Mcp Cli
Discover, inspect, and execute MCP server tools from the terminal while wiring agents to GitHub, filesystems, databases, and APIs.
Overview
MCP-cli is an agent skill most often used in Build (also Ship testing, Operate debugging) that documents how to list, inspect, and call MCP server tools from the command line.
Install
npx skills add https://github.com/github/awesome-copilot --skill mcp-cliWhat is this skill?
- Five command shapes: list servers, list tools per server, fetch JSON schema, call tool with JSON args, and grep search a
- Optional `-d` flag adds descriptions when exploring crowded servers like filesystem or GitHub MCP.
- Documented 4-step workflow: discover, explore, inspect schema, execute with arguments.
- Positions MCP as the bridge to external systems—GitHub, filesystems, databases, and HTTP APIs.
- 5 documented MCP-CLI command patterns in the skills table
- 4-step discover-explore-inspect-execute workflow
Adoption & trust: 9.2k installs on skills.sh; 34.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have MCP servers configured but waste time guessing tool names, schemas, and JSON argument shapes before your agent can use them reliably.
Who is it for?
Builders and agent users who live in the terminal and need to probe GitHub, filesystem, or custom MCP tools before baking calls into skills or scripts.
Skip if: Greenfield MCP server implementation—use an MCP builder or framework docs when you need to author tools, not only invoke them.
When should I use this skill?
Use when you need to interact with external tools, APIs, or data sources through MCP servers, list available MCP servers/tools, or call MCP tools from command line.
What do I get? / Deliverables
You can run a repeatable CLI workflow from listing servers through schema inspection to successful tool execution with validated JSON arguments.
- Successful MCP tool invocations from the terminal
- Documented tool schemas and parameter maps for agent prompts
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
MCP-CLI is shelved under Build integrations because most installs happen while connecting agents to external systems during implementation. Integrations fits the discover → schema → execute workflow for third-party MCP servers rather than pure infra monitoring.
Where it fits
Inspect filesystem MCP tool schemas before embedding paths in an agent skill.
Execute GitHub MCP tools with sample JSON to verify CI-related automations pre-release.
Re-run a failing MCP tool call from the shell to compare agent-reported errors with raw CLI output.
How it compares
Terminal driver for existing MCP servers—not an MCP SDK tutorial or hosted MCP marketplace UI.
Common Questions / FAQ
Who is mcp-cli for?
Solo developers and agent operators who already use MCP and want a concise CLI reference for discovery, schema inspection, and tool execution.
When should I use mcp-cli?
Use it in Build when wiring integrations, in Ship during testing to verify MCP tool behavior, and in Operate when debugging failed agent tool calls—whenever you need MCP from the command line.
Is mcp-cli safe to install?
Calling MCP tools can access repos, secrets, or production APIs depending on server config; review the Security Audits panel on this page and run inspect-only commands before destructive executes.
SKILL.md
READMESKILL.md - Mcp Cli
# MCP-CLI Access MCP servers through the command line. MCP enables interaction with external systems like GitHub, filesystems, databases, and APIs. ## Commands | Command | Output | | ---------------------------------- | ------------------------------- | | `mcp-cli` | List all servers and tool names | | `mcp-cli <server>` | Show tools with parameters | | `mcp-cli <server>/<tool>` | Get tool JSON schema | | `mcp-cli <server>/<tool> '<json>'` | Call tool with arguments | | `mcp-cli grep "<glob>"` | Search tools by name | **Add `-d` to include descriptions** (e.g., `mcp-cli filesystem -d`) ## Workflow 1. **Discover**: `mcp-cli` → see available servers and tools 2. **Explore**: `mcp-cli <server>` → see tools with parameters 3. **Inspect**: `mcp-cli <server>/<tool>` → get full JSON input schema 4. **Execute**: `mcp-cli <server>/<tool> '<json>'` → run with arguments ## Examples ```bash # List all servers and tool names mcp-cli # See all tools with parameters mcp-cli filesystem # With descriptions (more verbose) mcp-cli filesystem -d # Get JSON schema for specific tool mcp-cli filesystem/read_file # Call the tool mcp-cli filesystem/read_file '{"path": "./README.md"}' # Search for tools mcp-cli grep "*file*" # JSON output for parsing mcp-cli filesystem/read_file '{"path": "./README.md"}' --json # Complex JSON with quotes (use heredoc or stdin) mcp-cli server/tool <<EOF {"content": "Text with 'quotes' inside"} EOF # Or pipe from a file/command cat args.json | mcp-cli server/tool # Find all TypeScript files and read the first one mcp-cli filesystem/search_files '{"path": "src/", "pattern": "*.ts"}' --json | jq -r '.content[0].text' | head -1 | xargs -I {} sh -c 'mcp-cli filesystem/read_file "{\"path\": \"{}\"}"' ``` ## Options | Flag | Purpose | | ------------ | ------------------------- | | `-j, --json` | JSON output for scripting | | `-r, --raw` | Raw text content | | `-d` | Include descriptions | ## Exit Codes - `0`: Success - `1`: Client error (bad args, missing config) - `2`: Server error (tool failed) - `3`: Network error