mcp AGENTS.md

Repository instructions for developing the @rendobar/mcp server, a local program that lets AI agents use Rendobar media tools. They describe project structure, release rules, testing constraints, and communication requirements.

In plain words
What is it for?
Use them when modifying, testing, releasing, or reviewing the Rendobar MCP server and its SDK dependencies.
Why use it?
They prevent changes that could break the server connection, release process, startup speed, or package compatibility. They also keep the server consistent with the wider Rendobar codebase.

Instructions file for CodexOpenCode

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 instructions/rendobar/mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/rendobar/mcp

Made for: Codex, OpenCode.

Per session 940 This file is loaded in full into every session.
When invoked 940 The same file — it is already loaded in full.
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 $0.00940 $0.00940
Opus 5 $0.00470 $0.00470
Sonnet 5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured yesterday against content hash 8297c353955b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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 · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — @rendobar/mcp

Guide for agents and humans working on the Rendobar MCP server. Companion to the monorepo guide at rendobar/rendobar. Dev rules, build/test commands, and the MCP-specific hard bans live in CLAUDE.md — read it before changing code.

TL;DR

  • What this is: the local stdio Model Context Protocol server for Rendobar. Single ESM bundle, ~6 tools, public, MIT.
  • SDK source: lives in the rendobar/rendobar monorepo under packages/sdk/. Consumed here as @rendobar/sdk from npm.
  • Release: conventional commits → release-please → npm publish with provenance + .mcpb GitHub Release asset + official MCP registry.
  • No manual tags, no manual version bumps. release-please owns them.

The rules that bite (full detail in CLAUDE.md)

  • Never write to stdout. It is reserved for JSON-RPC framing; one stray byte kills the connection. Logs go to stderr.
  • Recoverable tool failures return { isError: true }, not throws. Throw only for programmer bugs.
  • Cold-start budget < 2 s, bundle < 100 KB. CI asserts both. No network calls at module load.
  • One Zod version. The SDK uses zod/v4; two copies break registerTool. Fix the dep tree, never as any.

Cross-repo brand consistency

This repo is part of the broader Rendobar platform. The canonical reference for brand strings, URLs, and metadata across every rendobar repo is the apex monorepo's .claude/rules/brand-consistency.md:

https://github.com/rendobar/rendobar/blob/main/.claude/rules/brand-consistency.md

Canonical brand strings (must match apex)

Field Value
Display name Rendobar
Slogan Media processing API for developers and agents
Apex URL https://rendobar.com
Apex page URLs https://rendobar.com/<path>/ (always trailing slash)
API URL https://api.rendobar.com
Dashboard URL https://app.rendobar.com
CDN URL https://cdn.rendobar.com
Twitter handle @rendobar
Discord https://discord.gg/kAGqjBzx8N

Read the full file on GitHub · 61 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. yesterday First seen · 61 lines · 940 tokens per session scan A 8297c353955b

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository rendobar/mcp (1 stars, last pushed yesterday), licensed MIT. It adds 940 tokens to every session, about $0.0047 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 instructions, from other repositories