mcp-builder is a skill in ThinkInAIXYZ/deepchat, last changed 13 Jan 2026. It can touch credentials, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing.

From the author
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

At a glance

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 145e517 · 3 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit 145e517, the one we checked, or the latest version.

Read SKILL.md first
Apache 2.0
Licence
6.4k
Repo stars
Publisher

What it can touch

From the files and frontmatter at commit 145e517. This is how much a skill can do, not whether it is risky.

  • Touches credentials

    It reads, asks for or contains keys, tokens, passwords or similar secrets.

    reference/python_mcp_server.md:512 (opens in a new tab)

  • Runs shell commands

    Its instructions or files give the agent commands to run on your computer.

  • Reaches the network

    It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

  • Names web addresses

    It mentions outside web addresses the agent may visit. We list them but don't follow them.

    Outside links we did not follow
  • Bundles scripts

    The folder holds code files the agent may run.

Pattern check

Pattern check: nothing flagged · commit 145e517 · 3 Nov 2026

We checked every text file in this skill, at commit 145e517 on 3 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

  • https://modelcontextprotocol.io/sitemap.xml
  • https://modelcontextprotocol.io/specification/draft.md
  • https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md
  • https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md
  • http://www.apache.org/licenses/
  • http://www.apache.org/licenses/LICENSE-2.0

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specPasses

    The open format from agentskills.io, held to the strictest version of each rule among the agents we check.

    • Note

      Reference files over 100 lines with no table of contents at the top: reference/evaluation.md (602 lines), reference/mcp_best_practices.md (250 lines), reference/node_mcp_server.md (970 lines) and reference/python_mcp_server.md (719 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      Reference files over 100 lines with no table of contents at the top: reference/evaluation.md (602 lines), reference/mcp_best_practices.md (250 lines), reference/node_mcp_server.md (970 lines) and reference/python_mcp_server.md (719 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadPasses

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Note

      The description is 277 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      Reference files over 100 lines with no table of contents at the top: reference/evaluation.md (602 lines), reference/mcp_best_practices.md (250 lines), reference/node_mcp_server.md (970 lines) and reference/python_mcp_server.md (719 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes
  • VS Code & CopilotPasses

SKILL.md

Files

Copies

More from ThinkInAIXYZ/deepchat

SkillWhat it can touchPattern checkLicenceUpdated
  • Names web addresses
  • Bundles scripts
Pattern check: Nothing flaggedApache 2.013 Jan 2026
code-reviewComprehensive code review assistant that analyzes code quality, security, and best practices
  • Instructions only

Pattern check: Nothing flaggedApache 2.0Updated 13 Jan 2026

  • Instructions only
Pattern check: Nothing flaggedApache 2.013 Jan 2026
  • Instructions only
Pattern check: Nothing flaggedApache 2.03 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedApache 2.05 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedApache 2.011 Apr 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedSource-available11 Aug 2026
All skills in ThinkInAIXYZ/deepchat

Other Agent tooling skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedMIT21 Oct 2026
  • Runs shell commands
  • Bundles scripts
Pattern check: Nothing flaggedMIT21 Oct 2026
  • Runs shell commands
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Runs shell commands
Pattern check: Nothing flaggedMIT11 Jun 2026
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

anthropics/skills

  • Touches credentials
  • +6 more

Pattern check: 1 item to reviewApache 2.0Updated 9 Oct 2026

  • Touches credentials
  • Downloads software
  • +5 more
Pattern check: 1 item to reviewApache 2.09 Oct 2026
  • Touches credentials
  • Runs shell commands
  • +3 more
Pattern check: Nothing flaggedApache 2.028 Oct 2026

Repo facts from GitHub on 3 Nov 2026. Files read at commit 145e517.

QAI did not write these skills and is not affiliated with their authors unless a page says so. Logos and icons belong to their owners and are not a mark of approval. How we check