Prompts, rules and skills for coding agents, ready to copy. Read only. Search without signing in.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Checks Copybook text already in a repo by the IDs in its From Copybook source lines: <slug>#<8 hex> (the slug of the source URL with each block or unit ID), up to 100, IDs only (no paths or file contents). Each ID is current (the tip still has that text; local edits are not checked) or changed (the tip no longer has it). Also reports each tip as live, superseded (with its replacement) or retired (its latest check broke), with checks and durability. Without IDs, get_tip returns the current text to compare. Needs a Copybook sign-in; without one, the result's message says how to sign in from this client.
The IDs from the source lines above Copybook text in the repo, up to 100, each <slug>#<8 hex>: the slug from the line's URL, then each block or units ID. Never file contents or paths.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http copybook https://copybook.page/mcp/account
Checks Copybook text already in a repo by the IDs in its From Copybook source lines: <slug>#<8 hex> (the slug of the source URL with each block or unit ID), up to 100, IDs only (no paths or file contents). Each ID is current (the tip still has that text; local edits are not checked) or changed (the tip no longer has it). Also reports each tip as live, superseded (with its replacement) or retired (its latest check broke), with checks and durability. Without IDs, get_tip returns the current text to compare. Needs a Copybook sign-in; without one, the result's message says how to sign in from this client.
| Argument | Type | Description |
|---|---|---|
| ids* | array | The IDs from the source lines above Copybook text in the repo, up to 100, each <slug>#<8 hex>: the slug from the line's URL, then each block or units ID. Never file contents or paths. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"ids"
],
"properties": {
"ids": {
"type": "array",
"items": {
"type": "string",
"pattern": "^([a-z0-9]+(?:-[a-z0-9]+)*)#([0-9a-f]{8})(?:-[1-9]\\d{0,2})?$",
"maxLength": 140
},
"maxItems": 100,
"minItems": 1,
"description": "The IDs from the source lines above Copybook text in the repo, up to 100, each <slug>#<8 hex>: the slug from the line's URL, then each block or units ID. Never file contents or paths."
}
},
"additionalProperties": false
}Returns, word for word, the parts of a tip that meet one concise English repo need. The need is a short phrase: no code, file contents, paths or secrets. With slug, it reads that tip alone. state fit: whole blocks or named checklist sections; menu: the tip fits but no part was selected (get_tip has the whole text); none: no part selected (search_tips lists candidates). Each part carries its source line, the tip URL with a mark that check_installed reads later, and its durability, check age and models and conflicts_with. Missing metadata means unknown.
| Argument | Type | Description |
|---|---|---|
| need* | string | One concise English task, up to 200 characters, e.g. limit unrelated code edits. Omit repo/framework details unless essential. Never code, file contents, paths or secrets. |
| slug | string | Optional: a tip already chosen, from a search card, to answer for that tip alone. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"need"
],
"properties": {
"need": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "One concise English task, up to 200 characters, e.g. limit unrelated code edits. Omit repo/framework details unless essential. Never code, file contents, paths or secrets."
},
"slug": {
"type": "string",
"pattern": "^[a-z0-9]+(?:-[a-z0-9]+)*$",
"maxLength": 120,
"minLength": 1,
"description": "Optional: a tip already chosen, from a search card, to answer for that tip alone."
}
}
}Returns one complete tip: its exact Copy assets, three steps, notes, dated saves, latest check, playbooks and related slugs. Takes a slug, a Copybook or voxyz.ai tip URL (English or Chinese) or an X/twitter.com post URL, so a known reference needs no search. An unknown reference returns uncertain suggestions. Install IDs and source lines come from find_snippets; get_tip has none.
| Argument | Type | Description |
|---|---|---|
| slug* | string | A slug, a copybook.page or voxyz.ai tip URL in either language, or the tip's X/twitter.com post URL. Known hosts also work without https://. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "A slug, a copybook.page or voxyz.ai tip URL in either language, or the tip's X/twitter.com post URL. Known hosts also work without https://."
}
}
}List filter ids, plain names, technical terms and current tip counts for search_tips. Counts exclude broken and superseded tips.
No arguments.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
}Searches Copybook's catalog of prompts, rules, skills and setups for coding agents by an English task, with optional kind, topic and tool filters (list_facets lists their values). sort: saves orders by most saved; the default is relevance with a query and newest without. Returns compact cards with the exact paste text, dated saves and the latest check. state: match passes lexical checks, not verified suitability; related can still fit; none means no card. get_tip returns a whole tip; find_snippets(need, slug) returns the parts of one tip a repo needs.
| Argument | Type | Description |
|---|---|---|
| kind | string | Kind id: prompt, rules, skill, plugin, mcp, subagent, command or config; list_facets gives names and counts. |
| sort | string | Order: relevance with a query, newest without (defaults); saves means most saved on X. |
| tool | string | Tool id: claude-code, codex, cursor, pi, grok, gemini or any; list_facets gives current counts. |
| limit | integer | Maximum number of candidates: 1 to 20, default 3. Candidates can be uncertain; check state. |
| query | string | Words or a request in English, up to 200 characters; leave out to list by sort. |
| topic | string | Topic id: repo (Codebase), review (Review), design (Design), long-runs (Long runs), models (Models and cost), ship (Launch), writing (Writing). |
We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 21, 2026.
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"kind": {
"enum": [
"prompt",
"rules",
"skill",
"plugin",
"mcp",
"subagent",
"command",
"config"
],
"type": "string",
"description": "Kind id: prompt, rules, skill, plugin, mcp, subagent, command or config; list_facets gives names and counts."
},
"sort": {
"enum": [
"relevance",
"newest",
"saves"
],
"type": "string",
"description": "Order: relevance with a query, newest without (defaults); saves means most saved on X."
},
"tool": {
"enum": [
"claude-code",
"codex",
"cursor",
"pi",
"grok",
"gemini",
"any"
],
"type": "string",
"description": "Tool id: claude-code, codex, cursor, pi, grok, gemini or any; list_facets gives current counts."
},
"limit": {
"type": "integer",
"default": 3,
"maximum": 20,
"minimum": 1,
"description": "Maximum number of candidates: 1 to 20, default 3. Candidates can be uncertain; check state."
},
"query": {
"type": "string",
"maxLength": 200,
"description": "Words or a request in English, up to 200 characters; leave out to list by sort."
},
"topic": {
"enum": [
"ship",
"design",
"long-runs",
"review",
"repo",
"writing",
"models"
],
"type": "string",
"description": "Topic id: repo (Codebase), review (Review), design (Design), long-runs (Long runs), models (Models and cost), ship (Launch), writing (Writing)."
}
}
}