Skip to content
cccskills
FreePublished on GitHub

fastmcp-client-cli

Discover MCP servers and inspect their available tools from the command line, then invoke operations with typed arguments or JSON. Use local files, remote endpoints, or configured server names, and return structured output for scripts.

OriginalShow the original description

Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.

See how to install

Good for

  • Finding MCP servers configured in editors or a project
  • Inspecting available tools and input definitions
  • Calling tools on local or remote MCP servers
  • Using JSON results in scripts and workflows

Files included (1)

  • SKILL.md3.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

FastMCP CLI: List and Call

Use fastmcp list and fastmcp call to interact with any MCP server from the command line.

Listing Tools

# Remote server
fastmcp list http://localhost:8000/mcp

# Local Python file (runs via fastmcp run automatically)
fastmcp list server.py

# MCPConfig with multiple servers
fastmcp list mcp.json

# Stdio command (npx, uvx, etc.)
fastmcp list --command 'npx -y @modelcontextprotocol/server-github'

# Include full input/output schemas
fastmcp list server.py --input-schema --output-schema

# Machine-readable JSON
fastmcp list server.py --json

# Include resources and prompts
fastmcp list server.py --resources --prompts

Default output shows tool signatures and descriptions. Use --input-schema or --output-schema to include full JSON schemas, --json for structured output.

Calling Tools

# Key=value arguments (auto-coerced to correct types)
fastmcp call server.py greet name=World
fastmcp call server.py add a=3 b=4

# Single JSON object for complex/nested args
fastmcp call server.py create_item '{"name": "Widget", "tags": ["a", "b"]}'

# --input-json with key=value overrides
fastmcp call server.py search --input-json '{"query": "hello", "limit": 5}' limit=10

# JSON output for scripting
fastmcp call server.py add a=3 b=4 --json

Type coercion is automatic: limit=5 becomes an integer, verbose=true becomes a boolean, based on the tool's input schema.

Server Targets

All commands accept the same server targets:

TargetExample
HTTP/HTTPS URLhttp://localhost:8000/mcp
Python fileserver.py
MCPConfig JSONmcp.json (must have mcpServers key)
Stdio command--command 'npx -y @mcp/server'
Discovered nameweather or source:name

Servers configured in editor configs (Claude Desktop, Claude Code, Cursor, Gemini CLI, Goose) or project-level mcp.json can be referenced by name. Use source:name (e.g. claude-code:my-server, cursor:weather) to target a specific source. Run fastmcp discover to see available names.

For SSE servers, pass --transport sse:

fastmcp list http://localhost:8000/mcp --transport sse

Auth

HTTP targets automatically use OAuth (no-ops if the server doesn't require auth). Disable with --auth none:

fastmcp call http://server/mcp tool --auth none

Discovering Configured Servers

# See all MCP servers in editor/project configs
fastmcp discover

# Filter by source
fastmcp discover --source claude-code

# JSON output
fastmcp discover --json

Scans Claude Desktop, Claude Code, Cursor, Gemini CLI, Goose, and ./mcp.json. Sources: claude-desktop, claude-code, cursor, gemini, goose, project.

Workflow Pattern

Discover tools first, then call them:

# 1. See what servers are configured
fastmcp discover

# 2. See what tools a server has
fastmcp list weather

# 3. Call a tool
fastmcp call weather get_forecast city=London

If you call a nonexistent tool, FastMCP suggests close matches.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

docs

FreeSummary

Write and revise FastMCP documentation pages with consistent structure, clear explanations, and runnable code examples. Covers accessibility, link and Python checks, and the publishing steps needed to confirm changes reach the live site.

  • Documenting a new FastMCP feature
  • Reworking an existing documentation page
  • Reviewing accessibility and page consistency
PrefectHQ/fastmcp28.2KUpdated Oct 21, 2026

fastmcp-server

FreeSummary

Build, extend, or review Python FastMCP servers using documentation for the installed version. Design operations that agents can discover and use, then check input definitions, results, error handling, and representative agent workflows.

  • Building an MCP server with Python FastMCP
  • Adding tools, resources, or reusable prompts
  • Reviewing input definitions and error handling
PrefectHQ/fastmcp28.2KUpdated Oct 21, 2026

fix-issue

FreeSummary

Take a selected FastMCP bug from a reproducible failure to a focused fix. Check compatibility, run required validation, prepare a pull request, and follow automated checks and review feedback after publication.

  • Fixing a reproducible FastMCP bug
  • Checking compatibility before publishing a fix
  • Following checks and feedback after opening a pull request
PrefectHQ/fastmcp28.2KUpdated Oct 21, 2026

python-tests

FreeSummary

Write regression tests that catch recurring bugs in FastMCP changes using pytest. Covers reproducing failures before a fix, testing requests without a network server, and checking outgoing requests while replacing external services with test substitutes.

  • Reproducing a bug before testing its fix
  • Testing MCP behavior without a network server
  • Checking requests sent to external services
PrefectHQ/fastmcp28.2KUpdated Oct 21, 2026

release

FreeSummary

Prepare and publish FastMCP releases, from reviewing changes and crediting contributors to updating changelogs, creating release tags, checking Python package publication on PyPI, and confirming that the documentation site reflects the release.

  • Previewing changes for the next FastMCP release
  • Preparing release notes and contributor credits
  • Publishing a patch or maintenance release
PrefectHQ/fastmcp28.2KUpdated Oct 21, 2026

review-issue

FreeSummary

Evaluate an incoming FastMCP issue and its linked pull requests. Check whether the reported behavior is a supported bug, assess the proposed contribution, and recommend assigning the contributor, declining, or seeking a specific maintainer decision.

  • Deciding whether to assign an external contributor
  • Assessing a pull request closed by contribution checks
  • Checking whether reported behavior is a supported bug
PrefectHQ/fastmcp28.2KUpdated Oct 21, 2026

See all skills by PrefectHQ

Report a problem with this skill