2026-10-27T01:46:55.236Z)

## Verdict

Mozilladatacollective Datasets MCP server answered 99.77% of Glimind's liveness checks over 30 days, better than 23% of MCP servers, with 1262 ms median handshake and 14 outages in 90 days. Its agent-readiness grade is A (96/100) across 3 tools, costing an agent about 1,048 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.77% | 23% of MCP servers |
| Median handshake latency | 1262 ms | 13% of MCP servers |
| p95 handshake latency | 3591 ms | — |
| Checks in 30 days | 4,966 | — |
| Outages, 90 days | 14 | — |
| Median recovery | 7 min | — |
| Agent-readiness score | 96/100 (A) | 82% of MCP servers |
| Tools | 3 | — |
| Tool-list size for an agent | ~1,048 tokens | 72% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "mozilladatacollective-datasets-mcp-serve": {
      "type": "http",
      "url": "https://mozilladatacollective.com/api/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http mozilladatacollective-datasets-mcp-serve https://mozilladatacollective.com/api/mcp
```

## Tools (3)

- `fetch`: Fetch the full public details of one Mozilla Data Collective dataset by id or slug: description, organization, task, locale, license, format, size, pricing, and
- `list_filters`: List every value the search tool's filters accept: the tasks, locales, licenses and formats present in the catalog, plus the sort and date-range options. Task a
- `search`: Search the Mozilla Data Collective catalog of AI training datasets by natural-language query, optionally narrowed by task, language, license, format, price, sam

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.