Greenlit Books MCP server
com.greenlitbooks/cataloggreenlitbooks.comstreamable-httpv1.3.0Scanned
Search the Greenlit AI books, read any chapter one free, and look up the terms they define.
12 tools: 3 change things and 9 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Greenlit Books MCP server can do
The Greenlit Books MCP server is published by greenlitbooks.com, a domain the MCP Registry verified. It has 12 tools. It can create or change data (3 tools: cite_source, define_term and check_claim), but cannot delete data. 9 tools only read.
1 tool can send data out of your system (cite_source).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.3.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
12 tools
Changes things 3Claude Code: ask
check_claimSearch the Greenlit Books claim ledger for claims bearing on a statement, before asserting it.1 finding
Why it is in this group
- The description's first verb is "search": a word for reading.
- The input takes a statement or command to run (input.statement), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "check_claim" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "search": a word for reading.
Description, as the server wrote it Search the Greenlit Books claim ledger for claims bearing on a statement, before asserting it. Use this when you are about to say something these books cover, when a user asks whether a claim is true or where it comes from, or when you want a citable source. Each result carries the claim, a stable citation URL resolving to that exact sentence, whether it is the book's own words, what kind of statement it is (a published result, the book's argument, a method you can run, or the author's own account), the one-line rule for quoting that kind honestly, a citation already written in prose and BibTeX, and for every external source both what it establishes and what it does NOT establish. Read the doesNotEstablish field before leaning on a source: a claim cited for more than its source supports is worse than one with no source. Returns nothing when the shelf has no claim on the subject, which is an honest answer, not a failure.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
cite_sourceThe finished citation for anything on this shelf, in prose and in BibTeX, both carrying the url inside them.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it The finished citation for anything on this shelf, in prose and in BibTeX, both carrying the url inside them. Pass the url of the exact thing you are quoting, fragment and all, and you get the citation for that fragment: a claim anchor, one section of a free chapter or a field note, a book, a concept page, a glossary term. Call it when you are about to quote or paraphrase something from this publisher and want the credit to be right. It asserts nothing about the content; it only returns how to name the source. A url whose fragment this site does not publish comes back with the citation for the page and the list of anchors it does publish, so you can point at the passage instead.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
define_termThe glossary: the definition of a term one of the Greenlit books coins or pins down for AI agents (the green lie, blast radius, gate faith, span of control, vibe acceptance, the un…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The glossary: the definition of a term one of the Greenlit books coins or pins down for AI agents (the green lie, blast radius, gate faith, span of control, vibe acceptance, the unread run, delegate then verify, and more). Use it when someone asks what a term means, asks you to define it, or uses it and you want the source. Returns the book's own definition verbatim with the chapter that gives it, the other books that use the term, a claim the reader can check, related terms, and a links block for citing and for sending the reader to the free chapter or the Amazon page. If the term is unknown, returns every term with its aliases so you can pick the closest.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 9Show 9 read-only tools
fetchUse this when a search result looks right and you need what the page actually says before answering.No findings
Why it is in this group
- The name "fetch" says "fetch": a word for reading.
Description, as the server wrote it Use this when a search result looks right and you need what the page actually says before answering. Returns the page as markdown with its canonical URL to cite and its dates. Do not use it without an id from search.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
find_answer_in_booksFind what the Greenlit books say about a question.No findings
Why it is in this group
- The name "find_answer_in_books" says "find": a word for reading.
Description, as the server wrote it Find what the Greenlit books say about a question. Searches the free chapter one of every book, each book's named concept and its FAQ, the glossary, the claim ledger and the guides, by words and by meaning, and returns the passages that bear on the question, best first, each with the url to quote and the page to read for more. Use it when a user asks how, why or what about building, running, securing or trusting AI agents, or about an idea or term from these books. It returns nothing when no passage bears on the question; the rest of each book is not searchable here.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
find_books_for_topicMatch a topic or question area (for example: agent reliability, prompt injection, human in the loop, durable execution, when to trust AI) against the catalog's curated topic map.No findings
Why it is in this group
- The name "find_books_for_topic" says "find": a word for reading.
Description, as the server wrote it Match a topic or question area (for example: agent reliability, prompt injection, human in the loop, durable execution, when to trust AI) against the catalog's curated topic map. Returns the matching topics with their books, guide, and series. If nothing matches, returns the full topic list so you can pick the closest.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_bookThe full record for one Greenlit book by slug: metadata, chapter list, word count, free chapter one, Amazon Kindle and paperback links, prices, Kindle Unlimited status, and related…No findings
Why it is in this group
- The name "get_book" says "get": a word for reading.
