What is tool-transcribai-mcp AGENTS.md?

A set of AGENTS.md instructions for developing and configuring the tool-transcribai-mcp image-transcription server. AGENTS.md is a project guidance file for coding agents.

It is for working on the server’s OCR, image-listing, image-analysis, and folder-processing tools, including running its type checks and tests.

It tells an agent which tools exist, which commands to run, and which checks are required before considering changes complete.

How psqle22/tool-transcribai-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to psqle22/tool-transcribai-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/psqle22/tool-transcribai-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/psqle22/tool-transcribai-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/psqle22/tool-transcribai-mcp/agents-md.svg)](https://agentmods.dev/instructions/psqle22/tool-transcribai-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/psqle22/tool-transcribai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/psqle22/tool-transcribai-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 993 This file is loaded in full into every session.

When invoked 993 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	$0.00993	$0.00993
Opus 5	$0.00496	$0.00496
Sonnet 5	$0.00199	$0.00199
Haiku 4.5	$0.00099	$0.00099

Measured 7d ago against content hash f2769c5c1503, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tool-transcribai-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 7d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tool-transcribai-mcp

Servidor MCP (Model Context Protocol) para transcribir texto de imágenes con OCR local (tesseract.js) y generar descripciones breves con bajo consumo de tokens. Compatible con ChatGPT, Claude, opencode, Cursor y cualquier cliente MCP.

Herramientas MCP

Registradas en src/server.ts (cada una en src/tools/):

Herramienta	Archivo	Qué hace
`transcribir_imagen`	`tools/transcribir.ts`	OCR local de una imagen → texto plano + bloques con confianza
`listar_imagenes`	`tools/listar.ts`	Lista las imágenes soportadas de un directorio
`analizar_imagen`	`tools/analizar.ts`	OCR + descripción breve (opcional) → `.md`/`.txt`/`.json`, puede guardar archivo
`procesar_carpeta`	`tools/carpeta.ts`	Procesa TODAS las imágenes de una carpeta en lote, un archivo por imagen

Comandos

npm run dev — ejecuta el servidor en modo stdio con tsx
npm run build — compila TypeScript a dist/
npm run start — arranca dist/index.js (uso en producción)
npm test — tests con Vitest (test/)
npm run typecheck — tsc --noEmit
npm run lint — ESLint

Siempre ejecuta npm run typecheck y npm test antes de terminar cualquier cambio.

Convenciones de código

TypeScript ESM: "type": "module", e imports con extensión .js explícita (p. ej. from './config.js'). No uses .ts en los imports.
Todo está en español: mensajes de error, descripciones de schemas y salida de herramientas.
Schemas de entrada con zod (z.object(...)) y type Args = z.infer<...>.
Archivo de servicio por herramienta en src/tools/, lógica compartida en src/services/.
Nunca hagas console.log para responder: las herramientas devuelven textResult(texto) (de src/tools/helpers.ts).
Mensajes de error: ante SecurityError usa ⛔ {message}; para otros errores ❌ Error....

Configuración (variables de entorno)

Prefijo TOOL_TRANSCRIBAI_ (ver src/config.ts):

TOOL_TRANSCRIBAI_ROOT — directorio raíz permitido (por defecto cwd). Cualquier ruta fuera de aquí se rechaza.
TOOL_TRANSCRIBAI_MAX_IMAGE_BYTES — tamaño máximo por imagen (por defecto 20 MB).
TOOL_TRANSCRIBAI_MAX_BATCH — máx. imágenes por carpeta (por defecto 100).
TOOL_TRANSCRIBAI_LANG_PATH — datos de idioma local de Tesseract (para uso offline, sin CDN).
TOOL_TRANSCRIBAI_HTTP=1 + TOOL_TRANSCRIBAI_HTTP_PORT — modo Streamable HTTP (por defecto stdio).
TOOL_TRANSCRIBAI_API_KEY / OPENAI_API_KEY — API key de la IA descriptiva (solo env, nunca argumentos).
TOOL_TRANSCRIBAI_DESCRIBE_ENDPOINT / TOOL_TRANSCRIBAI_DESCRIBE_MODEL — endpoint y modelo (por defecto gpt-4o-mini).

Read the full file on GitHub · 59 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.

7d ago First seen · 59 lines · 993 tokens per session scan A f2769c5c1503

Subscribe to this mod's changes

tool-transcribai-mcp AGENTS.md is an instructions file published in the GitHub repository psqle22/tool-transcribai-mcp (0 stars, last pushed 9d ago), licensed MIT. It adds 993 tokens to every session, about $0.0050 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.

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

tool-transcribai-mcp: Instructions file for Codex