# Usedby MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.usedby%2Fusedby
Registry id: `mcp-registry/ai.usedby/usedby`
Status: live (checked 2026-11-22T19:03:48.686Z)

## Verdict

Usedby MCP server answered 99.97% of Glimind's liveness checks over 30 days, better than 34% of MCP servers, with 213 ms median handshake and 3 outages in 90 days. Its agent-readiness grade is A (90/100) across 7 tools, costing an agent about 3,718 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.97% | 34% of MCP servers |
| Median handshake latency | 213 ms | 57% of MCP servers |
| p95 handshake latency | 737 ms | — |
| Checks in 30 days | 6,942 | — |
| Outages, 90 days | 3 | — |
| Median recovery | 6 min | — |
| Agent-readiness score | 90/100 (A) | 60% of MCP servers |
| Tools | 7 | — |
| Tool-list size for an agent | ~3,718 tokens | 34% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "usedby-mcp-server": {
      "type": "http",
      "url": "https://www.usedby.ai/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http usedby-mcp-server https://www.usedby.ai/mcp
```

## Tools (7)

- `company_stack`: Tools a company publicly uses according to usedby, strongest proof first, each with its proof level (job-post signals last) and source page. Each `listed` line 
- `compare`: Two tools side by side: public customers with their proof mix, top industries, the companies on both (every proof level, each side's level given), and vendor fa
- `recent_changes`: Companies newly listed as customers by tool vendors in the last N days, optionally for one tool. Departures are not published. Each `listed` line carries its `p
- `search_tools`: Find AI and software tools tracked on usedby by name, other product name, or what they do (category, topic or task, in English, French, Spanish, German or Portu
- `shortlist_tools`: Check exact documented requirements (integrations, data residency, DPA, languages, an exact operation) for up to three tools from the accepted evidence catalog 
- `what_peers_use`: Use this when someone asks which tool to choose for a task: it returns the tools that comparable companies publicly use, by task category, industry and size ban
- `who_uses`: Companies that publicly use a tool, strongest proof first, each with its proof level (CONFIRMED, DECLARED: the company states it, OBSERVED, or SIGNAL: a job pos

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