Log inSubmit server
Promptlike MCP logo

Promptlike MCP

Connects Claude Code to PromptLikeEngineer libraries for finding, filling, using, and versioning saved prompts.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Promptlike MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "promptlike-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "promptlike-mcp@0.7.2"
      ],
      "env": {
        "PROMPTLIKE_API_URL": "YOUR_VALUE_HERE",
        "PROMPTLIKE_CONFIG_DIR": "YOUR_VALUE_HERE",
        "PLE_SUGGEST": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

promptlike-mcp connects Claude Code to a PromptLikeEngineer prompt library through MCP tools for listing, searching, retrieving, filling, suggesting, saving, updating, moving, and commenting on prompts. The Claude Code plugin also exposes saved prompts as slash commands and @ resources, with variables passed into prompt text at use time. A local suggestion hook can match messages against a cached library without sending the message itself over the network. Reach for it when reusable prompts need to stay versioned in PromptLikeEngineer instead of being copied into system instructions.

Use cases

  • Retrieve a versioned code-review prompt for a branch
  • Run saved prompts from Claude Code's slash-command menu
  • Fill reusable prompt variables from command arguments
  • Suggest matching library prompts before a message is processed
  • Save reusable instructions discovered during a conversation

Key features

  • Searches and retrieves PromptLikeEngineer prompts
  • Fills ordered `{{variables}}` in prompt text
  • Exposes saved prompts as slash commands and @ resources
  • Supports non-destructive save, update, and move operations
  • Provides local prompt suggestions through a Claude Code hook
  • Rejects text resembling API keys or tokens

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

8/8 checks healthy over the last 37d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 13h ago via OSV.dev · promptlike-mcp@0.7.2 (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads1.8kPackage downloads in the last 30 days.
Last commit9d agoMost recent push to the default branch.

How Promptlike MCP works

What promptlike-mcp does

promptlike-mcp brings a PromptLikeEngineer prompt library into Claude Code. Claude can find a prompt by name or search term, retrieve its content, fill its {{variables}}, and use the result in a conversation. The plugin also turns saved prompts into selectable slash commands and @ resources, so a prompt can be invoked directly rather than retrieved through a conversational request.

Prompt saving is add-only. Creating a prompt does not remove existing content, updating creates another version while retaining the older one, and moving changes a prompt's repository or folder without deleting it. Saving the same content twice has no effect. Text that resembles an API key or token is rejected, and account plan limits still apply.

How it works

Claude Code starts the MCP process through npx. The server runs locally and communicates with PromptLikeEngineer at https://promptlikeengineer.com, or with the endpoint selected through PROMPTLIKE_API_URL. Authentication comes from the session created by ple login and is refreshed through the same service when needed.

Saved prompts are available as MCP prompts and resources. A title such as “Code Review” becomes a code-review slash-command name, and arguments fill variables in the order those variables first appear. Variables omitted from a slash-command invocation remain in the resulting text. Resource references use the promptlike://<repo>/<prompt> form.

Before each Claude Code message, the optional suggestion hook runs a local match against cached prompts. It ignores slash commands, short messages, weak matches, and prompts already suggested in the session. If a match is found, Claude receives a short note naming up to three prompts and decides whether to fetch one. A background cache refresh may download the user's prompt list when the local copy is stale.

Setup and configuration

Install the plugin from its marketplace or run Claude Code with a clone supplied through --plugin-dir. Install the PromptLikeEngineer CLI globally, then sign in once with ple login. The plugin can load without authentication, but tool calls return a login instruction instead of prompt content.

The suggestion hook requires the CLI. It can be disabled from Claude Code's configuration, with ple config set suggest off, or by setting PLE_SUGGEST=off. PromptLikeEngineer CLI files are stored under ~/.config/promptlike/ by default; PROMPTLIKE_CONFIG_DIR changes that location. When signed out, the hook reads from ~/.promptlike.

Tools and capabilities

  • list_prompts and search_prompts find library entries.
  • get_prompt retrieves a selected prompt.
  • fill_variables substitutes values into prompt text.
  • suggest_prompts matches a task description against the library.
  • save_prompt, update_prompt, and move_prompt manage prompts without deletion.
  • submit_feedback sends a short, confirmed note to the maker.
  • Saved prompts appear as slash commands and promptlike:// resources in Claude Code.

Fetching a prompt through a tool, slash command, or resource records a use event containing the prompt and version, access method, suggestion status, and MCP client identity.

Limitations and notes

The suggestion hook performs matching locally and does not send the message itself. The MCP server does send prompt reads, requested task text for suggest_prompts, saved text, and confirmed feedback to PromptLikeEngineer as needed. The suggest_prompts task description is limited to 2,000 characters and is not logged or stored by that endpoint.

The local cache holds up to 500 prompts with metadata and the first 600 characters of each text. Feedback can be submitted without a session, but it must be a short message and cannot resemble a key or token. The server does not delete prompts; moving, updating, and saving are non-destructive operations.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Promptlike MCP

promptlike-mcp is an MCP server that connects Claude Code to a PromptLikeEngineer prompt library. Its main tools list, search, retrieve, fill variables, suggest, save, update, move prompts, and submit feedback. It also exposes saved prompts as slash commands and @ resources while preserving prior versions and rejecting text resembling API keys or tokens.

Install the promptlike plugin from its marketplace, or run Claude Code with a cloned repository using `claude --plugin-dir ./promptlike-plugin`. Then install the PromptLikeEngineer CLI and run `ple login` so the server can access your library.

Yes, promptlike-mcp is packaged as a Claude Code plugin. Claude Code starts the MCP server, registers the tools, exposes saved prompts as slash commands and resources, and can run the optional suggestion hook before messages.

Disable suggestions with Claude Code's configuration, `ple config set suggest off`, or `PLE_SUGGEST=off`. Turning the feature off also stops the hook's background cache refresh.

No, promptlike-mcp uses non-destructive save, update, and move operations. Updates retain older versions, moves relocate a prompt without deleting it, and saving identical content twice makes no change.

Related MCP servers

All in Conversational AI All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPromptlike MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/promptlike-mcp?style=directory)](https://allmcps.com/mcp/promptlike-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/promptlike-mcp"><img src="https://allmcps.com/api/badge/promptlike-mcp?style=directory" alt="Promptlike MCP on AllMCPs" /></a>