LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
SkillRisingofficial publisher

mcp-builder (Anthropic)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires claude-code

Official skill that helps design and code a clean MCP server.

Useful as soon as you want to connect a custom service to an agent.

Official site GitHub · 183,548 ★
Overall score
8.7 /10
Security: nothing to flag
Utility
7.0
Reliability
10.0
Security
No caveat on record
Ease
1 click · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Building an MCP (Model Context Protocol) server from scratch requires knowing the protocol conventions, the expected file structure, and implementation best practices. Without guidance, developers waste time reading documentation and fixing structural errors.

mcp-builder is an official Anthropic skill that installs inside Claude Code. Once active, it loads a SKILL.md file containing precise instructions that Claude follows to design and generate the full code of an MCP server, respecting protocol conventions.

This skill is aimed at developers who want to connect a custom service or tool to a Claude agent, without having to memorize all MCP specifications. It suits those already working in Claude Code who want to automate this scaffolding step.

It is not suited for non-technical users looking for a graphical interface, nor for those without access to Claude Code, as the skill works exclusively in that environment.

What it offers

  • ·Dynamic loading of specialized instructions via a SKILL.md file to guide Claude in generating MCP servers.
  • ·Generation of the file structure and code of an MCP server following protocol conventions.
  • ·Direct installation from the Claude Code plugin marketplace with a single command.
  • ·Available as open source under the Apache 2.0 license, freely readable and modifiable.
  • ·Usable as a reference or starting point for creating custom skills.
  • ·Compatible with the Claude Code plugin system, allowing activation or deactivation depending on project needs.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude-code
Host
claude-code
Licence
Apache-2.0
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 October 2025

How to install mcp-builder (Anthropic)

1. Open Claude Code in your development environment. 2. Add the official marketplace with the command: /plugin marketplace add anthropics/skills 3. Select "Browse and install plugins", then "anthropic-agent-skills", then "example-skills". 4. Click "Install now" to install the skill group including mcp-builder. 5. Verify the skill is loaded by mentioning mcp-builder in a message to Claude Code. 6. Precaution: do not deploy the generated MCP server to production without first testing it in an isolated environment.
/plugin install example-skills@anthropic-agent-skills

In the same category

Whole category Frame (methods, guardrails) →