Prompt Maker Studio

io.github.chrysogonusPublished by GitHub account chrysogonusv0.17.0Updated Nov 5, 2026

Your prompt library in any MCP client: list, fetch, save and version prompt templates.

VerifiedStreamable HTTPWeb executableKnowledge & MemoryAI & ML

Overview

AI-generated overview

Remote MCP server for a self-hosted prompt library, letting an assistant list, fetch, save and version prompt templates.

What you can do
  • List and fetch saved prompt templates from the library
  • Save prompts and keep versions so edits can be compared or restored
  • Work with reusable templates that use variables and filled-in values
  • Access the same prompt services the web app uses, through REST and MCP
When to use it
Useful when you keep a personal or team prompt library in Prompt Maker Studio and want ChatGPT, Claude or another MCP client to read and update it directly instead of copying prompts by hand.
Requirements
A remote endpoint at neadlab.com with OAuth sign-in required. You need an account on that deployment; the README describes self-hosting with Git, Docker Compose, Make and OpenSSL, with registration open by default. AI features need a configured provider (OpenAI, Anthropic, Gemini, Ollama, vLLM or an OpenAI-compatible endpoint).
Before you install
OAuth grants the client access to your prompt library, and saving prompts writes data to the deployment. AI conversion, refinement and evaluation send prompt content to the configured provider, and hosted calls may incur provider charges. The project is early-stage 0.x, so APIs and schemas may change; back up before upgrading.

Installation

In SourceWeft

  1. Open Prompt Maker Studio in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. 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.chrysogonus%2Fprompt-maker-studio/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. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "prompt-maker-studio": {
      "type": "http",
      "url": "https://neadlab.com/api/mcp"
    }
  }
}

README

Prompt Maker Studio

A self-hosted workspace for prompts you want to use again. Keep them organised, refine the wording, and test how they perform before your next edit.

[License: Apache 2.0] [CI] [mcptry]

Get started · Connect ChatGPT or Claude · Contribute

Keep your useful prompts close

Find prompts with search, folders and favourites. Write reusable sections with {{variables}}, fill them in, and copy the result into any chat app. Saved versions let you compare edits and restore an earlier approach.

[Prompt library with search, favourites, folders and reusable variables]

Turn a working prompt into a reusable template

Choose Add existing prompts in the library and then Make reusable with AI, or Paste a prompt in the editor. AI turns unstructured text into XML-style sections and identifies variables with their original values filled in. Review and edit the variables, keep an input fixed, and copy either the template or filled prompt. Apply to the draft with Undo; Save keeps it. Example inputs are separate from template content and require an explicit choice.

Refine with a clear view of what changes

Answer clarifying questions, then review a proposed draft section by section. See the wording changes before applying them; undo or save when you're ready.

[Refinement panel showing section changes beside the original prompt]

Test with examples that matter

Give a saved prompt test inputs and choose automatic checks, AI review or your own rating. Inspect model outputs and feedback, then compare runs to understand the effect of an edit. Keep your test cases reusable with CSV import and export.

[Evaluation history showing per-case model outputs, scores and review feedback]

Screenshots use synthetic demo data, including illustrative AI outputs and scores.

Free tools, templates and guides without an account

Every deployment also serves public pages for visitors who are not signed in: free tools to fill in templates, check a prompt, compare two versions and estimate tokens and cost (plus an optional free refiner on the server's AI connection), a gallery of ready-to-use prompt templates, practical guides, and an About page. They are server-rendered with structured data, a sitemap and /llms.txt, so search engines and AI assistants can find them.

Prompt management works without an AI connection. Prompt conversion, refinement, Try once and evaluation use your configured provider: OpenAI, Anthropic, Gemini, Ollama, vLLM or another OpenAI-compatible endpoint. Hosted calls may incur provider charges; operators can set monthly spending limits.

Quick Start with Docker

You'll need Git, Docker with Compose, Make and OpenSSL.

bash
git clone https://github.com/chrysogonus/prompt-maker-studio.gitcd prompt-maker-studiomake setupmake up

Open localhost:3000 and create your account. Registration is open by default; set REGISTRATION_MODE=closed to admit only the first account. For AI features, connect a provider under Settings → AI connection, or use the operator's optional server default when configured.

make setup creates local configuration with a generated signing key. Browser API calls stay on the same origin through the frontend proxy. Run make down to stop the app. See the Docker guide for configuration and local email testing.

Architecture

mermaid
flowchart LR    Browser[Browser] --> Edge["Caddy · HTTPS"]    MCP["ChatGPT / Claude / MCP client"] --> Edge    Edge -->|Web app| UI["Next.js · React"]    Edge -->|REST / MCP / OAuth| API[FastAPI]    API --> DB[(SQLite)]    API -.->|Import · refine · evaluate| AI["Configured AI provider"]

Caddy handles production HTTPS and routing. Locally, Next.js proxies /api to FastAPI. SQLite stores accounts, prompts, versions and evaluation history; REST and MCP share the same prompt services. AI calls are optional.

The stack: Python 3.12 with FastAPI and SQLAlchemy 2.1 on SQLite; Next.js 16, React 18 and TypeScript; Docker Compose with Caddy, plus Prometheus and Grafana for monitoring.

Go further

Project status

Early-stage, 0.x. APIs and database schemas may change between releases. Back up before upgrading; see the changelog. The 0.16.2 release record records publication, immutable image digests and verification for the latest release: MCP tool titles are also sent as annotations.title, with no migrations. Each release record lists its own migrations and upgrade notes; follow them for every release you skip. Upgrades from before 0.5.0 must also follow the 0.5.0 upgrade checks, including rehearsing migrations on an isolated production-backup copy.

License

Apache 2.0. See NOTICE and third-party notices for attribution.

Source: README.md at commit bb46eaa

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

8
  1. v0.17.0LatestNov 5, 2026
  2. v0.16.2Nov 3, 2026
  3. v0.16.1Nov 3, 2026
  4. v0.14.0Oct 29, 2026
  5. v0.6.0Oct 17, 2026
  6. v0.5.1Oct 17, 2026
  7. v0.4.0Oct 14, 2026
  8. v0.3.0Oct 14, 2026

Score

85% 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 listed15 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