foldseek-mcp
Click on "Deploy 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., "@foldseek-mcp search PDB 1abc against pdb100"
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.
foldseek-mcp
独立的 FastMCP 服务端,用 MCP 工具封装 FoldSeek easy-search。
本项目面向 ProteinMCP / Claude / Agent Runtime 使用。MCP 负责参数校验、路径安全、Docker/FoldSeek 调用、结果解析、日志、artifact、command.json 和 manifest.json 记录。
MCP Tools
foldseek_search_structure:用 PDB/mmCIF 结构文件搜索官方 FoldSeek 数据库。foldseek_search_sequence:用 FASTA 文本或 FASTA 文件搜索结构数据库。foldseek_list_databases:列出已安装数据库、可用官方数据库、模型状态和 Agent 建议。foldseek_download_database:显式下载官方 FoldSeek 数据库。foldseek_validate_environment:检查 Docker/FoldSeek、数据库目录、模型目录和运行目录。
Related MCP server: ESMfold MCP Server
默认数据库策略
默认官方数据库 alias:
afdb_uniprot50_minimal对应 FoldSeek 官方数据库名:
Alphafold/UniProt50-minimal注意:该官方库约 114GB,不会在普通安装时静默下载。需要显式确认后下载,或由外部流程提前下载好并挂载/配置给 MCP。
不再把自建 fixture 数据库作为默认科学搜索数据库。fixture 只能用于链路 smoke test,不能替代官方数据库。
推荐部署方式
大型 FoldSeek 数据库不要打进 MCP Docker 镜像。推荐:
MCP 镜像只包含运行环境、FoldSeek runtime、MCP 代码。
官方数据库放在服务器持久化目录。
运行时通过 volume 或环境变量挂载。
示例目录:
/opt/mgi/foldseek-mcp/
/data/foldseek/databases/afdb_uniprot50_minimal/
/data/foldseek/models/
/data/foldseek/runs/如果你先在 Windows 下载到 E:\download\foldseek,服务器上可以拷贝成:
/data/foldseek/databases/afdb_uniprot50_minimal/然后设置:
FOLDSEEK_MCP_DATABASE_ROOT=/data/foldseek/databases
FOLDSEEK_MCP_MODEL_ROOT=/data/foldseek/models
FOLDSEEK_MCP_RUN_ROOT=/data/foldseek/runs
FOLDSEEK_MCP_BACKEND=docker
FOLDSEEK_MCP_DOCKER_IMAGE=openeuler/foldseek:10-941cd33-oe2403sp3
FOLDSEEK_MCP_AUTO_DOWNLOAD=false数据库 prefix 应为:
<DATABASE_ROOT>/afdb_uniprot50_minimal/afdb_uniprot50_minimal下载官方数据库
通过 MCP 工具下载时,需要显式确认大体积下载:
{
"database": "afdb_uniprot50_minimal",
"confirm_large": true
}也可以直接用 Docker 下载到外部目录:
$ROOT = "E:\download\foldseek"
New-Item -ItemType Directory -Force -Path "$ROOT\databases\afdb_uniprot50_minimal\tmp"
docker pull openeuler/foldseek:10-941cd33-oe2403sp3
docker run --rm `
-v "${ROOT}:/data" `
openeuler/foldseek:10-941cd33-oe2403sp3 `
foldseek databases "Alphafold/UniProt50-minimal" `
/data/databases/afdb_uniprot50_minimal/afdb_uniprot50_minimal `
/data/databases/afdb_uniprot50_minimal/tmp `
--threads 8安装
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"或:
bash quick_setup.shWindows 默认使用 Docker 后端。如果 Docker Desktop 未启动,MCP 会返回结构化错误 docker_unavailable,提示用户启动 Docker。
运行
python -m foldseek_mcp.serverLocal-first remote fallback
Search tools use local-first, remote-fallback:
If the requested database is installed or mounted locally, MCP runs local
foldseek easy-search.If the local database is missing and
FOLDSEEK_MCP_REMOTE_FALLBACK=true, MCP calls the official Foldseek Web API.If the remote API also fails, MCP returns a structured error with a local database remediation hint.
