JapanFold

io.github.japanfoldPublished by GitHub account japanfoldv1.0.0Updated Oct 26, 2026

Fold proteins, co-fold ligands with binding affinity, design binders and embed sequences.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

Remote MCP server for JapanFold that lets an assistant fold proteins, co-fold ligands with binding affinity, design binders and compute sequence embeddings.

What you can do
  • Fold protein sequences into structures with models such as Boltz-2, ESMFold-2, OpenFold3 and RoseTTAFold3
  • Co-fold proteins with ligands and report binding affinity
  • Design binders with BoltzGen, RFdiffusion3, PXDesign and related models, and score already-designed binders with AF2-IG
  • Compute sequence embeddings with ESMC and SaProt
  • List available model ids and their size limits, then submit asynchronous jobs and poll for results
When to use it
Useful when a conversation needs structural biology work — predicting protein structures, ligand binding, binder design or embeddings — without owning a GPU, and you want the assistant to run those jobs through a hosted API.
Requirements
A remote endpoint at api.japanfold.aiand.com/mcp; no local install or GPU. API access needs a JapanFold key from the account token page, sent as an Authorization Bearer header (JAPANFOLD_API_KEY for the skill or Claude Code setup). Connectors such as claude.ai, Claude Desktop and ChatGPT sign in instead of using a key.
Before you install
Every API call requires a key, so treat it as a secret and keep it out of shared configs. Jobs are asynchronous and may consume paid account quota; check limits and pricing before bulk runs. Fast mode is off by default and trades accuracy for throughput when enabled. Sequences and other inputs are sent to a third-party service.

Installation

In SourceWeft

  1. Open JapanFold in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.japanfold%2Fjapanfold/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "japanfold": {
      "type": "http",
      "url": "https://api.japanfold.aiand.com/mcp"
    }
  }
}

README

JapanFold skill

Fold proteins, co-fold with ligands (+ binding affinity), design binders, and embed sequences from your AI agent, via the JapanFold API. Get a key at japanfold.aiand.com/account/token and set JAPANFOLD_API_KEY. No local GPU. Runs Boltz-2 / ESMFold-2 / OpenFold3 / OpenBind-0 / RoseTTAFold3 / OpenDDE for structures, AF2-IG for scoring a binder you already designed, BoltzGen / RFdiffusion3 / PXDesign / RFD4-Proteina for design, and ESMC / SaProt for embeddings, on Tenstorrent.

Agents can call the API directly, no install needed:

bash
export JAPANFOLD_API_KEY=jf_live_...          # from japanfold.aiand.com/account/tokencurl -s https://api.japanfold.aiand.com/v1/predictions \  -H "Authorization: Bearer $JAPANFOLD_API_KEY" -H 'Content-Type: application/json' \  -d '{"model":"esmfold2","sequence":"MKTAYIAKQRQISFVKSHFSRQLEERLGLIEVQ"}'

Base URL https://api.japanfold.aiand.com, key in Authorization: Bearer. GET /v1/models lists the model ids to send (boltz2, esmfold2, openfold3, ...) with their size limits. The agent-readable summary is llms.txt.

It's a single SKILL.md built on the open Agent Skills standard, so it installs into any compatible harness with one command.

Install

One line installs it everywhere the open standard is supported: Claude Code, Cursor, Codex, Gemini CLI, Cline, Windsurf, Copilot, Amp and the rest:

bash
npx skills add japanfold/japanfold          # this projectnpx skills add japanfold/japanfold -g       # global: every project / new chat
  • Target specific agents: -a claude-code, -a cursor, -a codex, -a '*' (all).
  • Prefer not to use the installer? It is one file. Download it unchanged into your agent's skills directory, for Claude Code: curl -fsSL --create-dirs -o ~/.claude/skills/japanfold/SKILL.md https://japanfold.aiand.com/skill.md. A web-fetch tool returns only a summary of the page, so an agent should use curl too.

Claude Science manages skills in-app (no installer): Customize → Skills, add from this repo (or paste SKILL.md) and publish it. Or skip install entirely: the API is public and self-describing, so just ask: "use the JapanFold API at api.japanfold.aiand.com to fold …".

Use

Once installed, ask your agent in plain language:

"Fold this sequence with Boltz-2 and report the confidence: MKTAYIAK…" "Design 10 nanobody binders against this target."

Or invoke it explicitly where supported: /japanfold.

MCP

The API is also a remote MCP server at https://api.japanfold.aiand.com/mcp, listed in the MCP Registry as io.github.japanfold/japanfold. claude.ai, Claude Desktop and ChatGPT add it as a connector and sign in, no key needed. Claude Code: claude mcp add --transport http japanfold https://api.japanfold.aiand.com/mcp --header "Authorization: Bearer $JAPANFOLD_API_KEY".

To publish a new registry version, bump version in server.json and run mcp-publisher login github && mcp-publisher publish.

The API

https://api.japanfold.aiand.com: async (submit → poll → download), a key on every call. Full contract at /v1/openapi.json. See SKILL.md for endpoints, examples, and limits.

Fast mode is off unless the agent sends "params": {"fast": true}. It gives higher throughput and may be slightly less accurate. The workbench turns it on for people clicking through; the API and this skill leave it off so a scripted run gets the accurate path. ESMFold-2 always runs fast on this hardware, and its job records fast: true.

Source: README.md at commit 0da945a

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.0LatestOct 19, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.