biosamples-mcp
Click on "Install 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., "@biosamples-mcpRecommend a checklist for a soil metagenome sample"
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.
Biosamples - MCP
A Model Context Protocol (MCP) server for biological sample checklist validation and recommendation.
Built as part of GSoC 2026 proposal preparation for EMBL-EBI (Project: Expose BioSamples Submission and Search Capabilities as MCP Tools for AI-Assisted Metadata Interaction).
What it does
Exposes 3 MCP tools that an LLM (e.g. Claude) can call:
Tool | Description |
| Validates sample metadata against a specific ENA checklist via BioValidator API |
| Returns all mandatory and optional fields for a given checklist ID |
| Scores sample metadata against 15 checklists and returns ranked recommendations with confidence scores |
Related MCP server: bvbrc-mcp-server
Architecture
Key findings from API research
BioValidator (
/biosamples/validate) validates JSON structure but does not enforce checklist mandatory fields — the MCP server's scoring engine fills this gap independentlyENA Browser XML API (
/ena/browser/api/xml/{id}) is the reliable public source for checklist field definitionsBioSamples JSON Schema Store (internal MongoDB) is not publicly accessible — flagged as a risk in the GSoC proposal with ENA XML as a confirmed working alternative
Validation errors return as structured
{dataPath, errors}arrays — machine-parseable and LLM-friendly
Setup
git clone https://github.com/rithvik318/biosamples-mcp
cd biosamples-mcp
python -m venv venv
venv\Scripts\activate # Windows
# source venv/bin/activate # Mac/Linux
pip install -r requirements.txtRun
python server.pyTest with MCP Inspector
npx @modelcontextprotocol/inspector python D:\biosamples-mcp\server.pyOpen http://localhost:6274 and connect using:
Command:
D:\biosamples-mcp\venv\Scripts\python.exeArguments:
D:\biosamples-mcp\server.py
Example tool calls
validate_sample
{
"sample_name": "soil sample from Delhi",
"characteristics": "{\"organism\": [{\"text\": \"soil metagenome\"}], \"collection_date\": [{\"text\": \"2024-01-01\"}], \"geographic_location_country_andor_sea\": [{\"text\": \"India\"}]}",
"checklist_id": "ERC000011"
}recommend_checklist
{
"sample_name": "soil metagenome sample",
"characteristics": "{\"organism\": [{\"text\": \"soil metagenome\"}], \"collection_date\": [{\"text\": \"2024-01-01\"}]}",
"top_n": 3
}Technologies
Python 3.10+
httpx (async HTTP)
xml.etree.ElementTree (XML parsing)
Tested with MCP Inspector v0.21.1
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rithvik318/biosamples-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server