Remote fallback configuration:
FOLDSEEK_MCP_REMOTE_FALLBACK=true
FOLDSEEK_MCP_REMOTE_BASE_URL=https://search.foldseek.com
FOLDSEEK_MCP_REMOTE_TIMEOUT_SECONDS=900
FOLDSEEK_MCP_REMOTE_POLL_INTERVAL_SECONDS=2.0Remote alias mapping:
afdb_uniprot50_minimal -> afdb50
afdb_swissprot -> afdb-swissprot
afdb_proteome -> afdb-proteome
pdb -> pdb100
cath50 -> cath50search.foldseek.com is suitable as a free fallback path, but it is a public web server API rather than a production SLA service. For reproducibility, compliance, or private structures, mount local databases and set:
FOLDSEEK_MCP_REMOTE_FALLBACK=falseArtifacts
每次搜索会创建:
runs/jobs/<job_id>/
query.pdb 或 query.fasta
results.tsv
results.json
stdout.log
stderr.log
command.json
manifest.jsonmanifest.json 记录 query hash、数据库 alias、数据库 path/prefix、FoldSeek 版本、命令参数、时间戳、状态和 artifact 路径。
常见错误
docker_unavailable:Windows Docker 后端不可用,启动 Docker Desktop 后重试。docker_image_missing:本地没有 FoldSeek Docker 镜像,运行quick_setup.sh或docker pull openeuler/foldseek:10-941cd33-oe2403sp3。auto_download_limit_exceeded:官方库体积超过自动下载阈值,需要显式confirm_large=true。database_missing:官方数据库未下载或未挂载到FOLDSEEK_MCP_DATABASE_ROOT。foldseek_nonzero_exit:FoldSeek 命令执行失败,查看该 job 的stderr.log和command.json。
Available Tools
5 toolsfoldseek_download_databaseC
Download or prepare a catalog-listed FoldSeek database.
Inputs: database (required), confirm_large. Returns: object
foldseek_list_databasesA
List installed and available FoldSeek databases and model resources.
Inputs: no named parameters. Returns: object
foldseek_search_sequenceC
Run FoldSeek easy-search with a FASTA query and configured ProstT5 model.
Inputs: model, evalue, threads, use_gpu, +8 more. Returns: object
foldseek_search_structureC
Run FoldSeek easy-search with a PDB/mmCIF structure query.
Inputs: query_path (required), evalue, threads, use_gpu, +6 more. Returns: object
foldseek_validate_environmentA
Validate the local FoldSeek MCP runtime environment.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct operation: database download, listing, sequence search, structure search, and environment validation. No functional overlap.
All tools follow the consistent pattern 'foldseek_verb_noun' with clear, descriptive names (e.g., foldseek_download_database, foldseek_search_sequence).
Five tools is appropriate for a focused scientific server covering database management, two search modalities, and environment checks.
Core workflows are covered, but missing a tool to delete or update databases, which is a minor gap for full lifecycle management.
Related MCP Connectors
Fold proteins, co-fold ligands with binding affinity, design binders and embed sequences.
Run protein folding, docking, design and sequence analysis tools, and read their results.
Protein analysis: ESM-2/ESMC embeddings, mutation scoring, landscape scans, ESMFold structure.
Search InterPro entries, map domains onto proteins and PDB structures, and scan raw sequences.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables searching, retrieving, and downloading protein structure data from the RCSB Protein Data Bank. Supports intelligent protein structure search, comprehensive data retrieval, and multiple file format downloads for bioinformatics research.3MIT
- FlicenseNot gradedqualityDmaintenanceEnables protein sequence analysis and structure prediction by extracting ESM-2 embeddings and batch processing FASTA files via Docker. It provides tools for large-scale embedding extraction, job monitoring, and model management within an MCP-compatible environment.-
- FlicenseBqualityDmaintenanceProvides programmatic access to AlphaFold protein structure predictions and UniProt data, enabling users to retrieve protein structures, summaries, and annotations through natural language.3-
- FlicenseNot gradedqualityCmaintenanceEnables AI-powered protein structure prediction and variant analysis via Docker, with tools for submitting predictions, batch processing variants, and monitoring jobs.2-