A local tool that converts books and other supported document files into clean Markdown chapters for use with language models. It works without internet access or language-model calls and produces repeatable output.

Use it to process EPUB, FB2, DOCX, HTML, TXT, Markdown, or text-based PDF files, organize their chapters, count tokens, and find text.

It removes the need to manually clean and split books before searching or giving them to an AI system.

librarian — MCP server by Terobyte/librarian-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.

Clone the repo

git clone --depth 1 https://github.com/Terobyte/librarian-cli

Made for: Claude Code, Codex, Cursor, Gemini CLI, 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/mcp/terobyte/librarian-cli/librarian/github.svg)](https://agentmods.dev/mcp/terobyte/librarian-cli/librarian)

Your own site

<a href="https://agentmods.dev/mcp/terobyte/librarian-cli/librarian"><img src="https://agentmods.dev/badge/mcp/terobyte/librarian-cli/librarian/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/mcp/terobyte/librarian-cli/librarian"><img src="https://agentmods.dev/badge/mcp/terobyte/librarian-cli/librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

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.

Security

Grade A, and why

librarian 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 1mo 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.

server.json · 11 lines

What it actually says

{
  "librarian": {
    "command": "uvx",
    "args": [
      "librarian-cli"
    ],
    "env": {
      "LIB_HOME": ""
    }
  }
}

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.

1mo ago First seen · 11 lines scan A f624158b43ac

Subscribe to this mod's changes

librarian is an MCP server published in the GitHub repository Terobyte/librarian-cli (2 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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.

Documents LLM claude cli ebooks epub fb2

story-cli

Zero-deploy, Git-native content management CLI for Markdown stories and knowledge bases. Built-in MCP Server for AI integration, EPUB export, and structure-aware data pipelines for LLM fine-tuning. Runs locally from the @yuelinghuashu/story-cli npm package.

yuelinghuashu/story-cli · not measured

pdftomarkdown-fyi

MCP server "pdftomarkdown-fyi" as configured in HEMANT16/pdftomarkdown. Runs locally from the pdftomarkdown-fyi npm package.

HEMANT16/pdftomarkdown · not measured

docs

Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package.

Goldziher/ai-rulez · not measured

pdf-mcp

Gives AI agents agentic RAG over one PDF or a whole folder of them: hybrid semantic + keyword search, selective page reads, tables, images, TOC, OCR, chart data, and CJK/vertical-script support, with SQLite caching. Runs locally from the pdf-mcp Python package. Needs 2 environment variables to run.

jztan/pdf-mcp · not measured

office-oxide-mcp

Rust-native MCP server for Office document processing. Runs locally from the @aimino/opendocswork-mcp npm package.

Aimino-Tech/opendocswork-mcp · not measured

glitchtip

MCP server "glitchtip", hosted remotely at glitchtip.infra.developerz.ai, as configured in developerz-ai/ai-task-master.

developerz-ai/ai-task-master · not measured