Skip to content
MCP server

Crela

Search the Crela software marketplace and publish or review software from your agent

Status and history

Answered our latest tool-list check 21 hours ago with 13 tools. It will be marked verified after 3 successful checks in 7 days.

Install
Pricing
Free
Platforms
API, CLI, Web
Runs
Locally or Remotely
Version
1.10.1
Listing updated
3 days ago

About Crela

Crela is a free MCP server for developer tools. It can run locally on your machine or as a hosted remote server.

Crela's MCP server covers the whole publishing cycle, not only search. An agent can read the platform rules, dry-run a build before spending a review, submit a ZIP with metadata, upload screenshots and then poll the automated review and read its report. New versions go through the same review, and a demo channel lets you publish a demo without touching the live listing.

There are two ways to connect. The local package @crela/mcp runs on your own computer over stdio, because uploading builds and screenshots needs files from your disk. A hosted connector at crela.io/mcp needs no install: it searches the catalogue without signing in, and after you connect your Crela account it can manage existing listings, though it cannot upload builds.

The docs describe a REST API that the MCP server is built on, for use from CI/CD scripts. Discovery tools work without a key; publish, review and management tools need a crela_ API key from the creator dashboard. The local server needs Node.js 18 or newer.

Install

Run in a terminal

claude mcp add --transport http mcp https://crela.io/mcp

Add to Settings → Connectors → Add custom connector

https://crela.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://crela.io/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://crela.io/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://crela.io/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://crela.io/mcp"
    }
  }
}

Configuration

  • CRELA_API_KEYCrela API key (crela_...) from https://crela.io/dashboard/creator/keys. Only needed for the publish tools; search works without it.
  • CRELA_BASE_URLCrela API base URL.

Tools this server provides (13)

Read directly from the server.

search_software
Search the Crela marketplace for reviewed software, apps and games you buy once and own - no subscription. Returns only approved, publicly listed tools, each with a url to its Crela page where it can be bought. Use limit (1-50) to keep the response small and page through the rest; get_software returns the full detail of one.
get_software
Full public detail of one approved software item by its slug: description, price, platforms, version, system requirements and the url of its Crela page.
get_submission_requirements
Return the machine-readable submission rules for selling software on Crela (required fields, KO rules, bundle rules). Public, no sign-in required. Use it to check whether a project fits Crela before building. Uploading builds and screenshots needs files from disk and is only available in the local server (npx -y @crela/mcp). This server manages existing software: list_my_software, check_review_sta
list_my_software
List all software you own with its id, slug, review status (pending/approved/rejected/flagged), whether it is unlisted, price and sales count. Use this to recover the software_id needed by check_review_status, set_metadata and delete_software. Unlike search_software, this also returns pending, rejected and unlisted tools. Requires sign-in to your Crela account; your client asks you to connect when
get_my_software_details
Read the full metadata and media list of one of your own software items by software_id. Works for all statuses (pending, approved, rejected). Returns { tool, media, missing_media, presentation } where media lists all uploaded screenshots/images with their ids and sizes, and presentation attests the listing level (incomplete, minimum, ideal) with toward_ideal, the steps left to the ideal presentati
check_review_status
Poll the lightweight review status of a submitted software (progress, sub-step, rate-limit budget). Returns { tool_id, tool_status, awaiting_media, missing_media, presentation, next_step, version, review_job_status, review_sub_step, review_passed, rejection_reason, review_started_at, review_completed_at, rate_limit }. awaiting_media true means the tool is approved but not listed yet because screen
get_review_report
Fetch the full review report of a submitted software: pass/fail, rejection reasons and structured findings to fix. Heavier than check_review_status - call this only after the review has completed, not for live progress polling. Findings are capped at 10 locations each (a CVE finding can carry hundreds of near-identical ones); the response then sets truncated:true and locations_omitted per finding.
set_metadata
Change metadata (title, description, price, categories, tags, etc.) of an existing software - no binary upload. Changing title, description, long_description or categories on an approved tool triggers a re-review. Upgrading price_eur from 0 to a paid value also triggers re-review. All other fields (tags, price reductions, tool_languages, unlisted) do NOT trigger re-review. Set unlisted:true to tak
delete_software
Permanently and irreversibly delete one of your software items. Only works if it has never been sold - sold tools cannot be deleted (buyers keep their claim); take those off the market with set_metadata { unlisted: true } instead. Requires sign-in to your Crela account; your client asks you to connect when you first use it.
delete_media
Permanently delete a screenshot, logo or other media item from a software listing. Use get_my_software_details to get the media ids of uploaded files. Uploaded files (screenshots and logos) are also deleted from storage; video URL entries are only removed from the listing. Requires sign-in to your Crela account; your client asks you to connect when you first use it.
update_media
Update a media item: the sort order of any item (lower sort_order appears first), or the URL of a video entry (https YouTube/Vimeo link only). This tool does not create entries: a video is added with set_metadata { video_url }. Use get_my_software_details to get media ids. Provide at least one of sort_order/url. Requires sign-in to your Crela account; your client asks you to connect when you first
get_sdk_marker
Fetch the per-tool SDK marker (KO-10) of an EXISTING tool by software_id. Embed it via the build env var CRELA_SDK_MARKER before building a new version. For a tool that does not exist yet use preview_marker (needs slug, not software_id). Requires sign-in to your Crela account; your client asks you to connect when you first use it.
preview_marker
Compute the per-tool SDK marker (KO-10) for a NOT-yet-created tool from its planned slug. Paid tools (price > 0) must embed this marker via the build env var CRELA_SDK_MARKER before building and submitting. For tools that already exist use get_sdk_marker (needs software_id, not slug). Returns { marker, slug, slug_available }. Requires sign-in to your Crela account; your client asks you to connect

What it does

Search without a key
search_software and get_software query the catalogue and link each result to its Crela page.
Build precheck
precheck_build dry-runs the submit gate so missing files or the marker are caught before a review cycle.
Submit and version
submit_new_software and update_software send metadata plus a build ZIP; versions are semver.
Review reports
check_review_status and get_review_report show review progress and findings to fix.
Hosted connector
A URL-only connector for browser and phone clients, with account sign-in for management tools.
REST API
The same endpoints are available for CI/CD pipelines with a Bearer API key.

Good for

  • Publish a finished tool to the Crela marketplace from a coding agent chat
  • Dry-run a build ZIP before submitting it for review
  • Read review findings and resubmit a fixed build
  • Search the Crela catalogue from an AI assistant
  • Ship a demo build without changing the live listing

Pricing

Free

Server and API key are free to create; software prices are set by creators

Prices change. Check crela.io before you buy.

Crela FAQ

Do I need an API key?

Not for search. Publish, review and management tools need a crela_ key created in the creator dashboard.

Can the hosted connector upload builds?

No. Uploading builds and screenshots needs the local @crela/mcp server because it reads files from your disk.

What do I need to run the local server?

Node.js 18 or newer; clients such as Claude Code, Claude Desktop, Cursor or VS Code start it for you.

Does anything go live without review?

No. The docs say every submission goes through the review pipeline first.

Is Crela free?

Yes. Crela is free to use.

How do I add Crela to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://crela.io/mcp

What are the best alternatives to Crela?

The closest alternatives to Crela are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Crela

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools