MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Guide to designing and building MCP servers: tool, resource and prompt design for agent usability, with TypeScript or Python implementation workflows.
Install MCP Server Builder
$ npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shareAI-lab/Kode-CLI mcp-builder --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/builtin-skills/skills/mcp-builder .claude/skills/mcp-builder && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "mcp-builder" agent skill from https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builder into .claude/skills/mcp-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-builder", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builderType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shareAI-lab/Kode-CLI mcp-builder --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/builtin-skills/skills/mcp-builder .agents/skills/mcp-builder && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "mcp-builder" agent skill from https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builder into .agents/skills/mcp-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-builder", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shareAI-lab/Kode-CLI mcp-builder --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/builtin-skills/skills/mcp-builder .cursor/skills/mcp-builder && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "mcp-builder" agent skill from https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builder into .cursor/skills/mcp-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-builder", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/shareAI-lab/Kode-CLI.git --path packages/builtin-skills/skills/mcp-builder--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shareAI-lab/Kode-CLI mcp-builder --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/builtin-skills/skills/mcp-builder .gemini/skills/mcp-builder && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "mcp-builder" agent skill from https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builder into .gemini/skills/mcp-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-builder", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install shareAI-lab/Kode-CLI mcp-builderInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/builtin-skills/skills/mcp-builder .github/skills/mcp-builder && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "mcp-builder" agent skill from https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builder into .github/skills/mcp-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-builder", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shareAI-lab/Kode-CLI mcp-builder --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shareAI-lab/Kode-CLI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/builtin-skills/skills/mcp-builder .opencode/skills/mcp-builder && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "mcp-builder" agent skill from https://github.com/shareAI-lab/Kode-CLI/tree/main/packages/builtin-skills/skills/mcp-builder into .opencode/skills/mcp-builder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-builder", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
mcp-builder- GitHub stars
- 5.2k
- Token cost
- ~1.9k tokens
- SKILL.md length
- 762 words
- Files
- 5
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Guide to designing and building MCP servers: tool, resource and prompt design for agent usability, with TypeScript or Python implementation workflows.
- Works in 3 steps: Deep Research and Planning → Implementation → Review and Test
- Designing the tools of a new MCP server for an external service
- SKILL.md covers Overview, 🚀 High-Level Workflow and 📚 Documentation Library
- Reaches raw.githubusercontent.com and modelcontextprotocol.io
What it does
An MCP server is judged by how well it lets an LLM finish real tasks through well-designed tools. The agent first asks once for the target SDK, TypeScript, Python or another official one, and for the language of the walkthrough, English or Chinese. Phase one is research and planning: balance full API coverage against specialized workflow tools, preferring coverage when unsure, use consistent action-oriented tool names with prefixes, keep descriptions concise with filtering and pagination, and write error messages that suggest next steps.
The agent is also told to study the MCP specification, starting from its sitemap and fetching pages as markdown, covering the architecture, transports such as streamable HTTP and stdio, and tool, resource and prompt definitions. TypeScript is the recommended stack. Reference files cover MCP best practices, Node servers and Python servers. The excerpt ends in the first phase, so later phases are not described here.
When your agent uses it
- Designing the tools of a new MCP server for an external service
- Choosing between TypeScript and Python for an MCP server
- Reviewing tool names, error messages and pagination for agent usability
Example prompts
- “Build an MCP server for our internal ticketing API in TypeScript.”
- “Review the tool names and error messages in my Python MCP server for agent usability.”
- “Plan which of our REST endpoints become MCP tools and which become higher-level workflow tools.”
Requirements
- A TypeScript or Python MCP SDK, chosen when the build starts
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c7f6fcc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
raw.githubusercontent.commodelcontextprotocol.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
MCP Server Builder loads about 1.9k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 762 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from shareAI-lab/Kode-CLI at commit c7f6fcc, republished under its Apache-2.0 licence (© shareAI-lab). 762 words, ~1,861 tokens.
Download SKILL.mdSave it as
.claude/skills/mcp-builder/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- mcp-builder
- description
- Guide for building high-quality MCP (Model Context Protocol) servers and tools: what MCP is, how to design tools/resources/prompts for agent usability, and how to implement servers in TypeScript or Python. Use when you need MCP best practices, server architecture patterns, or a step-by-step build workflow (with language preference).
- license
- Complete terms in LICENSE.txt
MCP Server Development Guide
Overview
Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
Process
🚀 High-Level Workflow
Creating a high-quality MCP server involves three main phases:
Before starting, confirm two preferences (ask once):
- Target implementation language/SDK (TypeScript SDK, Python SDK, or another official MCP SDK)
- Preferred language for the build walkthrough (English / 中文)
Phase 1: Deep Research and Planning
1.1 Understand Modern MCP Design
API Coverage vs. Workflow Tools: Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage.
Tool Naming and Discoverability:
Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., github_create_issue, github_list_repos) and action-oriented naming.
Context Management: Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently.
Actionable Error Messages: Error messages should guide agents toward solutions with specific suggestions and next steps.
1.2 Study MCP Protocol Documentation
Navigate the MCP specification:
Start with the sitemap to find relevant pages: https://modelcontextprotocol.io/sitemap.xml
Then fetch specific pages with .md suffix for markdown format (e.g., https://modelcontextprotocol.io/specification/draft.md).
Key pages to review:
- Specification overview and architecture
- Transport mechanisms (streamable HTTP, stdio)
- Tool, resource, and prompt definitions
1.3 Study Framework Documentation
Recommended stack:
- Language: TypeScript (high-quality SDK support and good compatibility in many execution environments e.g. MCPB. Plus AI models are good at generating TypeScript code, benefiting from its broad usage, static typing and good linting tools)
- Transport: Streamable HTTP for remote servers, using stateless JSON (simpler to scale and maintain, as opposed to stateful sessions and streaming responses). stdio for local servers.
Load framework documentation:
- MCP Best Practices: 📋 View Best Practices - Core guidelines
For TypeScript (recommended):
- TypeScript SDK: Use WebFetch to load
https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md - ⚡ TypeScript Guide - TypeScript patterns and examples
For Python:
- Python SDK: Use WebFetch to load
https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md - 🐍 Python Guide - Python patterns and examples
1.4 Plan Your Implementation
Understand the API: Review the service's API documentation to identify key endpoints, authentication requirements, and data models. Use web search and WebFetch as needed.
Tool Selection: Prioritize comprehensive API coverage. List endpoints to implement, starting with the most common operations.
Phase 2: Implementation
2.1 Set Up Project Structure
See language-specific guides for project setup:
- ⚡ TypeScript Guide - Project structure, package.json, tsconfig.json
- 🐍 Python Guide - Module organization, dependencies
Show full SKILL.md (314 more words)Show less
2.2 Implement Core Infrastructure
Create shared utilities:
- API client with authentication
- Error handling helpers
- Response formatting (JSON/Markdown)
- Pagination support
2.3 Implement Tools
For each tool:
Input Schema:
- Use Zod (TypeScript) or Pydantic (Python)
- Include constraints and clear descriptions
- Add examples in field descriptions
Output Schema:
- Define
outputSchemawhere possible for structured data - Use
structuredContentin tool responses (TypeScript SDK feature) - Helps clients understand and process tool outputs
Tool Description:
- Concise summary of functionality
- Parameter descriptions
- Return type schema
Implementation:
- Async/await for I/O operations
- Proper error handling with actionable messages
- Support pagination where applicable
- Return both text content and structured data when using modern SDKs
Annotations:
readOnlyHint: true/falsedestructiveHint: true/falseidempotentHint: true/falseopenWorldHint: true/false
Phase 3: Review and Test
3.1 Code Quality
Review for:
- No duplicated code (DRY principle)
- Consistent error handling
- Full type coverage
- Clear tool descriptions
3.2 Build and Test
Verification is client- and environment-specific. Focus on correctness and agent usability:
- Ensure tools/resources/prompts are discoverable, well-described, and return constrained outputs.
- Sanity-check the server using whatever MCP client/inspector/runtime you are targeting (stdio or streamable HTTP).
- Prefer small, repeatable smoke checks over a complex “environment validation” checklist.
Reference Files
📚 Documentation Library
Load these resources as needed during development:
Core MCP Documentation (Load First)
- MCP Protocol: Start with sitemap at
https://modelcontextprotocol.io/sitemap.xml, then fetch specific pages with.mdsuffix - 📋 MCP Best Practices - Universal MCP guidelines including:
- Server and tool naming conventions
- Response format guidelines (JSON vs Markdown)
- Pagination best practices
- Transport selection (streamable HTTP vs stdio)
- Security and error handling standards
SDK Documentation (Load During Phase 1/2)
- Python SDK: Fetch from
https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md - TypeScript SDK: Fetch from
https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md
Language-Specific Implementation Guides (Load During Phase 2)
🐍 Python Implementation Guide - Complete Python/FastMCP guide with:
- Server initialization patterns
- Pydantic model examples
- Tool registration with
@mcp.tool - Complete working examples
- Quality checklist
⚡ TypeScript Implementation Guide - Complete TypeScript guide with:
- Project structure
- Zod schema patterns
- Tool registration with
server.registerTool - Complete working examples
- Quality checklist
© shareAI-lab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files in packages/builtin-skills/skills/mcp-builder of shareAI-lab/Kode-CLI.
