Skip to main content

Fiverr MCP Server

PyPI version License: MIT

mcp-name: io.github.KyuRish/fiverr-mcp-server

MCP server for searching and browsing Fiverr - gigs, sellers, pricing, and reviews. No API key required.

Features

  • Search gigs by keyword with filters (price, seller level, category, sorting)
  • Get gig details including pricing packages (Basic/Standard/Premium), description, and tags
  • View seller profiles with certifications, languages, hourly rate, and gig listings
  • Read gig reviews from the first page of any gig
  • List categories to discover valid category slugs for filtered search
  • All prices returned in USD (not cents)
  • Built-in rate limiting and retry with browser fingerprint rotation
  • Structured error messages on failures (no raw crashes)

Installation

{
  "mcpServers": {
    "fiverr": {
      "command": "uvx",
      "args": ["fiverr-mcp-server"]
    }
  }
}

Using pip

pip install fiverr-mcp-server

From source

git clone https://github.com/KyuRish/fiverr-mcp-server.git
cd fiverr-mcp-server
uv sync
uv run fiverr-mcp-server

Configuration

Add to your Claude Desktop config (claude_desktop_config.json):

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "fiverr": {
      "command": "uvx",
      "args": ["fiverr-mcp-server"]
    }
  }
}

Environment Variables

Variable Description Default
TRANSPORT Transport mode (stdio or sse) stdio
PROXY_URL Optional HTTP proxy for requests -
RATE_LIMIT_DELAY Minimum seconds between requests 2

Available Tools

search_gigs

Search the Fiverr marketplace by keyword. Returns up to 48 gigs per page with pagination info.

Parameters:

  • query (required) - Search query (e.g. "logo design", "python developer")
  • category - Category slug (use list_categories to see valid values)
  • min_price / max_price - Price range filter in USD
  • seller_level - "level_one_seller", "level_two_seller", or "top_rated_seller"
  • sort_by - "relevance", "best_selling", "newest", "price_asc", or "price_desc"
  • page - Page number for pagination

Returns: List of gigs with title, price (USD), rating, reviews count, seller name, and URL. Also includes total_results and has_more for pagination.

get_gig_details

Get full details of a specific gig including all pricing tiers.

Parameters:

  • url (required) - Fiverr gig URL or path

Returns: Title, description, seller info, packages (name/price/delivery/revisions/features), tags, metadata, rating, reviews count, category, and orders in queue.

get_seller_profile

Get a seller's profile. Use seller_name from search results as the username.

Parameters:

  • username (required) - Seller's Fiverr username

Returns: Display name, bio, location, member since, languages, certifications, hourly rate (USD), gig listings, and verification status.

get_gig_reviews

Get the first page of reviews for a gig (typically 5-10 reviews loaded from the page).

Parameters:

  • url (required) - Fiverr gig URL or path

Returns: List of reviews with buyer name, country, rating, date, and text.

list_categories

List all available Fiverr category slugs for use with search_gigs.

Returns: List of category objects with slug and name.

Workflow Examples

Finding a freelancer:

  1. list_categories() - see available categories
  2. search_gigs("3D character modeling") - browse results
  3. get_gig_details(url) - check pricing tiers (use URL from search results)
  4. get_seller_profile(seller_name) - review their profile (use seller_name from search results)
  5. get_gig_reviews(url) - read reviews

Limitations

  • Reviews - only the first page of reviews is available (Fiverr loads more via AJAX which requires authenticated requests)
  • Rate limiting - Fiverr may block rapid requests. A 2-second minimum delay is enforced between requests (configurable via RATE_LIMIT_DELAY)
  • Data freshness - all data is scraped from public pages in real-time, not cached

How It Works

This server extracts structured data from Fiverr's public pages by reading the Perseus SSR data blob (<script id="perseus-initial-props">) that Fiverr's frontend framework embeds in every page. Uses curl_cffi for browser TLS fingerprint impersonation to handle Cloudflare protection, with automatic retry and fingerprint rotation.

Responsible Use

This tool is intended for personal use - finding freelancers, comparing gigs, and reading reviews through an AI assistant. Please:

  • Do not use for mass data harvesting or building databases of seller information
  • Do not use for automated competitive monitoring at scale
  • Respect Fiverr's infrastructure by keeping the default rate limit
  • Be aware that web scraping may violate Fiverr's Terms of Service

Development

git clone https://github.com/KyuRish/fiverr-mcp-server.git
cd fiverr-mcp-server
uv sync
uv run fiverr-mcp-server

License

MIT

Metadata

Release files for fiverr-mcp-server 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for fiverr-mcp-server 0.1.1
File Size Uploaded
fiverr_mcp_server-0.1.1.tar.gz 58.5 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for fiverr-mcp-server 0.1.1
File Interpreter ABI Platform
fiverr_mcp_server-0.1.1-py3-none-any.whl Python 3 none any Details

Total release size: 72.2 kB

Release files / fiverr_mcp_server-0.1.1.tar.gz

Download URL fiverr_mcp_server-0.1.1.tar.gz
Size 58.5 kB
Tags Source
SHA-256 checksum
How to use checksums
c83315cc3a1494235b6f5f00697f67f1932ba21e7f4d9575253d6141aa691d66
BLAKE2b-256 checksum
How to use checksums
4c3016523ecd56c897ca19b4ab4db4b4f011f37d268e73be44a472ce9c431717
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 23, 2026.

Transparency log

Release files / fiverr_mcp_server-0.1.1-py3-none-any.whl

Download URL fiverr_mcp_server-0.1.1-py3-none-any.whl
Size 13.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
bf4ad1fb75694c43ef0e12b4efa4e8a1f607c1fbfdda5b772f63d77fd9341c62
BLAKE2b-256 checksum
How to use checksums
0dea0dee4a295acdf913894ee11ffd3fcb2c5414522dbdddd1d32b7d9935f1bd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Feb 23, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page