Docs / Strand / ai/claude-code
AI Skills
When you connect an AI assistant to the Strand MCP server, it automatically receives skills: guided instructions that teach the assistant how to use the tools effectively. No plugins or extra installation needed.
Setup#
Add the Strand MCP server to your Claude Code configuration (.mcp.json in your project root or ~/.claude.json globally):
{
"mcpServers": {
"strand": {
"type": "http",
"url": "https://app.tendrl.com/strand/mcp",
"headers": {
"Authorization": "Bearer <STRAND_API_KEY>"
}
}
}
}
Create API keys in the Strand dashboard under Access Control → API Keys.
Once connected, Claude automatically discovers the available skills.
How it works#
The Strand MCP server serves skills as MCP resources alongside its documentation. When any MCP client connects, it calls resources/list and sees the available skills. When you ask a question that matches a skill, the AI assistant reads the skill content via resources/read and uses it to guide which tools to call, what parameters to use, and how to interpret results.
This works with Claude Code, Cursor, Claude Desktop, and any MCP-compatible client. No plugins, no file downloads, no extra configuration: the skills ship with the server itself.
Skills#
You don't need to remember tool names or parameters; just describe what you want.
| Skill | What it does | Example triggers |
|---|---|---|
strand-workflows |
Create workflows, manage functions, check execution history | "create a workflow", "list my runs", "set up automation" |
strand-admin |
Manage vault secrets, roles, API keys, and usage | "what secrets do I have", "create an operator role", "check my usage" |
How skills work#
When you ask Claude something like "create a workflow that alerts when temp exceeds 80," it reads the strand-workflows skill from the server which provides context on:
- Which tool to call (
create_workflow) - How to structure the trigger, condition, and action
- How to verify execution via
list_runs - How to connect to Contact entities and connectors
Tendrl