agentmods.dev

google_search_mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

google_search_mcp copilot-instructions.md is an instructions file for GitHub Copilot from jspv/google_search_mcp. It costs 906 tokens per session, scanned A, original, MIT.

Repository instructions for a Google Programmable Search MCP server, a program that lets AI agents run Google custom searches through a standard tool connection.

In plain words
What is it for?
They guide changes to the search tool, its command-line and HTTP modes, AWS Lambda and container adapters, domain filtering, safe-search settings, result limits, logging, and secret handling.
Why use it?
They give contributors the server's structure, required configuration, response format, transport options, and rules for protecting search credentials.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is jspv/google_search_mcp's own configuration. It tells GitHub Copilot how to work on google_search_mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything google_search_mcp configures →

not rated 0repo 1y ago A scan 906 tokens original MIT
View source ↗ jspv/google_search_mcp
Reuse

Borrowing it

Nothing to install: this file belongs to jspv/google_search_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jspv/google_search_mcp/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/jspv/google_search_mcp

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for google_search_mcp copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jspv/google_search_mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/jspv/google_search_mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/jspv/google_search_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jspv/google_search_mcp/copilot-instructions/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.

agentmods 80×15 button for google_search_mcp copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jspv/google_search_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jspv/google_search_mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 906 This file is loaded in full into every session.
When invoked 906 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00906 $0.00906
Opus 5.5 $0.00362 $0.00362
Sonnet 5.5 $0.00181 $0.00181
Haiku 4.5 $0.00091 $0.00091

Measured 2mo ago against content hash a5c4b901abd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

google_search_mcp copilot-instructions.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 2mo 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.

.github/copilot-instructions.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions for google_search_mcp

Purpose: Give AI coding agents the minimum, high‑signal context to work productively in this repo.

What this repo is

  • An MCP server exposing one tool: Google Programmable Search (CSE).
  • Same logic runs in 3 surfaces: stdio (default), HTTP over SSE, and Streamable HTTP; plus adapters for AWS Lambda and containers.

Architecture (files you’ll touch)

  • server.py — FastMCP server with a single tool @mcp.tool() async def search(...). Uses one shared httpx.AsyncClient _http (HTTP/2). Config via Dynaconf (GOOGLE_*). Import‑time check requires GOOGLE_API_KEY and GOOGLE_CX.
    • Behavior: num clamped 1..10, safe must be off|active, optional ALLOW_DOMAINS filter, lean responses via fields when lean_fields=True.
    • Return shape (do not change casually): {provider, query, searchInfo, nextPage, latency_ms, results[], raw, trace}. Secrets are never echoed (no API key; cx omitted).
  • server_http.py — ASGI SSE app from the same mcp instance; exposes standard MCP endpoints /sse and /messages (not a custom REST API). CORS via CORS_ORIGINS ("*" default). On shutdown, awaits _http.aclose().
  • server_http_stream.py — Streamable HTTP transport variant; same CORS and shutdown behavior.
  • lambda_handler.py — Bridges Bedrock AgentCore Gateway to the stdio server by spawning python -m server and explicitly passing env.
  • Dockerfile.mcp — Multi‑mode container; MCP_MODE=stdio|http|http-stream (port 8000 by default).
  • Schema tooling: scripts/dump_tool_schema.py and deploy_aws_agentcore_auth0/gen_tool_schema.sh.

Workflows

  • Install deps: uv sync (+ extras as needed: --extra http, --extra lambda, --extra container).
  • Run servers: uv run python -m server | HOST=0.0.0.0 PORT=8000 uv run python -m server_http | uv run python -m server_http_stream.
  • Tests: uv run pytest -q (VS Code Task: “Run tests”). Tests patch env and mock HTTP; no real Google calls.

Conventions and patterns

  • Always reuse the global _http client; do not create per‑request clients. Ensure it’s closed on app shutdown (tests assert aclose() awaited).
  • No custom REST endpoints; only MCP transports. For middleware, attach to the Starlette app in get_app().
  • Config precedence: environment variables override .env (Dynaconf). DYNACONF_DOTENV_PATH is honored.
  • Logging is opt‑in via GOOGLE_LOG_*: logs go to stderr by default; optionally to GOOGLE_LOG_FILE. Query text is logged only if GOOGLE_LOG_QUERY_TEXT=true (hash otherwise).

Read the full file on GitHub · 46 lines

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. 2mo ago First seen · 46 lines · 906 tokens per session scan A a5c4b901abd8

Subscribe to this mod's changes

google_search_mcp copilot-instructions.md is an instructions file published in the GitHub repository jspv/google_search_mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 906 tokens to every session, about $0.0036 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 2026-08-31.

Related

google_search_mcp copilot-instructions.md compared with instructions from other repositories

google_search_mcp copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
google_search_mcp copilot-instructions.mdjspv/google_search_mcpInstructions file01y agoMITA906GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode