Agent skill

MCP-CLI

Interacts with MCP servers from the command line: lists servers and tools, inspects a tool's JSON schema, and calls a tool with JSON arguments from stdin or an argument.

MITAuto-check passedAgent Workflows

Install MCP-CLI

skills CLI

$ npx skills add philschmid/mcp-cli --skill mcp-cli -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install philschmid/mcp-cli mcp-cli --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "mcp-cli" agent skill from https://github.com/philschmid/mcp-cli/tree/main into .claude/skills/mcp-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-cli", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add philschmid/mcp-cli --skill mcp-cli -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install philschmid/mcp-cli mcp-cli --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mcp-cli" agent skill from https://github.com/philschmid/mcp-cli/tree/main into .agents/skills/mcp-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-cli", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add philschmid/mcp-cli --skill mcp-cli -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install philschmid/mcp-cli mcp-cli --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mcp-cli" agent skill from https://github.com/philschmid/mcp-cli/tree/main into .cursor/skills/mcp-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-cli", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add philschmid/mcp-cli --skill mcp-cli -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install philschmid/mcp-cli mcp-cli --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "mcp-cli" agent skill from https://github.com/philschmid/mcp-cli/tree/main into .gemini/skills/mcp-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-cli", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install philschmid/mcp-cli mcp-cli

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add philschmid/mcp-cli --skill mcp-cli -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "mcp-cli" agent skill from https://github.com/philschmid/mcp-cli/tree/main into .github/skills/mcp-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-cli", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add philschmid/mcp-cli --skill mcp-cli -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install philschmid/mcp-cli mcp-cli --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mcp-cli" agent skill from https://github.com/philschmid/mcp-cli/tree/main into .opencode/skills/mcp-cli/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-cli", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: mcp-cli
GitHub stars: 1.3k
Token cost: ~832 tokens
SKILL.md length: 217 words
Files: 39 (incl. scripts)
Skills in repo: 1
Repo updated: Feb 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Interacts with MCP servers from the command line: lists servers and tools, inspects a tool's JSON schema, and calls a tool with JSON arguments from stdin or an argument.

Works in 4 steps: Discover: mcp-cli → see available servers → Explore: mcp-cli info → see tools with… → Inspect: mcp-cli info → get full JSON… → …
Listing the MCP servers and tools available in the current environment
SKILL.md covers Commands, Workflow, Examples and Advanced Chaining, plus 3 more sections
Runs Shell and TypeScript scripts from its folder

What it does

The CLI exposes five core commands: running mcp-cli alone lists every configured server and its tools, info <server> shows a server's tools with parameters, info <server> <tool> returns the full JSON schema for one tool, grep searches tool names by pattern, and call <server> <tool> runs a tool, reading JSON arguments from stdin when none are given inline. Both a server/tool and a server tool argument order work, and call prints raw text content directly rather than JSON, so no separate parsing step is needed for plain text results.

A short workflow moves from discovering servers, to exploring a server's tools with parameters, to inspecting one tool's full schema, to executing it with arguments, and results can be chained into further shell commands, such as piping a filesystem search result into a read call. Two flags are listed, -d to include descriptions and -c to point at a specific config file, and a table of common mistakes maps wrong subcommands like run or list to their correct equivalents, call and info, along with the exit codes for client, server and network errors.

When your agent uses it

Listing the MCP servers and tools available in the current environment
Inspecting a specific MCP tool's input schema before calling it
Calling an MCP tool with JSON arguments from the command line
Chaining one MCP tool's output into another command

Example prompts

“List all available MCP servers and their tools.”
“Show me the JSON schema for the filesystem server's search_files tool.”
“Call the github server's create_issue tool with this JSON payload.”

