Evo2 MCP
About
MCP server for generating, scoring and embedding genomic sequences using Evo 2
Details
- Author
- Unknown
- Categories
- Other, AI
Jump to
The evo2-mcp server exposesEvo 2as a Model Context Protocol (MCP) server, providing tools for genomic sequence analysis. Any MCP-compatible client can use these tools to score, embed, and generate DNA sequences.
- Sequence Scoring: Compute log probabilities for DNA sequences
- Sequence Embedding: Extract learned representations from intermediate model layers
- Sequence Generation: Generate novel DNA sequences with controlled sampling
- Variant Effect Prediction: Score SNP mutations for variant prioritization
- Multiple Model Checkpoints: Support for 7B, 40B, and 1B parameter models
- Install Evo2 dependencies: SeeInstallation Guidefor details.
conda install -c nvidia cuda-nvcc cuda-cudart-dev
conda install -c conda-forge transformer-engine-torch=2.3.0
pip install flash-attn==2.8.0.post2 --no-build-isolation
pip install evo2
- Install evo2-mcp:
pip install evo2-mcp
- Activate MCP Server: Add the following to yourmcp.jsonconfiguration:
{
"mcpServers": {
"evo2-mcp": {
"command": "python",
"args": ["-m", "evo2_mcp.main"]
}
}
}
For detailed installation instructions, see theInstallation Guide.
Once installed, the server can be accessed by any MCP-compatible client. For available tools and usage examples, see theTools Documentation.
- score_sequence- Evaluate DNA sequence likelihood
- embed_sequence- Extract feature representations
- generate_sequence- Generate novel DNA sequences
- score_snp- Predict variant effects
- get_embedding_layers- List available embedding layers
- list_available_checkpoints- Show supported model checkpoints
See theTools Documentationfor detailed API reference and examples.
- Installation Guide- Detailed installation instructions
- Tools Reference- Complete API documentation and usage examples
- Development Guide- Contributing and testing information
- Changelog- Version history and updates
You can also find this project onBioContextAI, the community hub for biomedical MCP servers.
If you use evo2-mcp in your research, please cite:
@software{evo2_mcp, author = {Kreuer, Jules}, title = {evo2-mcp: MCP server for Evo 2 genomic sequence operations}, year = {2025}, url = {https://github.com/not-a-feature/evo2-mcp}, version = {0.2.3} }
For the underlying Evo 2 model, please also cite the original Evo 2 publication.
The banner image in this repository is a modified version of the originalEvo 2 bannerfrom theEvo 2 project, which is released under theApache 2.0 License. It was modified using Google Gemini “Nanobana” and GIMP.
- Prerequisites
- Step-by-Step Installation
- Troubleshooting
- Development Installation (Without Evo2)
- Verifying Installation
- Available Tools
- Checkpoint Selection
- Parameters
- Using the Dummy Implementation
- Running Tests
- Development Setup
- Contributing
- Environment Variable
- Dummy Implementation Details
- GitHub Actions
- When to Use Each Mode
- Implementation Details
- Unreleased
- [](https://evo2-mcp.readthedocs.io/en/latest/changelog.html#id1)<<<[0.2.3] - 2026-04-13
- 0.2.2 - 2025-10-23
- 0.2.0 - 2025-10-20
- 0.1.0 - 2025-10-19
Control anaerobic digestion modeling (ADM1) using natural language.
Detects bias in AI model outputs across protected characteristics — statistical parity checks, disparate impact analysis, intersectional fairness audits, and EU AI Act Article 10 compliance reporting.
Audited tarot, I Ching, and Xiao Liu Ren divination MCP server. Local seeded entropy; the model only interprets JSON output.
Detect fabrication and hallucination in any LLM output. Score responses from GPT-4o, Claude, Gemini, Llama and 30+ models. Free tier included.
Bioinformatics data for AI agents — gene search, protein structures, clinical variants, PubMed literature, and DNA sequences via NCBI and UniProt. No API key required.
An MCP-compatible server providing atomistic simulation capabilities through ASE, pymatgen, etc.
Interact with Omics AI Explorer networks for genomics research and data analysis.
Real-time access to 1000 Genomes Project dataset
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
