FrankenFish
Provides optional LLM-drafted buyer replies through an OpenAI-compatible API, with guard rails that flag off-platform words, clamp bargain offers below the floor price, and never auto-send messages.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
🧟 FrankenFish — the second-hand electronics shop assistant stitched from spare parts
Kiroween 2026 · Frankenstein category · built with Kiro
FrankenFish stitches together pieces that were never meant to meet:
Body part | What it is | Role |
🦴 Skeleton | goofish-cli (Apache-2.0) MCP server | Talks to Xianyu (闲鱼), China's largest second-hand marketplace, on the seller's own account |
🧠 Brain | Any OpenAI-compatible LLM (domestic or overseas, user's own key) | Drafts buyer replies in Chinese |
🫀 Heart | FrankenFish MCP server (this repo) | Price radar, pricing rules for used phones/laptops, reply guard rails |
⚡ Lightning | Kiro specs, hooks and steering | How the creature was assembled |
Who it is for: one-person second-hand electronics shops on Xianyu. The owner does sourcing, listing, customer service and after-sales alone. FrankenFish answers three questions every day:
What should I price this used iPhone 15 Pro 256G 95新 at? →
suggest_priceWhat is the market doing for this model this week? →
market_snapshotHow do I answer this buyer who is haggling / asking about battery health? →
draft_reply(never sends on its own)
Quick start (demo mode — no Xianyu account needed)
pip install -e .
frankenfish demo # colourful walkthrough from bundled synthetic dataExpected output: market snapshot → price suggestion → three buyer reply drafts. Runs in under one second.
MCP server (Kiro / Claude Code / any MCP client)
{ "mcpServers": { "frankenfish": { "command": "frankenfish", "args": ["mcp"] } } }Three tools are available:
Tool | Description |
| p25 / median / p75 of listing prices, outliers removed |
| list price (ends in 9) + floor price + basis explanation |
| classifies message, drafts Chinese reply, flags off-platform words, never auto-sends |
Every tool returns {"ok": bool, "data": ..., "error": str|null, "source": str}.
Related MCP server: xianyu-mcp
Live mode (optional — seller's own account only)
Install goofish-cli:
pip install goofish-cliAuthenticate:
goofish auth login --qrSet the env var:
FRANKENFISH_SOURCE=goofish
FrankenFish queries goofish-cli at most 3 times per minute and caches results for 1 hour. If goofish-cli is missing or not logged in, it falls back to demo data automatically.
LLM reply drafting (optional)
Set these env vars to enable LLM-drafted replies (falls back to rule-based drafts when unset):
FRANKENFISH_LLM_BASE_URL=https://api.openai.com/v1
FRANKENFISH_LLM_KEY=sk-...
FRANKENFISH_LLM_MODEL=gpt-4o-mini # any OpenAI-compatible modelThe same guard rails apply to LLM output: off-platform words are flagged, bargain offers
below floor_price are clamped, and auto_send is always False.
Pricing rules
Input | Adjustment |
Condition grade (全新/99新/95新/9新/8新/7新及以下) | ×1.10 to ×0.62 of market median |
Battery health < 85% | −5% |
Full original box included | +2% |
Valid Apple/manufacturer warranty remaining | +3% |
Outliers (< 40% or > 200% of raw median) | excluded before statistics |
list_price | rounded to nearest ¥10, then −¥1 (ends in 9) |
floor_price | min(list_price, p25 × factor) × 0.97, capped at list_price |
Tests
pip install -e ".[dev]"
PYTHONPATH=src python -m pytest -q24 tests including Hypothesis property tests for every pricing rule (R1–R3) and reply guard rails (R4.1–R4.4).
Responsible use
Demo data in
src/frankenfish/data/is synthetic (every row has"synthetic": true).Live mode reads a small number of on-demand searches on the seller's own account only.
No bulk scraping, no storing other users' data beyond a 1-hour in-process cache.
Replies are never sent automatically (
auto_sendis alwaysFalse).See
docs/compliance.mdfor full details.
How Kiro was used
See .kiro/ (specs, steering, hooks) and docs/kiro-writeup.md.
License
MIT. Uses goofish-cli (Apache-2.0) as an optional external dependency — see NOTICE.
中文说明
FrankenFish(缝合鱼)是给闲鱼数码个体店主用的 AI 助手:行情雷达 + 智能定价 + 客服回复草稿,以 MCP 工具形式接入 Kiro、Claude Code 等。
默认演示模式用合成数据,不需要闲鱼账号;实盘模式只用卖家本人账号、按需少量查询(≤3次/分钟,缓存1小时),不批量爬取、不自动发消息。
可选 LLM 接入(OpenAI 兼容接口),未配置时降级为规则模板。每条定价建议都有 basis 字段解释每一步调整,议价回复永远不低于 floor_price。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Live second-hand price estimates with confidence for AI agents. Cached lookups free.
Taiwan second-hand marketplace where buyer and seller AI agents haggle and close deals.
Drafts eBay listings from your item photos: title, description, price and condition.
AI resale manager. Photograph an item, AI writes the listing, publish a sale page, manage pickups.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interact with Goofish (闲鱼) marketplace, supporting product search, batch inquiry messaging, and conversation management for buyers.4MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to search Xianyu second-hand marketplace for product prices with automatic cookie detection.2-
- AlicenseNot gradedqualityDmaintenanceEnables automating buyer-side workflows on Xianyu (Goofish) by searching products, sending individual or batch price inquiries, and retrieving seller responses through MCP tools.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables searching Xianyu (Goofish) listings, fetching item details, taking keyword-monitor snapshots, and publishing secondhand products through MCP tools with local-session authentication.MIT