fastqc_singleLABSCO SUMMARY
QC results become something you can discuss, not just a folder of HTML reports.
The async pair is what makes it usable on real data: a batch over a whole directory is queued and polled rather than blocking the session, and MultiQC then folds the individual reports into one summary you can actually read across samples.
What it is
A server that runs FastQC and MultiQC over sequencing data: one file, a directory of them, or a combined summary report — with async variants and a job queue for long runs.
What you get
- FastQC on a single FASTQ or FASTA file, returning pass, warn or fail per module
- FastQC across a directory, with a file pattern and a thread count you choose
- A MultiQC report combining the FastQC results from a directory
- Custom contaminants, adapters and limits files passed through to FastQC
- Async variants of all three, for datasets too large to wait on
- Job status and results retrieved by ID, and a queued job cancelled
Requirements
FastQC and MultiQC installed on the same machine — conda is the route the project recommends, with apt or brew plus pip as alternatives. Python, with the package installed into the environment.
Setup effort
One command — pip install git+https://github.com/bio-mcp/bio-mcp-fastqc.git
USE CASES
01
Checking one sample that looks suspicious
Run FastQC on the file and read the per-module pass, warn and fail status.
02
Screening a whole run before you commit compute to it
Run the batch over the directory with a file pattern, then combine the results into one report.
03
Handling a dataset too big to wait on
Submit the batch asynchronously, then poll for status and collect the result when it is done.
04
Checking for an adapter you know is in the library
Pass your own adapters or contaminants file into the run instead of relying on the defaults.
05
Stopping a run you started by mistake
Cancel the queued job rather than waiting for it to finish and burn the compute.
9 tools
Listed in project docs. Your client may show a different list.
fastqc_batchmultiqc_reportfastqc_single_asyncfastqc_batch_asyncmultiqc_report_asyncget_job_statusget_job_resultcancel_jobBEFORE YOU INSTALL
What to know first
Tools you get
9 tools named in the project's documentation.
Requires
python on PATH
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install git+https://github.com/bio-mcp/bio-mcp-fastqc.gitMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"bio-fastqc": {
"command": "python",
"args": [
"-m",
"src.server"
],
"cwd": "<YOUR_PATH_TO_BIO_MCP_FASTQC>"
}
}
}
