agentleFS
jmolzjmolz/m0lz.01/.agents/skills/smithery-ai-cli/SKILL.md

smithery-ai-cli

Skill0 starsChanged 6 months agoMITView on GitHub

Find, connect, and use MCP tools and skills via the Smithery CLI. Use when the user searches for new tools or skills, wants to discover integrations, connect to an MCP, install a skill, or wants to interact with an external service (email, Slack, Discord, GitHub, Jira, Notion, databases, cloud APIs, monitoring, etc.).

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use smithery --help and <command> --help for flags, arguments, and full examples.

    line 11
  2. Very specific:

    Use one namespace per app/environment (for example, my-app-dev, my-app-prod), then set it as your active context.

    line 45
  3. Very specific:

    If CLI shows auth_required, tell your human to open the URL and then retry.

    line 76
  4. Distinctive:

    Never pass a full API key to untrusted code.

    line 81
  5. Very specific:

    Use rpcReqMatch to restrict specific MCP JSON-RPC requests (regex by request path).

    line 102
  6. Distinctive:

    When output is piped, Smithery commands emit JSONL (one JSON object per line):

    line 124

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Smithery

The marketplace for AI agents. Connect to 100K+ tools and skills instantly.

Use smithery --help and <command> --help for flags, arguments, and full examples. This skill focuses on concepts and canonical workflows.

Quick Start

# 1. Install
npm install -g @smithery/cli

# 2. Authenticate (requires human to confirm in browser)
smithery auth login

# 3. Search for MCP servers
smithery mcp search "github"

# 4. Connect to a server (URL or qualified name both work)
smithery mcp add "https://github.run.tools" --id github

# 5. Browse tools (tree view — drill into groups by passing the prefix)
smithery tool list github
smithery tool list github issues.

# 6. Inspect tool input/output JSON schema
smithery tool get github issues.create

# 7. Call a tool
smithery tool call github issues.create '{"repo": "owner/repo", "title": "Bug"}'

Core Concepts

Namespaces

A namespace is the workspace boundary for Smithery resources. Servers, connections, and skills all live in a namespace. Use one namespace per app/environment (for example, my-app-dev, my-app-prod), then set it as your active context. Canonical flow:

smithery namespace list
smithery namespace create my-app-prod
smithery namespace use my-app-prod

For namespace-specific flags and overrides, run smithery namespace --help and smithery mcp --help.

Connect (MCP Connections)

A connection is a managed, long-lived MCP session. Smithery Connect handles OAuth flow, credential storage, token refresh, and session lifecycle. Connection status model:

  • connected: ready to list/call tools
  • auth_required: human must open authorization URL
  • error: inspect details and retry/fix config

Canonical flow (single user-scoped connection):

smithery mcp add https://github.run.tools \
  --id user-123-github \
  --metadata '{"userId":"user-123"}'

smithery mcp list --metadata '{"userId":"user-123"}'
smithery tool list user-123-github

If CLI shows auth_required, tell your human to open the URL and then retry.

Token Scoping

Service tokens are restricted credentials for browser/mobile/agent usage. Never pass a full API key to untrusted code. Policy mental model:

  • A token policy is one or more constraints
  • In the CLI, pass one JSON object per --policy flag
  • Fields inside one constraint are AND-ed (more fields = narrower)
  • Lists and multiple constraints are OR-ed (more entries = wider)

Canonical user-scoped token:

smithery auth token --policy '{
  "namespaces": "my-app",
  "resources": "connections",
  "operations": ["read", "execute"],
  "metadata": { "userId": "user-123" },
  "ttl": "1h"
}'

Request-level Tool Restrictions (rpcReqMatch, experimental)

Use rpcReqMatch to restrict specific MCP JSON-RPC requests (regex by request path). Important: connection IDs are not in the JSON-RPC body, so combine:

  • metadata for connection-level restriction
  • rpcReqMatch for method/tool restriction

Canonical combined restriction:

smithery auth token --policy '{
  "resources": "connections",
  "operations": "execute",
  "metadata": { "connectionId": "my-github" },
  "rpcReqMatch": {
    "method": "tools/call",
    "params.name": "^issues\\."
  },
  "ttl": "30m"
}'

Piped Output

When output is piped, Smithery commands emit JSONL (one JSON object per line):

smithery tool list github --flat --limit 1000 | grep label

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.