mcp-clientlisted
Install: claude install-skill walidboulanouar/Ay-Skills
# Universal MCP Client
Connect to any MCP server with progressive disclosure - load tool schemas on-demand instead of dumping thousands of tokens into context upfront.
## Skill Location
This skill is located at: `.claude/skills/mcp-client/`
**Script path:** `.claude/skills/mcp-client/scripts/mcp_client.py`
## Configuration
The script looks for config in this order:
1. `MCP_CONFIG_PATH` env var (custom path)
2. **`references/mcp-config.json`** (this skill's config - recommended)
3. `.mcp.json` in project root
4. `~/.claude.json`
**Your config file:** `.claude/skills/mcp-client/references/mcp-config.json`
Edit this file to add your API keys. The example file (`example-mcp-config.json`) is kept as a reference template.
Security note:
- Never commit real API keys. This repo uses a placeholder `${AY_PROPOSALS_API_KEY}` for the AY Proposals server.
- Option 1 (recommended): Create a private config and point the script to it: `export MCP_CONFIG_PATH=~/.claude/skills/mcp-client/references/mcp-config.local.json` (same structure, with your real token). Keep that file out of git.
- Option 2: Export your key in the shell: `export AY_PROPOSALS_API_KEY=...` and ensure your runtime interpolates env vars. If not, use Option 1.
**If the user hasn't provided their Zapier API key yet, ask them for it.**
## Running Commands
All commands use the script at `.claude/skills/mcp-client/scripts/mcp_client.py`:
```bash
# List configured servers
python .claude/skills/mcp-client/scripts/mcp_