ebay-mcp CLAUDE.md

A set of project instructions for an eBay MCP server, a program that lets AI tools search eBay's public buy-side listings. It documents the package layout, credentials, development commands, and available search tools.

In plain words
What is it for?
Use it when developing or operating the server's listing search, item-detail lookup, and price comparison features.
Why use it?
It gives developers the information needed to run, test, and safely configure the server. It also explains how credentials are stored and that the server reads public listing data without saving it.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cunicopia-dev/ebay-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/cunicopia-dev/ebay-mcp
Per session 315 This file is loaded in full into every session.
When invoked 315 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00315 $0.00315
Opus 5 $0.00158 $0.00158
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00032 $0.00032

Measured yesterday against content hash e0c3d5bf870b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ebay-mcp CLAUDE.md scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

Stored in `~/.ebay-mcp.toml` (chmod 600). Never committed. Env vars override TOML.
CLAUDE.md · 42 lines

What it actually says

ebay-mcp

eBay Browse API MCP server — read-only, buy-side listing search and price intelligence.

Package layout

src/ebay_mcp/
  __init__.py   version
  config.py     credential loader (TOML + env vars) + ebay-mcp-config CLI
  browse.py     EbayBrowseClient — OAuth token cache + Browse API calls
  server.py     MCP server (list_tools / call_tool / main)
tests/
  test_config.py   config load + env-var precedence (no network)
  test_server.py   dispatch + price aggregation (mocked client)

Credentials

Stored in ~/.ebay-mcp.toml (chmod 600). Never committed. Env vars override TOML. Uses eBay's application client-credentials grant — no user login, no stored user data. This server only reads public buy-side listing data and does not persist any eBay data.

Dev

python3.12 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
ruff check .
mypy src/
pytest
ebay-mcp-config      # validate active credentials

Tools

Tool What it does
ebay_search Listing search with sort/filter/category
ebay_get_item Single item detail by ID
ebay_price_check Aggregated price landscape (min/median/max by condition)
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 42 lines · 315 tokens per session scan B e0c3d5bf870b

Subscribe to this mod's changes

ebay-mcp CLAUDE.md is an instructions file published in the GitHub repository cunicopia-dev/ebay-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 315 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens