# Livevariant MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.livevariant%2Flivevariant
Registry id: `mcp-registry/io.github.livevariant/livevariant`
Status: live (checked 2026-10-27T02:18:39.926Z)

## Verdict

Livevariant MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 906 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (91/100) across 9 tools, costing an agent about 4,239 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 | 906 ms | 24% of MCP servers |
| p95 handshake latency | 3256 ms | — |
| Checks in 30 days | 4,951 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 91/100 (A) | 71% of MCP servers |
| Tools | 9 | — |
| Tool-list size for an agent | ~4,239 tokens | 40% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "livevariant-mcp-server": {
      "type": "http",
      "url": "https://livevariant.com/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http livevariant-mcp-server https://livevariant.com/mcp
```

## Tools (29)

- `assign_variant`: Assign a user to a variant for an experiment
- `build_test`: Creates a LiveVariant test and returns every URL needed to run it, plus a freshly generated stats secret. Pass `variants` to test one element, or `slots` to tes
- `create_experiment`: Create a new A/B test experiment
- `create_metric`: Create a new metric
- `create_variant`: Create a new variant for an experiment
- `delete_experiment`: Delete an experiment
- `delete_metric`: Delete a metric
- `delete_variant`: Delete a variant
- `generate_priors`: Takes YOUR estimate of how each variant will perform and converts it into the prior the model starts from, so a test does not spend its first visitors rediscove
- `get_experiment`: Get details of a specific experiment
- `get_experiment_results`: Get results of an experiment
- `get_metric`: Get details of a metric
- `get_stats`: Fetches a test's results and works out what they mean. Alongside the raw counts it returns the probability that each combination is genuinely best and the expec
- `get_test_status`: Reports what the deployment's registry knows about a test: whether it is claimed into an account (and by which organization), and whether each redirect destinat
- `get_variant`: Get details of a variant
- `inspect_test`: Decodes a test and describes it: slots, variants, context, and whether it can be served by redirect. Also lints it for the mistakes that only show up once a cam
- `list_experiments`: List all experiments
- `list_metrics`: List all metrics
- `list_tests`: Lists tests registered to the signed-in account, newest first, with cursor pagination and an optional case-insensitive name filter. Only exists on deployments w
- `list_variants`: List variants of an experiment
- `register_test`: Registers a test you built earlier to the organization a publishable key belongs to, so it shows under My tests and its stats are readable from the dashboard wi
- `start_experiment`: Start an experiment
- `stop_experiment`: Stop an experiment
- `track_event`: Track an event for an experiment
- `update_experiment`: Update an existing experiment
- `update_metric`: Update a metric
- `update_variant`: Update a variant
- `upload_image`: Uploads an image to the deployment's asset store and returns its URL, for use as a variant's `image` (email tests) or `url`. The returned URL is deliberately no
- `variant_brief`: Returns the constraints to write or generate test variants against, for email or web, plus the rules that decide whether a test can be read at all once it runs.

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