anthropic-api-tools-mcp — Claude Code skill for tool use and MCP
anthropic-api-tools-mcp — a reference skill for Claude API work: tool definitions, Agent Skills packages and MCP connections, with endpoint specs and sample code.
no license 200 installs ★ 5 updated 2026-10-25
npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a claude-codeWhat anthropic-api-tools-mcp does
The skill ships as SKILL.md plus reference folders split by topic. Tool use material sits in references/tool-use/, Agent Skills in references/agent-skills/, MCP work in references/mcp-connector/ and references/mcp-tunnels/, and per-endpoint request and response specs in references/endpoints/. A samples/ folder holds worked examples, among them a custom tool definition, a tool runner and a skill package.
Finding a page takes three steps: match the task against a mapping table, open the README for that category, then read the page it points to. The table covers tool definitions, call and result handling, the split between client and server tools, the computer and browser toolsets, strict and parallel use, streaming, caching, and error troubleshooting.
Scope stops at the Claude API side. Streaming, caching and thinking belong to anthropic-api-core; CLI-level skill and MCP setup to anthropic-claude-code-extend; Agent SDK integration to anthropic-agent-sdk; usage analytics to anthropic-admin-platform. The file header sets user-invocable: false, so there is no slash command to type. The agent picks the skill up from its description.
What it helps with
- declare a tool with a JSON Schema definition
- read a tool call and its result out of a model response
- attach a remote MCP server through
mcp_servers - package an Agent Skill around
SKILL.md - look up a Tunnels API endpoint spec
Example prompts for the agent
- Show me how to declare a tool with JSON Schema and read the
tool_useblock from the response. - Which
mcp_serversfields do I need to reach a remote MCP server from Messages API? - Walk me through packaging an Agent Skill and uploading it with the Skills API.
How to install anthropic-api-tools-mcp
1Skills CLI (Vercel)
npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a claude-code2Manually: put the files in place
~/.claude/skills/anthropic-api-tools-mcp/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/anthropic-api-tools-mcp/
1Skills CLI (Vercel)
npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a codex2Manually: put the files in place
.agents/skills/anthropic-api-tools-mcp/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a cursor2Manually: put the files in place
.cursor/skills/anthropic-api-tools-mcp/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Fandhe-AI/agent-reference-skills skills/anthropic-api-tools-mcp2Manually: put the files in place
.github/skills/anthropic-api-tools-mcp/SKILL.md1Skills CLI (Vercel)
npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a gemini-cli2Platform CLI
gemini skills install https://github.com/Fandhe-AI/agent-reference-skills --path skills/anthropic-api-tools-mcpManually: put the files in place
.devin/skills/anthropic-api-tools-mcp/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about anthropic-api-tools-mcp
How do I install anthropic-api-tools-mcp in Claude Code?
Run npx skills add Fandhe-AI/agent-reference-skills --skill anthropic-api-tools-mcp -a claude-code. The skill file then lives at ~/.claude/skills/anthropic-api-tools-mcp/SKILL.md.
What does anthropic-api-tools-mcp do?
It acts as a lookup for Claude API tool use, Agent Skills and MCP: tool definitions, server and client tool sets, endpoint specs, sample code.
Does it cover streaming and prompt caching?
No. Those belong to anthropic-api-core, along with the workflow that pairs thinking with tools. This skill stays on tools, skills and MCP.