What is geminicli-mcp AGENTS.md?

A set of repository instructions for a stateless MCP server that lets Gemini CLI handle requests as a separate command-line process. MCP is a standard way for AI tools to call external services.

Use it when modifying the server, its Gemini invocation code, schemas, tests, or examples, so changes follow the repository's stated design constraints.

It documents the project rules that protect safe argument handling, fresh process execution, minimal dependencies, and predictable server behavior.

How trevoraspencer/geminicli-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to trevoraspencer/geminicli-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/trevoraspencer/geminicli-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/trevoraspencer/geminicli-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/trevoraspencer/geminicli-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/trevoraspencer/geminicli-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/trevoraspencer/geminicli-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/trevoraspencer/geminicli-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/trevoraspencer/geminicli-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/trevoraspencer/geminicli-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 494 This file is loaded in full into every session.

When invoked 494 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.

Model	Per session	Once invoked
Fable 5.1	$0.00494	$0.00494
Opus 5.5	$0.00198	$0.00198
Sonnet 5.5	$0.00099	$0.00099
Haiku 4.5	$0.00049	$0.00049

Measured 2mo ago against content hash 8ebe73b14384, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

geminicli-mcp 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 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.

AGENTS.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Instructions

Project Overview

This project is a stateless stdio MCP server for the Gemini CLI. It exposes Gemini as MCP tools and delegates each call to the headless gemini command.

Repository Layout

src/index.ts: MCP server entry point and tool registration.
src/invoke.ts: Gemini CLI process invocation and result handling.
src/schema.ts: Minimal structured-output schema validation.
test/*.test.mjs: Offline node:test coverage.
examples/: Example configuration and usage snippets.

Design Invariants

The server is stateless. Do not add sessions, resume state, or server-side working-directory switching.
Invoke Gemini with a fresh child process per call and assume one server process per MCP client.
Do not add server-side timeout enforcement; clients and the Gemini CLI are responsible for cancellation and time limits.
Preserve argv-array spawning. Do not concatenate user input into shell strings or rely on shell interpolation.
Child processes inherit the server environment so the Gemini CLI can use the same authentication and configuration as the parent process.
Keep runtime dependencies minimal. @modelcontextprotocol/sdk is the only runtime dependency.
Keep tests on the built-in node:test runner; do not add a third-party test framework.

Development Commands

npm install
npm run build
npm test
npm run lint
npm pack --dry-run

Use npm run test:live only when the Gemini CLI is installed, authenticated, and live CLI behavior is intentionally being tested.

Testing Expectations

Run npm run build before npm test; tests import compiled files from dist/.
Add offline node:test coverage for behavior changes.
Avoid live Gemini tests unless the change specifically depends on real CLI behavior.

Security Cautions

Never log secrets or environment values that may contain credentials.
Preserve argv-array spawning for all user-controlled input.
Do not expose trusted-environment assumptions as user-controlled behavior.
Keep MCP stdout clean. Diagnostics belong on stderr.

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 494 tokens per session scan A 8ebe73b14384

Subscribe to this mod's changes

geminicli-mcp AGENTS.md is an instructions file published in the GitHub repository trevoraspencer/geminicli-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 494 tokens to every session, about $0.0020 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.

geminicli-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
geminicli-mcp AGENTS.mdtrevoraspencer/geminicli-mcp	Instructions file	0	3d ago	MIT	A	494	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

geminicli-mcp: Instructions file for Codex