Maftools-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Maftools-MCPGenerate an oncoplot for the top 10 mutated genes in my MAF file."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Maftools-MCP
Maftools-MCP exposes R maftools analyses through the Model Context Protocol (MCP). An MCP-compatible client can translate a natural-language request into calls for mutation summaries, oncoplots, cohort comparisons, mutation signatures, clinical enrichment, survival analyses, and copy-number visualization.
The server includes the 59 tools counted in the manuscript, plus the
export_r_script validation utility: 60 registered tools in total. See the
complete tool reference for inputs, defaults, outputs and
underlying R functions. R code is executed through rpy2. ANNOVAR annotation is an
optional external workflow; the server's conversion tool consumes annotated
multianno files, not unannotated VCFs.
Installation
The packaged Docker image is available from Docker Hub:
docker pull lin97/maftools-mcp:v.1.1.0For an immutable image reference, use the recorded digest:
docker pull lin97/maftools-mcp@sha256:d7dc8ed2ea12c1a9ee9e60a4f304ab056a53e5cfa1d4780871603ed875ef2b86For setup instructions, MCP client configuration, and usage examples, see the Maftools-MCP tutorial.
Related MCP server: Liana-MCP
Code Availability
The Maftools-MCP source code is publicly available in this GitHub repository:
https://github.com/linchinghsuan/maftools-mcp
The Python MCP server source is located in src/maftools_mcp/.
The repository also includes the complete tool reference, machine-readable tool
schema, and curated validation materials in docs/ and
validation/.
The packaged environment is documented in
docs/environment.md, including the Docker image digest
and the observed Python, R, maftools, and ANNOVAR workflow versions. The
machine-readable image record is available at
environment/observed-docker-image.json.
Validation materials
The validation directory contains the detailed records supporting the Supplementary Tables. The corresponding materials are organized as follows:
Supplementary table | Validation materials |
Supplementary Table S1 |
|
Supplementary Table S2 |
|
Supplementary Table S3 |
|
Supplementary Table S4 |
|
These directories include the relevant inputs, execution records, generated outputs, comparison files, scripts, and figures where available. The validation materials are provided for review and provenance; ANNOVAR itself and restricted third-party data or databases are not redistributed.
License
Maftools-MCP code is available under the MIT License. R, maftools, ANNOVAR and other dependencies retain their own licenses. This repository does not grant redistribution rights for third-party datasets or ANNOVAR assets.
This server cannot be deployed
Maintenance
Related MCP Connectors
Cancer gene co-occurrence and exclusivity in tumour cohorts, with confound controls and exact tests.
Knowledge graph ingestion, entity search, ontology analysis, and CoPass scoring.
Free oncology data (research, trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions.
CIViC — Clinical Interpretation of Variants in Cancer.
Related MCP Servers
- AlicenseCqualityDmaintenanceA server that enables AI assistants to interact with cancer genomics data from cBioPortal, allowing users to explore cancer studies, access genomic data, and retrieve mutations and clinical information.176MIT
- FlicenseNot gradedqualityCmaintenanceEnables natural language interface for single-cell RNA-Seq analysis using Liana. Supports reading/writing scRNA-Seq data, cell-cell communication analysis, and visualization through circle plots and dotplots.1-
- AlicenseNot gradedqualityDmaintenanceEnables natural language interactions with cancer pharmacogenomics data through the DROMA platform, supporting drug-omics association analysis, dataset management, molecular profile loading, and treatment response analysis across multiple research projects.1Mozilla Public 2.0
- FlicenseNot gradedqualityCmaintenanceProvides a natural language interface for single-cell RNA-Seq analysis using the decoupleR framework. It enables users to perform biological pathway inference, data clustering, and visualization through MCP-compatible AI clients.4-