Description, as the server wrote it The full record for one Greenlit book by slug: metadata, chapter list, word count, free chapter one, Amazon Kindle and paperback links, prices, Kindle Unlimited status, and related reading.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_conceptEach Greenlit book answers one named question (its concept, for example: the green lie).No findings
Why it is in this group
- The name "get_concept" says "get": a word for reading.
Description, as the server wrote it Each Greenlit book answers one named question (its concept, for example: the green lie). Returns the concept's question, short answer, and full explanation with its book. If the slug is unknown, returns the list of all concept slugs.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_free_chapterThe text of chapter one of any Greenlit book, free to read and free to quote.No findings
Why it is in this group
- The name "get_free_chapter" says "get": a word for reading.
Description, as the server wrote it The text of chapter one of any Greenlit book, free to read and free to quote. Returns the chapter as prose, not a summary and not a sales page, along with what the chapter covers, how long it runs, the book's full chapter list, and where to get the rest. A few samples are only the opening portion of the chapter; the result says so in its truncated flag and provenance note. Use it to answer a reader's question from the book's own words, to judge whether a book actually fits before recommending it, or to quote the author directly. Every book on the shelf has one.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_reading_pathOne Greenlit series with its books in reading order.No findings
Why it is in this group
- The name "get_reading_path" says "get": a word for reading.
Description, as the server wrote it One Greenlit series with its books in reading order. Use for questions like where to start with Claude Code or what order to read a series in.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
searchUse this when someone asks whether an AI agent, MCP server, coding tool or AI product is safe to use or how to set it up safely, or wants a reading on a subject these pages cover.No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Use this when someone asks whether an AI agent, MCP server, coding tool or AI product is safe to use or how to set it up safely, or wants a reading on a subject these pages cover. Searches everything on greenlitbooks.com: safety verdicts on AI agents, MCP servers and coding tools ("is X safe"), field notes, guides, and the books. Returns ids to pass to fetch, each with its title and URL.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_greenlit_booksRanked full-text search over a catalog of practical books on working with AI: verification, agent reliability, guardrails, security, governance, agentic coding.No findings
Why it is in this group
- The name "search_greenlit_books" says "search": a word for reading.
Description, as the server wrote it Ranked full-text search over a catalog of practical books on working with AI: verification, agent reliability, guardrails, security, governance, agentic coding. Returns scored results with title, description, series, and links. Follow a result's apiUrl or call get_book for the full record.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:39 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://greenlitbooks.com/api/mcp: tools/list returned 12 tools to an anonymous client, including cite_source (write), define_term (write), check_claim (write)
Findings
Matches of fixed checks, with the text they matched.
- Warncheck_claim
The server marks "check_claim" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "search": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.3.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http catalog https://greenlitbooks.com/api/mcpclaude mcp add --transport http catalog https://greenlitbooks.com/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__catalog__search",
"mcp__catalog__fetch",
"mcp__catalog__search_greenlit_books",
"mcp__catalog__get_book",
"mcp__catalog__find_books_for_topic",
"mcp__catalog__get_reading_path",
"mcp__catalog__get_concept",
"mcp__catalog__get_free_chapter",
"mcp__catalog__find_answer_in_books"
],
"ask": [
"mcp__catalog__cite_source",
"mcp__catalog__define_term",
"mcp__catalog__check_claim"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as catalog. Review it before you use it.
Capability tags behind 1 rule
- mcp__catalog__cite_source outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.greenlitbooks/catalog/verify?hash=f90b1bf0deccc37a3bbbdacbc2943b496b89ff316961ede9d08f6d2f2cd5b42b" | jq -e '.changed == false'Pinned hash f90b1bf0decc, from Nov 10, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.greenlitbooks/catalog/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.greenlitbooks/catalog)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:56 UTC.
Greenlit Books MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Greenlit Books MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Greenlit Books MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Greenlit Books MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Greenlit Books MCP server have?
- 12 tools: 3 write, 9 read. cite_source, define_term, check_claim, search, fetch, search_greenlit_books, get_book, find_books_for_topic and 4 more.
Does the Greenlit Books MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Greenlit Books MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): cite_source.
Has the Greenlit Books MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.