# Xpansion Xfms MCP server

Source: https://glimind.com/server/mcp-registry%2Fdev.xpansion%2Fxfms
Registry id: `mcp-registry/dev.xpansion/xfms`
Status: live (checked 2026-10-27T06:19:32.358Z)

## Verdict

Xpansion Xfms MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 879 ms median handshake and 1 outage in 90 days. Its agent-readiness grade is A (98/100) across 7 tools, costing an agent about 2,559 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 42% of MCP servers |
| Median handshake latency | 879 ms | 22% of MCP servers |
| p95 handshake latency | 3171 ms | — |
| Checks in 30 days | 4,980 | — |
| Outages, 90 days | 1 | — |
| Median recovery | 26.4 h | — |
| Agent-readiness score | 98/100 (A) | 91% of MCP servers |
| Tools | 7 | — |
| Tool-list size for an agent | ~2,559 tokens | 49% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "xpansion-xfms-mcp-server": {
      "type": "http",
      "url": "https://xfms.vercel.app/mcp/"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http xpansion-xfms-mcp-server https://xfms.vercel.app/mcp/
```

## Tools (7)

- `benchmark`: The live test: the 5 proven models and 1 promising newcomer from discovery do the person's real tasks side by side, every requirement is judged, and the results
- `compare`: Same live test as benchmark, but on the models the person names (model_ids). Needs a finished discover session so every requirement is judged. Estimate first, t
- `discover`: Discovery: finds the true requirements of the person's job before any model is chosen. Start with purpose: the reply carries the discovery instructions and the 
- `field_results`: Results from real comparisons on Model Source for one kind of job (call with no job_type for the list): which models passed, how often, which won, typical cost 
- `pick`: The single best proven model for a job worked out with discover, with why and the runners-up. Pass the discover session.
- `rank`: The full shortlist for a job worked out with discover: 5 proven models and 1 promising newcomer, each with its standing on every requirement, plus near misses a
- `watch_job`: Saves a finished job for XF Model Watch, which re-tests it as new models arrive and emails the person only when a model passes every must-have and ranks higher 

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