Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interact with MCP (Model Context Protocol) servers using the mcporter CLI. Use this skill when you need to list available MCP servers, view tool schemas, call MCP tools, manage OAuth authentication, or generate CLI wrappers and TypeScript types for MCP servers.
.claude/skills/dicklesworthstone-mcporter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -58% | 0% |
Use the mcporter CLI to interact with MCP servers directly via HTTP or stdio.
mcporter listmcporter list <server> --schemamcporter call <server.tool> key=valueMultiple syntaxes are supported for calling MCP tools:
bashmcporter call linear.list_issues team=ENG limit:5
bashmcporter call "linear.create_issue(title: \"Bug\")"
bashmcporter call https://api.example.com/mcp.fetch url:https://example.com
bashmcporter call --stdio "bun run ./server.ts" scrape url=https://example.com
bashmcporter call <server.tool> --args '{"limit":5}'
bashmcporter auth <server | url> # Authenticate with a server mcporter auth <server> --reset # Reset authentication
bashmcporter config list # List all configured servers mcporter config get <key> # Get a config value mcporter config add <server> # Add a server mcporter config remove <server> # Remove a server mcporter config import <file> # Import configuration mcporter config login # Login to mcporter cloud mcporter config logout # Logout from mcporter cloud
bashmcporter daemon start # Start the daemon mcporter daemon status # Check daemon status mcporter daemon stop # Stop the daemon mcporter daemon restart # Restart the daemon
bashmcporter generate-cli --server <name> mcporter generate-cli --command <url>
bashmcporter inspect-cli <path> mcporter inspect-cli <path> --json # JSON output
bashmcporter emit-ts <server> --mode client # Generate client code mcporter emit-ts <server> --mode types # Generate type definitions
./config/mcporter.json. Override with --config <path>.--output json for machine-readable output when parsing results programmatically.key=value and key:value syntaxes work for arguments.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | pass→pass | 8,936 | 1,890 | -79% | 1 | 1 | 0% | 1,384 | 926 | -33% | 0 | 0 | — |
case-01 | fail→pass | 11,833 | 1,833 | -85% | 1 | 1 | 0% | 2,101 | 912 | -57% | 0 | 0 | — |
case-02 | fail→pass | 7,846 | 2,619 | -67% | 1 | 1 | 0% | 1,306 | 1,039 | -20% | 0 | 0 | — |
case-03 | pass→pass | 9,217 | 2,113 | -77% | 1 | 1 | 0% | 1,624 | 934 | -42% | 0 | 0 | — |
case-04 | fail→pass | 9,254 | 1,876 | -80% | 1 | 1 | 0% | 1,618 | 924 | -43% | 0 | 0 | — |
case-05 | fail→pass | 7,949 | 3,463 | -56% | 1 | 1 | 0% | 1,361 | 1,230 | -10% | 0 | 0 | — |
case-06 | fail→pass | 12,276 | 2,299 | -81% | 1 | 1 | 0% | 2,249 | 946 | -58% | 0 | 0 | — |
case-07 | pass→pass | 19,729 | 2,260 | -89% | 1 | 1 | 0% | 3,268 | 1,053 | -68% | 0 | 0 | — |
case-08 | fail→pass | 8,318 | 1,861 | -78% | 1 | 1 | 0% | 1,489 | 863 | -42% | 0 | 0 | — |
case-09 | pass→pass | 6,450 | 2,526 | -61% | 1 | 1 | 0% | 1,176 | 1,011 | -14% | 0 | 0 | — |
case-10 | pass→pass | 5,795 | 2,648 | -54% | 1 | 1 | 0% | 1,069 | 1,020 | -5% | 0 | 0 | — |
case-11 | fail→pass | 8,457 | 1,776 | -79% | 1 | 1 | 0% | 1,399 | 851 | -39% | 0 | 0 | — |
case-12 | pass→pass | 5,658 | 1,838 | -68% | 1 | 1 | 0% | 1,001 | 846 | -15% | 0 | 0 | — |
case-13 | fail→pass | 9,052 | 1,434 | -84% | 1 | 1 | 0% | 1,442 | 808 | -44% | 0 | 0 | — |
case-14 | pass→pass | 4,790 | 1,435 | -70% | 1 | 1 | 0% | 546 | 842 | +54% | 0 | 0 | — |
case-15 | fail→pass | 7,498 | 1,569 | -79% | 1 | 1 | 0% | 1,423 | 792 | -44% | 0 | 0 | — |
case-16 | fail→pass | 9,310 | 2,565 | -72% | 1 | 1 | 0% | 1,618 | 850 | -47% | 0 | 0 | — |
case-17 | fail→pass | 11,912 | 2,259 | -81% | 1 | 1 | 0% | 1,948 | 1,010 | -48% | 0 | 0 | — |
case-18 | fail→pass | 11,655 | 2,086 | -82% | 1 | 1 | 0% | 2,042 | 907 | -56% | 0 | 0 | — |
case-19 | pass→pass | 4,582 | 1,879 | -59% | 1 | 1 | 0% | 807 | 883 | +9% | 0 | 0 | — |
case-20 | pass→pass | 9,723 | 2,438 | -75% | 1 | 1 | 0% | 1,697 | 1,020 | -40% | 0 | 0 | — |
case-22 | pass→pass | 4,074 | 3,378 | -17% | 1 | 1 | 0% | 638 | 1,227 | +92% | 0 | 0 | — |
case-23 | pass→pass | 3,664 | 2,593 | -29% | 1 | 1 | 0% | 546 | 972 | +78% | 0 | 0 | — |
case-24 | pass→pass | 10,185 | 7,722 | -24% | 1 | 1 | 0% | 1,792 | 1,995 | +11% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +50 percentage points is the difference between those two pass rates over the 24 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.