# Pipe2 MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.pipe2%2Fmcp
Registry id: `mcp-registry/ai.pipe2/mcp`
Status: live (checked 2026-10-26T20:36:20.421Z)

## Verdict

Pipe2 MCP server answered 100% of Glimind's liveness checks over 30 days, better than 42% of MCP servers, with 908 ms median handshake and 4 outages in 90 days. Its agent-readiness grade is A (100/100) across 5 tools, costing an agent about 703 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 | 908 ms | 27% of MCP servers |
| p95 handshake latency | 2937 ms | — |
| Checks in 30 days | 4,917 | — |
| Outages, 90 days | 4 | — |
| Median recovery | 3 min | — |
| Agent-readiness score | 100/100 (A) | 94% of MCP servers |
| Tools | 5 | — |
| Tool-list size for an agent | ~703 tokens | 82% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "pipe2-mcp-server": {
      "type": "http",
      "url": "https://mcp.pipe2.ai/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http pipe2-mcp-server https://mcp.pipe2.ai/mcp
```

## Tools (5)

- `get_pipeline_run_status`: Check the status of a pipeline run. Returns status (pending/running/completed/failed), output data, error messages, timestamps, and generated asset URLs.
- `get_pipeline_schema`: Get the input schema for a specific pipeline. Returns the JSON Schema describing required and optional input fields. Use this before running a pipeline to under
- `list_pipelines`: List all available AI video/image pipelines. Returns name, slug, description, category, credit cost, and required providers for each active pipeline.
- `request_upload`: Request a presigned S3 upload URL for a file. Use this for pipeline inputs that require file URLs (e.g., images, videos, audio). **Two-step upload flow:** 1. Ca
- `run_pipeline`: Run an AI pipeline by slug with the given input. Use list_pipelines to discover available pipelines and get_pipeline_schema to see required inputs. Returns a ru

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