Borrowing it
Nothing to install: this file belongs to shopsavvy/shopsavvy-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shopsavvy/shopsavvy-mcp-server/main/AGENTS.mdgit clone --depth 1 https://github.com/shopsavvy/shopsavvy-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/shopsavvy/shopsavvy-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/shopsavvy/shopsavvy-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/shopsavvy/shopsavvy-mcp-server/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/shopsavvy/shopsavvy-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/shopsavvy/shopsavvy-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00873 | $0.00873 |
| Opus 5.5 | $0.00349 | $0.00349 |
| Sonnet 5.5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
shopsavvy-mcp-server AGENTS.md scanned grade A with 0 findings 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 25d ago.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Context for coding agents (Claude Code, Codex, Cursor, Copilot and others) working in this repository. Humans: see README.md and CONTRIBUTING.md.
Overview
@shopsavvy/mcp-server is a stdio bridge to ShopSavvy's hosted MCP server at https://api.shopsavvy.com/mcp (Streamable HTTP; /mcp/sse for HTTP+SSE clients). It relays JSON-RPC between a stdio-only MCP client and the hosted server. It is not a second implementation: the 15 tools, their schemas and their answers all come from the hosted server, so a change to what a tool does belongs there, not here.
- No API key is needed. Anonymous use is limited per IP (10 tool calls a minute, 100 an hour).
SHOPSAVVY_API_KEYraises it to 100 a minute with no hourly cap, and tool calls then use the key's Data API credits. SHOPSAVVY_MCP_URLpoints the bridge at another deployment (used by tests).- Per-client setup: https://shopsavvy.com/agents#install. Data API docs: https://shopsavvy.com/data/documentation
- MCP registry entry:
server.json(io.github.shopsavvy/shopsavvy-mcp-server), matchingmcpNameinpackage.json.
Layout
src/index.ts: the whole bridge (stdio transport in, Streamable HTTP client out, key validation, User-Agent)tests/test-mcp-server-bridge.test.ts: drives the builtdist/index.jsthrough the official MCP stdio client against the hosted serverserver.json: MCP registry metadata (npm stdio package plus the two remotes)examples/: client config and usage examplestest.sh:--integrationruns live REST checks withSHOPSAVVY_API_KEY
Commands
bun install
bun run build # tsc -> dist/
bun test # needs network: talks to the hosted server, no key required
./test.sh --integration # optional, needs SHOPSAVVY_API_KEY, uses credits
Build before testing: the tests run dist/index.js, not the source.
Code conventions
- stdout carries the MCP protocol. Every log line goes to stderr (
log()insrc/index.ts). A strayconsole.logcorrupts the stream. - Keep the bridge thin: relay messages, set headers, validate the key format, exit with a clear stderr message on misconfiguration. No tool logic, no caching, no rewriting of tool results.
- The key format is
ss_live_orss_test_followed by 32 characters. Reject a malformed key loudly rather than silently falling back to anonymous. - Keep
package.jsonversion,server.jsonversionand the npm package version inserver.json.packagesequal. - TypeScript, ES modules, Node 18+ compatible (the published package runs under
npx).
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.
- 25d ago First seen · 54 lines · 873 tokens per session scan A cd012356d431
shopsavvy-mcp-server AGENTS.md is an instructions file published in the GitHub repository shopsavvy/shopsavvy-mcp-server (9 stars, last pushed 25d ago), licensed MIT. It adds 873 tokens to every session, about $0.0035 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
shopsavvy-mcp-server AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shopsavvy-mcp-server AGENTS.mdshopsavvy/shopsavvy-mcp-server | Instructions file | 9 | 25d ago | MIT | A | 873 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |