Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →List, auth, and call MCP servers/tools from the terminal.
.claude/skills/nousresearch-mcporter/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 9% | 0% |
Use mcporter to discover, call, and manage MCP (Model Context Protocol) servers and tools directly from the terminal.
Requires Node.js:
bash# No install needed (runs via npx) npx mcporter list # Or install globally npm install -g mcporter
bash# List MCP servers already configured on this machine mcporter list # List tools for a specific server with schema details mcporter list <server> --schema # Call a tool mcporter call <server.tool> key=value
mcporter auto-discovers servers configured by other MCP clients (Claude Desktop, Cursor, etc.) on the machine. To find new servers to use, browse registries like mcpfinder.dev or mcp.so, then connect ad-hoc:
bash# Connect to any MCP server by URL (no config needed) mcporter list --http-url https://some-mcp-server.com --name my_server # Or run a stdio server on the fly mcporter list --stdio "npx -y @modelcontextprotocol/server-filesystem" --name fs
bash# Key=value syntax mcporter call linear.list_issues team=ENG limit:5 # Function syntax mcporter call "linear.create_issue(title: \"Bug fix needed\")" # Ad-hoc HTTP server (no config needed) mcporter call https://api.example.com/mcp.fetch url=https://example.com # Ad-hoc stdio server mcporter call --stdio "bun run ./server.ts" scrape url=https://example.com # JSON payload mcporter call <server.tool> --args '{"limit": 5}' # Machine-readable output (recommended for Hermes) mcporter call <server.tool> key=value --output json
bash# OAuth login for a server mcporter auth <server | url> [--reset] # Manage config mcporter config list mcporter config get <key> mcporter config add <server> mcporter config remove <server> mcporter config import <path>
Config file location: ./config/mcporter.json (override with --config).
For persistent server connections:
bashmcporter daemon start mcporter daemon status mcporter daemon stop mcporter daemon restart
bash# Generate a CLI wrapper for an MCP server mcporter generate-cli --server <name> mcporter generate-cli --command <url> # Inspect a generated CLI mcporter inspect-cli <path> [--json] # Generate TypeScript types/client mcporter emit-ts <server> --mode client mcporter emit-ts <server> --mode types
--output json for structured output that's easier to parse--stdio command) work without any config — useful for one-off callsterminal(command="mcporter auth <server>", pty=true) if needed| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,059 | 3,122 | -56% | 1 | 1 | 0% | 1,289 | 1,315 | +2% | 0 | 0 | — |
case-02 | pass→pass | 6,067 | 1,534 | -75% | 1 | 1 | 0% | 1,141 | 989 | -13% | 0 | 0 | — |
case-03 | fail→pass | 6,534 | 2,679 | -59% | 1 | 1 | 0% | 1,179 | 1,110 | -6% | 0 | 0 | — |
case-04 | pass→pass | 5,929 | 2,252 | -62% | 1 | 1 | 0% | 1,070 | 1,177 | +10% | 0 | 0 | — |
case-05 | pass→pass | 6,085 | 1,504 | -75% | 1 | 1 | 0% | 1,026 | 972 | -5% | 0 | 0 | — |
case-06 | fail→pass | 11,716 | 2,829 | -76% | 1 | 1 | 0% | 2,134 | 1,213 | -43% | 0 | 0 | — |
case-07 | fail→pass | 7,753 | 2,092 | -73% | 1 | 1 | 0% | 1,396 | 1,085 | -22% | 0 | 0 | — |
case-08 | fail→pass | 5,496 | 2,008 | -63% | 1 | 1 | 0% | 944 | 1,026 | +9% | 0 | 0 | — |
case-09 | fail→pass | 8,032 | 2,037 | -75% | 1 | 1 | 0% | 1,541 | 1,129 | -27% | 0 | 0 | — |
case-10 | fail→pass | 8,526 | 2,531 | -70% | 1 | 1 | 0% | 1,469 | 1,102 | -25% | 0 | 0 | — |
case-11 | pass→pass | 3,681 | 1,165 | -68% | 1 | 1 | 0% | 629 | 910 | +45% | 0 | 0 | — |
case-12 | fail→pass | 15,953 | 3,250 | -80% | 1 | 1 | 0% | 2,522 | 1,353 | -46% | 0 | 0 | — |
case-13 | pass→pass | 2,754 | 1,596 | -42% | 1 | 1 | 0% | 419 | 945 | +126% | 0 | 0 | — |
case-14 | fail→pass | 10,245 | 2,116 | -79% | 1 | 1 | 0% | 1,677 | 1,060 | -37% | 0 | 0 | — |
case-15 | pass→pass | 3,513 | 1,435 | -59% | 1 | 1 | 0% | 621 | 957 | +54% | 0 | 0 | — |
case-16 | pass→pass | 6,625 | 3,002 | -55% | 1 | 1 | 0% | 1,123 | 1,274 | +13% | 0 | 0 | — |
case-17 | pass→pass | 4,661 | 1,429 | -69% | 1 | 1 | 0% | 839 | 948 | +13% | 0 | 0 | — |
case-18 | pass→pass | 2,768 | 1,386 | -50% | 1 | 1 | 0% | 398 | 934 | +135% | 0 | 0 | — |
case-19 | fail→pass | 8,212 | 1,931 | -76% | 1 | 1 | 0% | 1,452 | 1,001 | -31% | 0 | 0 | — |
case-20 | pass→pass | 10,179 | 7,735 | -24% | 1 | 1 | 0% | 1,993 | 2,265 | +14% | 0 | 0 | — |
case-21 | pass→pass | 8,215 | 5,183 | -37% | 1 | 1 | 0% | 1,663 | 1,736 | +4% | 0 | 0 | — |
case-22 | pass→pass | 11,739 | 8,307 | -29% | 1 | 1 | 0% | 2,353 | 2,527 | +7% | 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. 22 cases were attempted. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 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.