mcpbeat Sign in

BioHarbor MCP Server

by danielluo2 Your server? Claim it
local only

BioHarbor runs on your own machine — the client starts it, so there is no endpoint to ping. 279 installs a week from pypi. Last commit 10 Oct 2026.

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

Installs per day peak 619 · avg 104 · +25% w/w
a month agotoday
279
Installs / week
pypi · bioharbor
0
Stars
0 open issues
10 Oct 2026
Last commit
from GitHub
Apache-2.0
License
Python

What the code does

We read the source, 3 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

    run = run or (lambda cmd: subprocess.run(cmd, check=True))

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add bioharbor -- uvx bioharbor
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "bioharbor": {
      "command": "uvx",
      "args": [
        "bioharbor"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.bioharbor]
command = "uvx"
args = ["bioharbor"]
.cursor/mcp.json
{
  "mcpServers": {
    "bioharbor": {
      "command": "uvx",
      "args": [
        "bioharbor"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "bioharbor": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "bioharbor"
      ]
    }
  }
}

Alternatives to BioHarbor

same job, measured the same way
Studio
by kaitoi

Build and run visual creative-production workflows from your AI agent.

answering
Replyhand
by replyhand

Run your Replyhand inbox, contacts, AI agent and reports from your own AI assistant.

answering
Reprise
by reprise

Un-flatten any flat AI design into editable layers, reproduce it bit-perfect, from your agent.

3 tools answering
Frame24
by frame24

Make narrated, on-brand product videos of your real app from your coding agent or AI assistant.

answering
Practonaut
by godarg

Local practice gym for AI agents on real apps: practice Excalidraw tasks, get a reproducible score.

58 installs/wk local only
P
Prismnetwork
by prismnetwork

Rent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.

171 installs/wk local only
Prismnetwork Tech
by prismnetwork-tech

Rent real NVIDIA GPUs from your agent. Browse with no wallet; pay per second onchain.

local only
LotsDirectory
by lots

Launch once, get found everywhere: a product page built for search and AI, run from your AI agent.

answering

BioHarbor — questions

Answers built from our own checks of this server.

Why is there no uptime for BioHarbor?
BioHarbor runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package bioharbor was installed 279 times last week.
How do I connect BioHarbor?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls bioharbor straight from pypi; nothing to host, nothing to sign up for.
How many people use BioHarbor?
The pypi package bioharbor was installed 279 times in the last week. Week over week that is +25%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is BioHarbor open source?
Yes — it is published under the Apache-2.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.