- SKILL.md
- LICENSE.txt
- reference/mcp_best_practices.md
- reference/node_mcp_server.md
- reference/python_mcp_server.md
Open the folder on GitHubat commit c7f6fcc
Compare with similar skills
MCP Server Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| MCP Server Builder this skillshareAI-lab/Kode-CLI | 5.2k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Server Builderalirezarezvani/claude-skills | 28k | — | ~985 | Automated safety check: Pass | MIT | |
| Copilot SDKintellectronica/agent-skills | 295 | — | ~3.2k | Automated safety check: Pass | CC0-1.0 | |
| Copilot SDKmicrosoft/skills | 3.1k | — | ~7.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
MCP Server Builder
alirezarezvani/claude-skills
Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers.
Copilot SDK
intellectronica/agent-skills
This skill helps with GitHub Copilot SDK work across Node.js/TypeScript, Python, Go, .NET, and Java.
- Official
Copilot SDK
microsoft/skills
Build applications powered by GitHub Copilot using the Copilot SDK.
Create MCP Servers
glittercowboy/taches-cc-resources
Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude.
More from shareAI-lab/Kode-CLI
All 8 skills in this repoSkill Creator
shareAI-lab/Kode-CLI
Guides writing a new agent skill or improving an existing one, covering how to keep it concise, how much freedom to give the agent and how to lay out bundled resources.
Skill Judge
shareAI-lab/Kode-CLI
Evaluates the design quality of an agent skill against official specifications and patterns from existing examples, scoring it and suggesting improvements.
Vibe Coding Partner
shareAI-lab/Kode-CLI
Gives an agent a set of working rules for any development task: understand first, surface decisions, verify results, and load deeper reference files per scenario.
Doc Co-Authoring Workflow
shareAI-lab/Kode-CLI
Guides a three-stage workflow for turning partial context into a clear PRD, RFC or design doc: capture context, draft section by section, then test with a fresh reader.
Kode Capabilities Manager
shareAI-lab/Kode-CLI
Lets the Kode agent manage its own features, such as LSP, statusline, output styles and plugins, by running its slash commands for you instead of listing install steps.
Kode LSP Maintenance
shareAI-lab/Kode-CLI
Diagnoses why Kode's LSP tool returns nothing and fixes it through plugin .lsp.json files and slash commands, then verifies with a real LSP call.
Related
Works with
Categories
Questions about MCP Server Builder
What does MCP Server Builder do?
Guide to designing and building MCP servers: tool, resource and prompt design for agent usability, with TypeScript or Python implementation workflows. An MCP server is judged by how well it lets an LLM finish real tasks through well-designed tools. The agent first asks once for the target SDK, TypeScript, Python or another official one, and for the language of the walkthrough, English or Chinese.
When should I use MCP Server Builder?
MCP Server Builder fits situations like: designing the tools of a new MCP server for an external service; choosing between TypeScript and Python for an MCP server; reviewing tool names, error messages and pagination for agent usability.
How do I install MCP Server Builder in Claude Code?
Run `npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a claude-code`. Or copy the skill folder (packages/builtin-skills/skills/mcp-builder in shareAI-lab/Kode-CLI) into .claude/skills/mcp-builder in your project. Claude Code loads it when a task matches its description.
How do I install MCP Server Builder in Codex?
Run `npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a codex`. Or copy the skill folder (packages/builtin-skills/skills/mcp-builder in shareAI-lab/Kode-CLI) into .agents/skills/mcp-builder in your project. Codex loads it when a task matches its description.
Can I use MCP Server Builder in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shareAI-lab/Kode-CLI --skill mcp-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-builder, .gemini/skills/mcp-builder, .github/skills/mcp-builder and .opencode/skills/mcp-builder in your project.
What does MCP Server Builder need to run?
SKILL.md names no scripts, command-line tools or credentials: MCP Server Builder is instructions for the agent only. Our summary lists: A TypeScript or Python MCP SDK, chosen when the build starts.
Does MCP Server Builder access the network?
SKILL.md names 2 domains. In commands or code: raw.githubusercontent.com and modelcontextprotocol.io; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Is MCP Server Builder safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does MCP Server Builder use?
MCP Server Builder is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does MCP Server Builder use?
About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to MCP Server Builder?
Skills that share tags, products or a category with MCP Server Builder: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Server Builder (alirezarezvani/claude-skills, 28k stars) and Copilot SDK (intellectronica/agent-skills, 295 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains MCP Server Builder?
shareAI-lab (a GitHub organization) maintains it in shareAI-lab/Kode-CLI, which has 5,232 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 27, 2026.
Source: shareAI-lab/Kode-CLI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.