Requirements

The mcp-cli binary
A configured MCP servers file

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Discover: mcp-cli → see available servers
Explore: mcp-cli info → see tools with parameters
Inspect: mcp-cli info → get full JSON schema
Execute: mcp-cli call '' → run with arguments

What it can do on your machine

Read from SKILL.md and the folder at commit d77672a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Shell and TypeScript, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP-CLI loads about 832 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 217 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~40
When it runs · the whole SKILL.md, loaded when a task matches: ~832

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from philschmid/mcp-cli at commit d77672a, republished under its MIT licence (© philschmid). 217 words, ~832 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-cli/SKILL.md (or your agent's skills folder). This skill also uses 38 other files; get the full folder from GitHub.

name: mcp-cli
description: Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers.

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 tools
`mcp-cli info <server>`	Show server tools and parameters
`mcp-cli info <server> <tool>`	Get tool JSON schema
`mcp-cli grep "<pattern>"`	Search tools by name
`mcp-cli call <server> <tool>`	Call tool (reads JSON from stdin if no args)
`mcp-cli call <server> <tool> '<json>'`	Call tool with arguments

Both formats work: <server> <tool> or <server>/<tool>

Workflow

Discover: mcp-cli → see available servers
Explore: mcp-cli info <server> → see tools with parameters
Inspect: mcp-cli info <server> <tool> → get full JSON schema
Execute: mcp-cli call <server> <tool> '<json>' → run with arguments

Examples

bash

# List all servers
mcp-cli

# With descriptions  
mcp-cli -d

# See server tools
mcp-cli info filesystem

# Get tool schema (both formats work)
mcp-cli info filesystem read_file
mcp-cli info filesystem/read_file

# Call tool
mcp-cli call filesystem read_file '{"path": "./README.md"}'

# Pipe from stdin (no '-' needed!)
cat args.json | mcp-cli call filesystem read_file

# Search for tools
mcp-cli grep "*file*"

# Output is raw text (pipe-friendly)
mcp-cli call filesystem read_file '{"path": "./file"}' | head -10

Advanced Chaining

bash

# Chain: search files → read first match
mcp-cli call filesystem search_files '{"path": ".", "pattern": "*.md"}' \
  | head -1 \
  | xargs -I {} mcp-cli call filesystem read_file '{"path": "{}"}'

# Loop: process multiple files
mcp-cli call filesystem list_directory '{"path": "./src"}' \
  | while read f; do mcp-cli call filesystem read_file "{\"path\": \"$f\"}"; done

# Conditional: check before reading
mcp-cli call filesystem list_directory '{"path": "."}' \
  | grep -q "README" \
  && mcp-cli call filesystem read_file '{"path": "./README.md"}'

# Multi-server aggregation
{
  mcp-cli call github search_repositories '{"query": "mcp", "per_page": 3}'
  mcp-cli call filesystem list_directory '{"path": "."}'
}

# Save to file
mcp-cli call github get_file_contents '{"owner": "x", "repo": "y", "path": "z"}' > output.txt

Note: call outputs raw text content directly (no jq needed for text extraction)

Options

Flag	Purpose
`-d`	Include descriptions
`-c <path>`	Specify config file

Common Errors

Wrong Command	Error	Fix
`mcp-cli server tool`	AMBIGUOUS_COMMAND	Use `call server tool` or `info server tool`
`mcp-cli run server tool`	UNKNOWN_SUBCOMMAND	Use `call` instead of `run`
`mcp-cli list`	UNKNOWN_SUBCOMMAND	Use `info` instead of `list`
`mcp-cli call server`	MISSING_ARGUMENT	Add tool name
`mcp-cli call server tool {bad}`	INVALID_JSON	Use valid JSON with quotes

Exit Codes

0: Success
1: Client error (bad args, missing config)
2: Server error (tool failed)
3: Network error

Files

SKILL.md and 38 other files (scripts) in the repository root of philschmid/mcp-cli.

SKILL.md
.github/workflows/ci.yml
.github/workflows/release.yml
.gitignore
CHANGELOG.md
LICENSE
README.md
biome.json
bun.lock
comparison.jpeg
install.sh
mcp_servers.json
package.json
scripts/generate-system-instructions.ts
scripts/release.sh
src/client.ts
src/commands
… and 22 more

Open the folder on GitHubat commit d77672a

Compare with similar skills

MCP-CLI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP-CLI compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
MCP-CLI this skillphilschmid/mcp-cli	1.3k	—	~832	Automated safety check: Pass	MIT	8 mo ago
MCP Server Builderanthropics/skills	180k	62 repos	~2.3k	Automated safety check: Pass	Apache-2.0	2 days ago
MCP Server BuildershareAI-lab/learn-claude-code	78k	5 repos	~1.2k	Automated safety check: Pass	MIT	9 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	37k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	today
Fastmcp Client CLIPrefectHQ/fastmcp	28k	1 repos	~823	Automated safety check: Pass	Apache-2.0	yesterday
Crush Configurationcharmbracelet/crush	29k	—	~3.7k	Automated safety check: Pass	Custom licence	today

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 62 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 5 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
37k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
28k GitHub starsUsed in 1 repo~823 tokens
Agent WorkflowsAuto-check passed
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
26k GitHub stars~4.1k tokensUpdated yesterday
Agent WorkflowsAuto-check passed

Works with

Model Context Protocol

Questions about MCP-CLI

What does MCP-CLI do?

Interacts with MCP servers from the command line: lists servers and tools, inspects a tool's JSON schema, and calls a tool with JSON arguments from stdin or an argument. The CLI exposes five core commands: running mcp-cli alone lists every configured server and its tools, info <server> shows a server's tools with parameters, info <server> <tool> returns the full JSON schema for one tool, grep searches tool names by pattern, and call <server> <tool> runs a tool, reading JSON arguments from stdin when none are given inline. Both a server/tool and a server tool argument order work, and call prints raw text content directly rather than JSON, so no separate parsing step is needed for plain text results.

When should I use MCP-CLI?

MCP-CLI fits situations like: listing the MCP servers and tools available in the current environment; inspecting a specific MCP tool's input schema before calling it; calling an MCP tool with JSON arguments from the command line; chaining one MCP tool's output into another command.

How do I install MCP-CLI in Claude Code?

Run `npx skills add philschmid/mcp-cli --skill mcp-cli -a claude-code`. Or copy the skill folder (the philschmid/mcp-cli repository) into .claude/skills/mcp-cli in your project. Claude Code loads it when a task matches its description.

How do I install MCP-CLI in Codex?

Run `npx skills add philschmid/mcp-cli --skill mcp-cli -a codex`. Or copy the skill folder (the philschmid/mcp-cli repository) into .agents/skills/mcp-cli in your project. Codex loads it when a task matches its description.

Can I use MCP-CLI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add philschmid/mcp-cli --skill mcp-cli -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-cli, .gemini/skills/mcp-cli, .github/skills/mcp-cli and .opencode/skills/mcp-cli in your project.

What does MCP-CLI need to run?

Going by SKILL.md and its folder, MCP-CLI needs a shell and TypeScript for the scripts in its folder. Our summary lists: The mcp-cli binary; A configured MCP servers file.

Does MCP-CLI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP-CLI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does MCP-CLI use?

MCP-CLI is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP-CLI use?

About 832 tokens (SKILL.md is roughly 3.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP-CLI?

Skills that share tags, products or a category with MCP-CLI: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP-CLI?

philschmid (a GitHub user) maintains it in philschmid/mcp-cli, which has 1,278 GitHub stars. The repository was last updated on February 5, 2026.

Source: philschmid/mcp-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install MCP-CLI

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

MCP-CLI

Commands

Workflow

Examples

Advanced Chaining

Options

Common Errors

Exit Codes

Files

Compare with similar skills

Similar skills

MCP Server Builder

MCP Server Builder

MCP Integration for Plugins

Fastmcp Client CLI

Crush Configuration

Context Mode Output Sandbox

Related

Questions about MCP-CLI