MCP.Market

BioHarbor MCP server

by danielLuo2·io.github.danielLuo2/bioharbor·v0.1.6
No reviews yet

Run real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.

A85/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

0 stars446 downloads/wk

Reviews

Write one

Nobody has reviewed BioHarbor yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

BioHarbor tools (7, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • cancel_jobwrite action

    Cancel a background job that has not started running yet.

  • describe_tool

    Explain how an analysis tool runs before calling it.

  • get_job

    Check a background job and get its result once it has finished.

  • gpu_status

    Show live GPU memory and utilisation on this machine.

  • list_databases

    List the sequence databases that search_homologs can search.

  • list_jobs

    List recent background jobs, newest first.

  • read_file

    Read a text output file written by a BioHarbor tool.

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

1 medium
  • Code scan21 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 3 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    bioharbor-0.1.6/src/bioharbor/tools/structure.py: …roteinFolding.from_pretrained(MODEL_ID).eval() if device.startswith("cuda…
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How BioHarbor compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 73% of 4,460 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
446
more than 85% of 1,538 AI and agents servers with a package

What its tools let an agent do: 6 read · 1 delete

Release history: 2 versions in the registry since 2026-10-07, latest 2026-10-10, typically one every 3 days.

Install BioHarbor in Claude Code, Cursor or VS Code

claude mcp add bioharbor -- uvx bioharbor
Add to Cursor

What the publisher says

From the BioHarbor repository's README, as published. We do not edit it. Read it on GitHub

BioHarbor

Run real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.

🧪 Alpha (v0.1). Sequence tools, homology search (MMseqs2) and structure prediction

(ESMFold, validated on RTX 5090) work. Feedback welcome — see the roadmap.

BioHarbor is an MCP server that lets AI agents such as Claude, Cursor and Codex execute bioinformatics tools — not just look things up. Agents ask for an analysis; BioHarbor validates the input, schedules it on a GPU with room, records exactly how it ran, and hands back a compact, agent-readable summary.

<!-- mcp-name: io.github.danielLuo2/bioharbor -->

Why another bio MCP server?

Most bio MCP servers wrap databases (UniProt, PDB, PubMed…). Use them — BioHarbor complements them by running the compute:

Quick start

pip install bioharbor
bioharbor doctor             # checks Python, GPUs, workspace, tools
bioharbor setup-db swissprot # reference database for search_homologs (needs MMseqs2)
bioharbor install            # shows how to connect Claude, Cursor or Codex

For structure prediction on a GPU: pip install "bioharbor[esmfold]" — see docs/gpu-setup.md (RTX 50xx needs a CUDA 12.8+ PyTorch).

Connect your agent

BioHarbor is a standard MCP server, so it works with any MCP client. One command sets up the popular ones (it writes an absolute path, so GUI apps find it even outside your venv):

Long-running tools return a job_id within ~20 s instead of blocking, so they stay within every client's tool-call timeout.

Step-by-step setup (local or on a GPU server, with troubleshooting): docs/connect-clients.md.

Then ask your agent something like:

*Find the longest ORF in this contig, translate it, search Swiss-Prot for homologs and

predict its structure. Which regions are low confidence?*

Use it without an agent

Every tool is also a CLI command, with identical behaviour:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

BioHarbor: common questions

Is BioHarbor MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the BioHarbor safety report
How do I install BioHarbor?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does BioHarbor need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is BioHarbor maintained?
The last commit was 25 days ago (2026-10-10). The latest release is v0.1.6.
How does BioHarbor compare with other AI and agents MCP servers?
safety score 85/100 (higher than 73% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.