Install FishClaw MCP

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

git clone https://github.com/TnoobT/FishClaw_MCP.git
cd FishClaw_MCP
pip install -e .

claude mcp add -e "AGENT_LLM_API_KEY=${AGENT_LLM_API_KEY}" fishclaw-mcp -- python /path/to/FishClaw_MCP/server.py

Replace any placeholder paths in the command with the real path on your machine.

Required:AGENT_LLM_API_KEY+ 3 optional

Environment Variables

Set these before running FishClaw MCP.

VariableDescriptionRequired

AGENT_LLM_API_KEYDashScope API Key for LLM inference and content generationYes

IMAGE_API_KEYDashScope API Key for image generationNo

PLAYWRIGHT_HEADLESSWhether to run browser in headless modeNo

ENABLE_FARMINGEnable account farming simulationNo

Once configured, FishClaw MCP gives your AI agent access to:

loginChecks login status or prompts for QR code scan.

search_marketSearches Xianyu for items and collects titles, prices, and links.

keyword

draft_itemFills out a product draft including images, description, category, and price.

titledescriptionprice

publish_itemPublishes the drafted item to the marketplace.

get_selling_itemsRetrieves a list of all currently listed items.

manage_itemDeletes or takes down a specific item.

item_idaction

get_page_contentReads visible text from the current browser page.

simulate_farmingSimulates human-like browsing behavior for account maintenance.

generate_imageGenerates a product cover image using DashScope.

prompt

generate_image_promptGenerates tech-themed English image prompts.

topic

generate_product_descriptionGenerates product descriptions for Xianyu.

topic

After setup, try these prompts with your AI agent:

→Help me publish a Python crawler service for 99 yuan.

→Show me all the items I currently have listed for sale.

→Search for 'Python tutorial' on Xianyu and summarize the pricing of the top results.

→Take down my second listed item.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed
AGENT_LLM_API_KEY — DashScope API Key for LLM inference and content generation

Save the docs, env vars, and workflow around FishClaw MCP in Conare so Claude Code, Codex, and Cursor remember it next time.