Metaplex MCP Server

Read Processing and Quality Control Toolkit for Dual-Indexed Metabarcoding

Local serverstdioPython

What is the Metaplex MCP server?

Read Processing and Quality Control Toolkit for Dual-Indexed Metabarcoding. That is what the metaplex mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

For a full list of MetaPlex primers and library preparation information, see here

The tools it exposes

The server publishes 4 tools. What each one is for:

  • Input — The remultiplexing process can start from either a raw unmapped bam file such as what is given by an Ion Torrent sequencer, or a fastq/fastq.gz file
  • Output — Remultiplexing produces a single gzipped fastq containing all sequences where both a forward and reverse barcode were found
  • Inputs — This workflow requires starting from data which has been demultiplexed utilizing QIIME2. Specifically, we start with a data type
  • Outputs — Return : Integer value of maximum number of index jumps (false reads) expected in a single sample

Getting it running

metaplex on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Metaplex's toolset — Input, Output, Inputs and 1 more — is a fair guide to whether it matches your workflow. It is maintained by Nick Gabry; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
InputThe remultiplexing process can start from either a raw unmapped bam file such as what is given by an Ion Torrent sequencer, or a fastq/fastq.gz file. Aside from the sequences, all that is needed is a .csv containing all
OutputRemultiplexing produces a single gzipped fastq containing all sequences where both a forward and reverse barcode were found.
InputsThis workflow requires starting from data which has been demultiplexed utilizing QIIME2. Specifically, we start with a data type SampleData[SequencesWithQuality], though it isn't necessary for the data to have quality va
OutputsReturn : Integer value of maximum number of index jumps (false reads) expected in a single sample

How to install the Metaplex MCP server

{
  "mcpServers": {
    "metaplex": {
      "command": "uvx",
      "args": ["metaplex"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Metaplex to Input.
  • Use Metaplex to Output.
  • Use Metaplex to Inputs.

Frequently asked questions

It connects Metaplex to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Input, Output, Inputs, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Metaplex directly.