Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Run real bioinformatics from your AI agent. Reliable, reproducible, on your own GPUs.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"bioharbor": {
"command": "uvx",
"args": [
"bioharbor",
"serve"
]
}
}
}在终端中运行这条命令
claude mcp add bioharbor -- uvx bioharbor serve粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"bioharbor": {
"command": "uvx",
"args": [
"bioharbor",
"serve"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"bioharbor": {
"type": "stdio",
"command": "uvx",
"args": [
"bioharbor",
"serve"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 danielLuo2 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.6)于28天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Foliosio
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Read your support inbox, tag conversations and save draft replies from your AI agent. Never sends.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
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.
Most bio MCP servers wrap databases (UniProt, PDB, PubMed…). Use them — BioHarbor complements them by running the compute:
| Database MCP servers | BioHarbor | |
|---|---|---|
| Runs real analyses (search, fold, cluster) | ❌ | ✅ |
| Validates inputs *before* burning GPU time | ❌ | ✅ |
| GPU-aware queue, polite on shared GPUs | ❌ | ✅ |
Long jobs return a job_id instead of timing out | ❌ | ✅ |
| Compact summaries + files on disk (saves tokens) | ❌ | ✅ |
| Provenance for every run, export to a pipeline | ❌ | ✅ (export: planned) |
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).
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):
| Client | Set up |
|---|---|
| Claude Code | claude mcp add bioharbor -- bioharbor serve |
| Claude Desktop | bioharbor install claude-desktop --write, then restart the app |
| Cursor | bioharbor install cursor --write, or |
| Codex (CLI, IDE extension, app) | codex mcp add bioharbor -- bioharbor serve, or bioharbor install codex --write |
| Biomni (Stanford's biomedical agent) | agent.add_mcp(...); see docs/use-with-biomni.md |
| Anything else | run bioharbor serve (stdio) or bioharbor serve --http (Streamable HTTP) |
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?*
Every tool is also a CLI command, with identical behaviour:
bioharbor tools list
bioharbor run find_orfs sequence=@contig.fa min_aa=100 --brief # human-readable bioharbor run seq_stats sequence=MKTAYIAKQRQISFVKSHFSRQ bioharbor jobs
GPUs on a lab server, agent on your laptop? Run BioHarbor on the server and reach it through an SSH tunnel; no extra port is opened on the server:
# on the GPU server
bioharbor serve --http --host 127.0.0.1 --port 8765
ssh -N -L 8765:127.0.0.1:8765 you@gpu-server
⚠️ HTTP mode has no authentication yet (on the roadmap), so keep it on
127.0.0.1and
use the tunnel. Details: docs/connect-clients.md.
| Tool | What it does | Runs |
|---|---|---|
seq_stats | Validate sequences; type, length, GC%, molecular weight | inline |
translate_sequence | DNA/RNA → protein, one or all six frames | inline |
find_orfs | Longest ORFs on both strands, with coordinates | inline |
search_homologs | MMseqs2 search (protein, or translated DNA) vs local DBs | job |
predict_structure | ESMFold structure, pLDDT bands, low-confidence regions, pTM | job (GPU) |
scrna_pipeline | scanpy QC → clustering → markers | *planned* |
Runtime tools: get_job, list_jobs, cancel_job, describe_tool, list_databases, gpu_status, read_file.
Agent ──MCP──▶ validate input ─▶ inline? ──yes──▶ run ─┐
│ no ├─▶ provenance + summary ─▶ Agent ▼ │ job queue (SQLite) ─▶ GPU placement ┘ (waits politely for a GPU with free memory)
provenance.json next to its outputs.nvidia-smi), keeps headroom, and reserves memory for jobs it has started so two jobs never grab the same space. Other users' processes are respected.summary, message, files, suggestions. Errors carry a hint and a retryable flag.Details: docs/design.md.
from pydantic import BaseModel, Field
from bioharbor.registry import Resources, RunContext, tool from bioharbor.results import ToolResult
class FoldParams(BaseModel): sequence: str = Field(..., description="Protein sequence")
@tool( version="1", slow=True, resources=Resources(gpu=True, gpu_mem_gb=lambda p: 4 + len(p.sequence) / 100), ) def predict_structure(params: FoldParams, ctx: RunContext) -> ToolResult: """Predict a protein structure with ESMFold.""" ... return ToolResult(summary={"mean_plddt": 87.1}, files=["model.pdb"])
Plugins can ship tools in their own package via the bioharbor.tools entry-point group. See CONTRIBUTING.md.
Apache-2.0