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.
npx agentmods add instructions/googleapis/mcp-toolbox/gemini-mdgit clone --depth 1 https://github.com/googleapis/mcp-toolboxWhat 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 | $0.03611 | $0.03611 |
| Opus 5 | $0.01806 | $0.01806 |
| Sonnet 5 | $0.00722 | $0.00722 |
| Haiku 4.5 | $0.00361 | $0.00361 |
Grade A, and why
mcp-toolbox GEMINI.md scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. **Test Endpoint:** `curl http://127.0.0.1:5000` How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Toolbox Context & Style Guide
This file (symlinked as CLAUDE.md, AGENTS.md, and .gemini/styleguide.md) provides context and guidelines for AI agents working on the MCP Toolbox for Databases project. It summarizes key information from CONTRIBUTING.md and DEVELOPER.md.
Project Overview
MCP Toolbox for Databases is a Go-based project designed to provide Model Context Protocol (MCP) tools for various data sources and services. It allows Large Language Models (LLMs) to interact with databases and other tools safely and efficiently.
Tech Stack
- Language: Go (1.23+)
- Documentation: Hugo (Extended Edition v0.146.0+)
- Containerization: Docker
- CI/CD: GitHub Actions, Google Cloud Build
- Linting:
golangci-lint
Key Directories
cmd/: Application entry points.internal/sources/: Implementations of database sources (e.g., Postgres, BigQuery).internal/tools/: Implementations of specific tools for each source.tests/: Integration tests.evals/: Evalsets and harness configs for evaluating the prebuilt tool configs with EvalBench; run by.ci/evals.cloudbuild.yaml.docs/en: Project documentation. Separated logically into:documentation/: Documentation and concepts (Section I).integrations/: Reference architectures for DB connectivity and tools (Section II).samples/: Tutorials and code samples (Section III).reference/: CLI info and FAQs (Section IV).
Development Workflow
Prerequisites
- Go 1.23 or later.
- Docker (for building container images and running some tests).
- Access to necessary Google Cloud resources for integration testing (if applicable).
Building and Running
- Build Binary:
go build -o toolbox - Run Server:
go run .(Listens on port 5000 by default) - Run with Help:
go run . --help - Test Endpoint:
curl http://127.0.0.1:5000
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.
- yesterday First seen · 248 lines · 3,611 tokens per session scan A b99bb31d4787
mcp-toolbox GEMINI.md is an instructions file published in the GitHub repository googleapis/mcp-toolbox (16,283 stars, last pushed today), licensed Apache-2.0. It adds 3,611 tokens to every session, about $0.0181 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
open-agents AGENTS.md
AGENTS.md instructions for vercel-labs/open-agents, covering agents.md, quick links, authentication, database & migrations and environment isolation.
Tracely-ai CLAUDE.md
Claude Code instructions for Jwuthri/Tracely-ai, covering claude.md, commands, architecture, hard rules and gotchas.
relay AGENTS.md
Instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.
axonhub AGENTS.md
AGENTS.md instructions for looplj/axonhub, covering agents.md, global rules, configuration, project overview and technology stack.
axonhub CLAUDE.md
Claude Code instructions for looplj/axonhub: @AGENTS.md read and follow its instructions.
neeko AGENTS.md
Instructions for tincopper/neeko, covering neeko — repository guidelines, 项目概览, 目录结构, 前端（feature-based 架构） and 后端（domain-driven 模块化架构）.