Borrowing it
Nothing to install: this file belongs to mordor-forge/gemini-media-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.
curl -O https://raw.githubusercontent.com/mordor-forge/gemini-media-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/mordor-forge/gemini-media-mcpWrote 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/mordor-forge/gemini-media-mcp/agents-md)<a href="https://agentmods.dev/instructions/mordor-forge/gemini-media-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mordor-forge/gemini-media-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.
<a href="https://agentmods.dev/instructions/mordor-forge/gemini-media-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mordor-forge/gemini-media-mcp/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 | $0.02046 | $0.02046 |
| Opus 5.5 | $0.00818 | $0.00818 |
| Sonnet 5.5 | $0.00409 | $0.00409 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
gemini-media-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 3d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guide for coding agents working on gemini-media-mcp: a Go MCP server
(module github.com/mordor-forge/gemini-media-mcp, binary gemini-media-mcp,
MCP server name gemini-media) for Google's generative media models - Nano
Banana images, Veo and Gemini Omni video, Gemini TTS and Lyria music - on the Gemini API or
Vertex AI. Go 1.26+ (see go.mod).
Commands
go build ./... # build
go test -race ./... # unit tests (no network, no API key)
go vet ./...
golangci-lint run # lint (golangci-lint v2)
go test ./internal/catalog # after editing internal/catalog/models.yaml
go run ./cmd/gemini-media-mcp doctor # check credentials/models (makes a free list call)
go run ./cmd/gemini-media-mcp models --all # print the catalog
npx @modelcontextprotocol/inspector go run ./cmd/gemini-media-mcp # poke the tools interactively
scripts/validate-packaging.sh # after touching any manifest, script or skill
Run build, vet, tests and lint before you say a change is done.
Rules that are easy to break
- E2E tests cost real money.
internal/media/e2e_test.go(build tage2e) calls Google's paid APIs and needsGEMINI_MEDIA_E2E=1plusGEMINI_API_KEY(or Vertex credentials); the Veo test (GEMINI_MEDIA_E2E_VIDEO=1) costs about $0.20 and the Omni test (GEMINI_MEDIA_E2E_OMNI=1) about $0.30. Never run them - or any command that generates media - unless the user explicitly asks.go test ./...without the tag is free. Live E2E runs are local-only; CI only compiles and vets the tagged tests. - stdout is the MCP JSON-RPC channel. In
serve(stdio) mode any byte written to stdout that is not protocol traffic breaks the client. Log with the injected*slog.Logger(it writes to stderr); neverfmt.Print*orlog.Print*to stdout from server code. The same holds formcpb/launch.sh. Only the one-shot subcommands (doctor,models,usage,version,configure) print to stdout. - Never log, echo or return credentials. Config files holding keys are written with mode 0600; keep it that way.
- Model facts live in data, not code.
internal/catalog/models.yamlis the single source of truth for model IDs, aliases, lifecycle dates, capabilities, constraints and prices. When Google adds, renames, reprices or retires a model, edit the YAML - not Go code. - Errors must be actionable. Return
internal/apperrclassified errors whose message tells the agent or user what to do next (which parameter, which command, which setting).
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.
- 3d ago First seen · 143 lines · 2,046 tokens per session scan A 952fa956125e
gemini-media-mcp AGENTS.md is an instructions file published in the GitHub repository mordor-forge/gemini-media-mcp (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,046 tokens to every session, about $0.0082 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 2026-10-08.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode design-tokens.instructions.md
Design-system size tokens (spacing, corner radius, font size, codicon size, stroke). Use when writing or editing CSS to size, space, or round UI — prefer the --vscode- token vars over hardcoded px values.