Skip to main content
Glama
ianphil

PromptBin

by ianphil
OverviewSchemaRelated ServersScoreDiscussions
Python
Local

PromptBin - MCP Server Example

The easiest way to run a Model Context Protocol (MCP) server with full prompt management.

Setup

1. Install and Configure

# Install PromptBin
pip install promptbin

# Install Dev Tunnels CLI (optional, for public sharing)
promptbin-install-tunnel

# Authenticate with Dev Tunnels (optional, one-time setup)
devtunnel user login -g

# Verify setup
promptbin-setup

2. Add to Your AI Client

Claude Desktop - Add to Settings β†’ Developer β†’ Edit Config:

{
  "mcpServers": {
    "promptbin": {
      "type": "stdio",
      "command": "uvx",
      "args": ["promptbin"]
    }
  }
}

3. Start Using

That's it! PromptBin is now running:

  • Web UI: http://localhost:5001 - Manage and create prompts

  • MCP Server: Ready for AI tool connections

Related MCP server: RISEN Prompt Engineering MCP Tool

Key Features

  • πŸš€ Easy setup: One command to get started

  • πŸ”— MCP integration: Full Model Context Protocol support

  • 🌐 Web interface: Auto-launching prompt management UI

  • πŸ”’ Secure sharing: Share prompts via Dev Tunnels with rate limiting

  • πŸ“ Local-first: Your data stays private, stored locally

  • βš™οΈ Production-ready: Comprehensive logging and error handling

Usage Options

# Default: Run both MCP server and web interface
promptbin

# Run only MCP server (for AI tools)
promptbin --mcp

# Run only web interface (standalone)
promptbin --web

# Custom port and options
promptbin --port 8080 --data-dir ~/my-prompts

Development Mode

For development or customization:

git clone https://github.com/ianphil/promptbin
cd promptbin
uv sync
uv run promptbin

What You Get

  • βœ… Complete MCP server - Full Model Context Protocol implementation

  • βœ… Auto-launching web UI - Prompt management interface at localhost:5000

  • βœ… AI tool integration - Works with Claude Desktop, ChatGPT Desktop

  • βœ… Secure sharing - Share prompts publicly via Dev Tunnels

  • βœ… File-based storage - No database required, organized by category

  • βœ… Cross-platform - Windows, macOS, Linux support

  • βœ… Production-ready - Rate limiting, logging, graceful shutdown

Advanced Features

Secure Public Sharing (Optional)

PromptBin includes Microsoft Dev Tunnels integration for sharing prompts publicly:

# Install Dev Tunnels CLI
uv run promptbin-install-tunnel

# Authenticate (one-time setup)
devtunnel user login -g

# Start PromptBin, then click "Start Tunnel" in the footer

Now your shared prompts get public URLs that work from anywhere. Includes automatic rate limiting and security protections.

For detailed setup instructions, see TUNNELS.md.

System Validation

# Check if your system is ready
uv run promptbin-setup

Add MCP Server to ChatGPT & Claude (Desktop)

Prereq: Install PromptBin first (pip install promptbin). The apps will launch the MCP server themselves.

ChatGPT Desktop (Mac/Windows):

  • Open Settings β†’ Developer β†’ Model Context Protocol.

  • Click "Add Server".

  • Name: PromptBin

  • Command: uvx

  • Args: promptbin

Claude Desktop (Mac/Windows):

  • Open Settings β†’ Developer β†’ Edit Config

"PromptBin": {
            "command": "uvx",
            "args": ["promptbin"]
        }

Notes:

  • After adding, you can list/search prompts via the PromptBin MCP tools. The MCP server also starts the local web UI on http://127.0.0.1:<port>.

  • If uvx is not available, ensure you have uv installed and use pip install promptbin instead.

Available Tools

1 tool
search_promptsB

Search prompts by content, title, tags, or description

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYes
categoryNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says what is searched, not how results are matched, whether search is case-insensitive, how results are ordered, or that the operation is non-destructive. 'Search' weakly implies a read operation, but concrete behavioral traits are missing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence with an active verb and no filler. Every word contributes to meaning, and the core searchable scope is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple search tool with an output schema, the description covers the core objective but omits the optional category filter and limit behavior. It is minimally viable, and the self-explanatory schema partially compensates, but the absence of usage/behavioral context leaves moderate gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It clarifies that query searches across content, title, tags, or description, but says nothing about the limit or category parameters, leaving their semantics to be inferred from their names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Search') and resource ('prompts'), and enumerates the fields being searched: content, title, tags, or description. It clearly identifies the tool's purpose, even without sibling tools to differentiate against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for finding prompts by text or metadata, but provides no explicit guidance on when to use this tool versus alternatives. No sibling tools are listed, so there is no direct comparison, but the usage context remains only implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool updatev0.5.1
    • First observedsearch_prompts
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap. The single tool's purpose is clearly distinct by default.

Naming Consistency5/5

The sole tool uses a clear verb_noun pattern: search_prompts. This is consistent, predictable, and matches its function.

Tool Count2/5

A single search-only tool feels far too thin for a server named PromptBin, which implies a prompt storage and management domain. Even a minimal prompt management server would need at least creation and listing capabilities.

Completeness1/5

The server exposes only search, with no way to add, update, delete, or retrieve prompts directly. This is severely incomplete for the apparent prompt-management scope and would cause agent failures for any non-search workflow.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Prompts MCP Server

    tanker327
    A
    license
    A
    quality
    D
    maintenance
    A Model Context Protocol server for managing prompt templates as markdown files with YAML frontmatter, allowing users and LLMs to easily add, retrieve, and manage prompts.
    5
    21
    16
    MIT

  • Prompt Registry MCP

    stevengonsalvez
    A
    license
    Not graded
    quality
    C
    maintenance
    A lightweight, file-based server for managing and serving personal prompt templates with variable substitution support via the Model Context Protocol. It allows users to store, update, and organize prompts in a local directory through integrated MCP tools and CLI assistants.
    20
    7
    MIT

  • Prompt Bookmarks

    nika-is-nika
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables users to organize, search, and manage a shared library of prompts across AI tools via the Model Context Protocol. It supports hierarchical folder organization, tagging, and template variable substitution for dynamic prompt generation.
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ianphil/promptbin'

If you have feedback or need assistance with the MCP directory API, please join our Discord server