Books For Agents

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill mostly matches its book-summary search purpose, but it also gives the agent direct ability to add and publish content to a shared knowledge base without documented approval, moderation, or rollback controls.

Install only if you are comfortable connecting to the external booksforagents.com MCP service. Use the search/read tools normally, but require your agent to ask before suggesting or publishing books, and do not submit private or sensitive text unless you trust the service.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

An agent could publish unwanted, inaccurate, or low-quality generated content to the shared knowledge base.

Why it was flagged

This exposes a direct publishing action and frames it as the next step after generation, but the artifact does not require explicit user approval, explain moderation, or describe rollback.

Skill content
Use `submit_book` to publish a generated summary directly to the knowledge base. Call this after generating content with `generate_book`.
Recommendation

Make read-only search the default, require explicit user confirmation before `suggest_book` or `submit_book`, and document moderation and rollback behavior.

What this means

If the remote tool returned unsafe or off-task instructions, the agent might over-trust them during content generation.

Why it was flagged

The skill asks the agent to follow instructions returned from a remote MCP tool. This is purpose-aligned for formatting book summaries, but remote instructions should not be treated as higher-priority behavioral instructions.

Skill content
When generating a book, follow the template and instructions returned by `generate_book` exactly.
Recommendation

Treat returned instructions as formatting/content guidance only, and ignore any tool-returned instruction that changes user intent, privacy expectations, or tool-use permissions.

What this means

Users must decide whether they trust the remote service without much registry-level provenance information.

Why it was flagged

The skill relies on a remote MCP service but the provided metadata does not identify a source repository or homepage for users to verify provenance.

Skill content
Source: unknown; Homepage: none
Recommendation

Provide a verifiable homepage or repository and document who operates the MCP endpoint.

What this means

Book queries, suggested titles, and generated summary text may be visible to the external service.

Why it was flagged

The skill connects the agent to an external MCP provider; search queries and submitted summary content are sent outside the local environment. This is disclosed and aligned with the purpose.

Skill content
claude mcp add --transport http books-for-agents https://booksforagents.com/mcp
Recommendation

Avoid sending private or sensitive material unless you trust the service and understand its retention and publication policies.