CtrlK
BlogDocsLog inGet started
Tessl Logo

mcporter

Call MCP Server tools directly via the mcporter CLI. Use when you need to interact with external APIs (GitHub, weather, etc.) without delegating to a Worker — useful for quick lookups or when you need a result to make a decision.

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

mcporter — MCP Tool CLI

You can call any configured MCP server's tools directly via mcporter. Your config is at ./config/mcporter.json (mcporter's default path — no --config flag needed, auto-generated by the setup-mcp-server.sh script).

Commands

# List all configured MCP servers and their tool counts
mcporter list

# View a specific server's tools with full parameter schemas
mcporter list <server-name> --schema

# Call a tool — key=value syntax for simple args
mcporter call <server-name>.<tool-name> key=value key2=value2

# Call a tool — JSON syntax for complex args (arrays, objects, numbers)
mcporter call <server-name>.<tool-name> --args '{"key":"value","count":5}'

Discovery Workflow

When you're unsure what tools are available or what parameters a tool expects:

  1. Run mcporter list to see all servers and tool counts
  2. Run mcporter list <server-name> --schema to see each tool's description, argument types, and which are required vs optional
  3. Call the tool with the appropriate arguments

When to Use

  • You need a quick lookup from an external API (e.g., search a GitHub repo, check an issue status)
  • You need a result to make a decision before delegating work to a Worker
  • You want to verify an API is working after running setup-mcp-server.sh

For sustained or complex API interactions, delegate to a Worker instead — they have their own mcporter skill and can work autonomously.

Repository
agentscope-ai/AgentTeams
Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.