Skip to main content

Natural language interface for celltype marker query through MCP.

Project description

biomarker-MCP

Natural language interface for celltype marker query through MCP.

🪩 What can it do?

  • query celltype marker from CellMarker database by natural language
  • will add more database

❓ Who is this for?

  • Anyone who wants to do query celltype marker with natural language!
  • Agent developers who want to query cell markers for their applications

🌐 Where to use it?

You can use biomarker-mcp in most AI clients, plugins, or agent frameworks that support the MCP:

  • AI clients, like Cherry Studio
  • Plugins, like Cline
  • Agent frameworks, like Agno

🎬 Demo

A demo showing scRNA-Seq cell cluster analysis in a AI client Cherry Studio using natural language based on biomarker-mcp

https://github.com/user-attachments/assets/71268f6f-c74d-4142-ad7a-893b411d748a

📚 Documentation

scmcphub's complete documentation is available at https://docs.scmcphub.org

🏎️ Quickstart

Install

Install from PyPI

pip install biomarker-mcp

you can test it by running

biomarker-mcp run

run biomarker-mcp locally

Refer to the following configuration in your MCP client:

check path

$ which biomarker 
/home/test/bin/biomarker-mcp
"mcpServers": {
  "biomarker-mcp": {
    "command": "/home/test/bin/biomarker-mcp",
    "args": [
      "run"
    ]
  }
}

run biomarker-server remotely

Refer to the following configuration in your MCP client:

run it in your server

biomarker-mcp run --transport shttp --port 8000

Then configure your MCP client in local AI client, like this:


"mcpServers": {
  "biomarker-mcp": {
    "url": "http://localhost:8000/mcp"
  }
}

🤝 Contributing

If you have any questions, welcome to submit an issue, or contact me(hsh-me@outlook.com). Contributions to the code are also welcome!

Citing

If you use biomarker-mcp in for your research, please consider citing following work:

Congxue Hu, Tengyue Li, Yingqi Xu, Xinxin Zhang, Feng Li, Jing Bai, Jing Chen, Wenqi Jiang, Kaiyue Yang, Qi Ou, Xia Li, Peng Wang, Yunpeng Zhang, CellMarker 2.0: an updated database of manually curated cell markers in human/mouse and web tools based on scRNA-seq data, Nucleic Acids Research, Volume 51, Issue D1, 6 January 2023, Pages D870–D876, https://doi.org/10.1093/nar/gkac947

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

biomarker_mcp-0.1.0.tar.gz (2.9 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

biomarker_mcp-0.1.0-py3-none-any.whl (3.0 MB view details)

Uploaded Python 3

File details

Details for the file biomarker_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: biomarker_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 2.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for biomarker_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 38758ac513d612a4ae1daf79a346621a96e8d7baaf45b3e0322f5c5da2ea99e7
MD5 46cdeb7ff14dd8a770b2991d5494d494
BLAKE2b-256 e4dc4c722e0f46b21da2144cf1bfb66c004a5e9ce1dd9a3f87fecbe01198e0d1

See more details on using hashes here.

Provenance

The following attestation bundles were made for biomarker_mcp-0.1.0.tar.gz:

Publisher: publish.yml on scmcphub/biomarker-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file biomarker_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: biomarker_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 3.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for biomarker_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 dd8dee017f933296cac2a438c80675cf2c0ac9dc59eb3b1c88aa422a11d4a776
MD5 20efa6e42f6745909caca24810713017
BLAKE2b-256 6afb8dad48e15ea4955a64e74e7f0cef8036ab0fdd9eab8bc0ac51338b01fc5e

See more details on using hashes here.

Provenance

The following attestation bundles were made for biomarker_mcp-0.1.0-py3-none-any.whl:

Publisher: publish.yml on scmcphub/biomarker-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page