gemini-cli-mcp-config-format-matrix

gemini-cli-mcp-config-format-matrix is a skill for Claude Code from davidruzicka/mcp4openapi. It costs 57 tokens per session (1,156 once invoked), scanned A, original, MIT.

A set of rules for writing or checking Gemini CLI configuration for MCP servers. Gemini CLI is a command-line tool, and MCP servers provide extra connections or tools to an agent.

In plain words
What is it for?
Generating and reviewing Gemini CLI settings and commands for local or web-based MCP servers.
Why use it?
It prevents configuration examples from mixing Gemini's format with formats used by other clients.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex; mentions Gemini CLI.

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 skills/davidruzicka/mcp4openapi/gemini-cli-mcp-config-format-matrix
Any agent
npx skills add davidruzicka/mcp4openapi --skill gemini-cli-mcp-config-format-matrix
Clone the repo
git clone --depth 1 https://github.com/davidruzicka/mcp4openapi

Made for: Claude Code.

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 gemini-cli-mcp-config-format-matrix

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidruzicka/mcp4openapi/gemini-cli-mcp-config-format-matrix.svg)](https://agentmods.dev/skills/davidruzicka/mcp4openapi/gemini-cli-mcp-config-format-matrix)
Your own site
<a href="https://agentmods.dev/skills/davidruzicka/mcp4openapi/gemini-cli-mcp-config-format-matrix"><img src="https://agentmods.dev/badge/skills/davidruzicka/mcp4openapi/gemini-cli-mcp-config-format-matrix.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,156 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00057 $0.01156
Opus 5 $0.00028 $0.00578
Sonnet 5 $0.00011 $0.00231
Haiku 4.5 $0.00006 $0.00116

Measured 5d ago against content hash df624fab9f48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gemini-cli-mcp-config-format-matrix 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 5d 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.

.claude/skills/gemini-cli-mcp-config-format-matrix/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Generate correct Gemini CLI MCP configuration without mixing formats from other clients.

Rules

  1. Prefer Gemini-native JSON config in settings.json:
    • top-level mcpServers for server entries.
    • optional top-level mcp for global policies (allowed, excluded, optional serverCommand).
  2. For stdio servers, use server entry fields compatible with Gemini CLI:
    • command, optional args, optional cwd, optional timeout, optional trust.
    • Do not generate env for Gemini snippets as a generic tunneling mechanism for host env vars.
  3. For streamable HTTP servers, use httpUrl in server entry.
  4. For HTTP auth headers, use Gemini-native header mapping:
    • JSON: headers: { "Authorization": "Bearer ..." }
    • CLI: --header "Authorization: Bearer ..."
  5. Keep Gemini snippets client-native:
    • Do not emit Codex TOML fields (bearer_token_env_var, http_headers, env_http_headers).
    • Do not emit Claude Desktop MCP format.
  6. Preserve secure placeholder values in examples:
    • Prefer placeholders like ${TOKEN_ENV_VAR} in JSON examples instead of hardcoded secrets.
  7. When server filtering is required, use Gemini fields:
    • includeTools / excludeTools on the server entry.
  8. When generating commands for management operations, use Gemini CLI verbs:
    • gemini mcp add -s user ...
    • gemini mcp list
    • gemini mcp remove <name>
  9. Do not generate --env flags for Gemini CLI snippets.

Output Patterns

  • Local stdio snippet: JSON mcpServers.<name>.command with optional args and env.
  • Remote streamable snippet: JSON mcpServers.<name>.httpUrl with optional headers.

JSON Examples (Gemini Docs Aligned)

Use these as canonical formatting references for settings.json.

Stdio server with args

{
  "mcpServers": {
    "gitlab": {
      "command": "npx",
      "args": ["-y", "mcp4openapi", "--profile", "gitlab"]
    }
  }
}

Streamable HTTP server with OAuth (or none) autentization

{
  "mcpServers": {
    "gitlab": {
      "httpUrl": "https://<cmp_server_host>/profile/gitlab/mcp"
    }
  }
}

Read the full file on GitHub · 144 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. 5d ago First seen · 144 lines · 57 tokens per session scan A df624fab9f48

Subscribe to this mod's changes

gemini-cli-mcp-config-format-matrix is a skill published in the GitHub repository davidruzicka/mcp4openapi (0 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,156 once invoked, about $0.0003 per session on Opus 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

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens