MCP Sequence Simulation Server

You have a dedicated MCP server that simulates DNA and amino acid sequences, runs evolutionary models, and produces data for testing, teaching, or benchmarking. You can generate sequences, simulate sequencing reads, mutate and evolve sequences, and analyze phylogenetic scenarios all within a single, extensible MCP framework.

How to use

You use this MCP server by connecting your MCP client to the local MCP runtime, then invoking specific tools to generate or manipulate sequences, simulate reads, or evolve sequences over time. Each tool exposes parameters you can tune, such as sequence length, composition, model type, mutation rates, and output format. You can combine tools in workflows to reproduce complex evolutionary scenarios, track lineages, or generate datasets for phylogenetic studies.

How to install

Prerequisites: you need Node.js and npm installed on your system.

Install dependencies and build the MCP server locally.

npm install
npm run build

Configuration and usage notes

Configure the MCP server as a local stdio service to run on your machine. The example shows starting the server with Node and pointing to the built server file.

{
  "mcpServers": {
    "sequence_sim": {
      "command": "node",
      "args": ["dist/server.js"]
    }
  }
}

Examples of what you can do with the tools

• Generate DNA sequences with models like random, markov, or codon-biased; specify length, GC content, and seed for reproducibility.
• Generate protein sequences with options, including random, hydrophobic-bias, or disorder-prone compositions.
• Simulate FASTQ reads with configurable read length, coverage, error models, and quality scores.
• Mutate sequences with substitutions, indels, and iteration-based tracking for both DNA and proteins.
• Evolve sequences across generations with fitness functions and lineage tracking.
• Simulate phylogenies on different substitution models and formats (FASTA, NEXUS, PHYLIP).

All outputs include detailed statistics and can be exported in FASTA, NEXUS, PHYLIP, or JSON formats to support downstream analyses.

Available tools

generateDna

Generate random DNA sequences using various models with parameters for length, GC content, seed, and output format.

generateProtein

Create random protein sequences with different biases or compositions, including hydrophobic or disorder-prone tendencies.

simulateFastq

Produce FASTQ reads from a reference sequence with configurable read length, coverage, error model, and quality scores.

mutateSequence

Apply substitutions and indels to DNA or protein sequences across multiple iterations.

evolveSequence

Simulate sequence evolution across generations with population size, mutation rate, and fitness-based selection.

simulatePhylogeny

Simulate evolution on phylogenetic trees under multiple substitution models and output formats.