Skip to main content
hc
Submit
toolsSource-backedReview first Safety · Privacy ·
Smithery logo

Smithery

MCP server discovery and deployment platform for finding, installing, and running model context protocol tools.

by Smithery·added 2026-04-27·
CLI
HarnessCLI
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/tools/smithery
Source URLs
https://smithery.ai/docs, https://github.com/JSONbored/awesome-claude/blob/main/content/tools/smithery.mdx, https://smithery.ai
Brand
Smithery
Brand domain
smithery.ai
Brand asset source
brandfetch
Author
Smithery
Claim status
unclaimed
Last verified
2026-04-27

Schema details

Install type
copy
Troubleshooting
No
Tool listing metadata
Pricing
freemium
Disclosure
editorial
Application category
DeveloperApplication
Operating system
Web
Full copyable content
## Editorial notes

Smithery is relevant to HeyClaude users because MCP server discovery, installation, and trust scoring are central to agent workflows.

## Disclosure

Editorial listing. No paid placement or affiliate link is used.

About this resource

Editorial notes

Smithery is relevant to HeyClaude users because MCP server discovery, installation, and trust scoring are central to agent workflows.

Disclosure

Editorial listing. No paid placement or affiliate link is used.

#mcp#tool-discovery

Source citations

Add this badge to your README

Show that Smithery is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/tools/smithery.svg)](https://heyclau.de/entry/tools/smithery)

How it compares

Smithery side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field
Smithery logoSmithery

MCP server discovery and deployment platform for finding, installing, and running model context protocol tools.

Open dossier
Agenta logoAgenta

Open-source LLMOps platform for prompt management, prompt versioning, evaluation, and observability across LLM applications.

Open dossier
ClawHub logoClawHub

MIT-licensed OpenClaw skill and plugin registry with a hosted catalog, `clawhub` CLI, npm package, native OpenClaw install flows, SKILL.md publishing, plugin package publishing, vector search, scan status, moderation controls, install lockfiles, and opt-out install telemetry.

Open dossier
MCP Supergateway Hub

Self-hostable hub that wraps stdio MCP servers as streamable HTTP endpoints via supergateway, so a fleet of Model Context Protocol servers can run on one machine and be reached from any MCP client over the network.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety · Privacy · Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandSmithery logoSmitheryAgenta logoAgentaClawHub logoClawHub—
Categorytoolstoolstoolstools
Sourcesource-backedsource-backedsource-backedsource-backed
AuthorSmitheryAgentaOpenClawdpdanpittman
Added2026-04-272026-06-032026-06-182026-06-02
Platforms
CLI
CLI
CLI
CLI
Source repo————
Safety notes— missing✓Agenta can manage and deploy prompt or configuration changes, so production updates should go through review and rollback controls. Webhooks and GitHub automations tied to prompt or deployment changes should be scoped to trusted repositories and guarded workflows. Evaluation and online monitoring results should support, not replace, domain review for high-risk application behavior.✓ClawHub installs agent skills and OpenClaw plugins. Inspect source links, files, changelogs, declared runtime metadata, scan state, and plugin compatibility before installing or updating. `clawhub install`, `openclaw skills install`, and update commands write local skill files and metadata such as `.clawhub/lock.json` and per-skill origin records. Pin important local installs before updating shared workspaces. `clawhub token` prints the stored API token to stdout. Avoid exposing tokens through shell history, CI logs, support transcripts, screenshots, or model prompts. Publishing a skill to ClawHub releases it under MIT-0 according to the skill-format docs; do not publish proprietary, private, customer, or conflicting-license content. Plugin publishing resolves local folders, GitHub repositories, GitHub refs, or archives and checks OpenClaw compatibility metadata. Use `--dry-run`, verify artifacts, and review ClawPack digest/scan output before public release. Scan-held or blocked releases can be hidden from public catalog and install surfaces while remaining visible to owners; do not assume search visibility proves a release is safe or accepted.✓Bridges stdio MCP servers to HTTP and exposes them on your network, so each wrapped server's tools become reachable over HTTP — run it on a trusted network or behind authentication, not on a public interface. Running dozens of servers behind one host broadens the tool surface available to any connected client; use the --only/--exclude flags to scope what is exposed.
Privacy notes— missing✓Prompt records, variants, test sets, traces, model inputs and outputs, feedback, annotations, and evaluation results may be stored in Agenta. Hosted Agenta use sends that data to Agenta Cloud; self-hosted deployments still require retention, access-control, and backup policies. Review Agenta's sensitive-data redaction and retention guidance before sending production, customer, or regulated data.✓The CLI stores API token and registry configuration in the operating-system config directory or the path set by `CLAWHUB_CONFIG_PATH`. Logged-in `clawhub install` may send best-effort install telemetry containing the skill slug and version only; set `CLAWHUB_DISABLE_TELEMETRY=1` to opt out. ClawHub public listings can expose skill files, source links, versions, changelogs, install counts, stars, comments, publisher identity, and scan summaries. Publishing uploads `SKILL.md` plus supporting text files to the hosted registry. Keep secrets, private prompts, customer data, proprietary code, and credentials out of published bundles. Self-hosting ClawHub involves Convex, GitHub OAuth, JWT/JWKS keys, OpenAI embeddings for vector search, file storage, moderation data, and report handling.✓The gateway process and its .env hold API keys and see traffic passing between MCP clients and the wrapped servers. Fully self-hosted, so data stays on your own infrastructure rather than a third-party service.
Prerequisites— none listed
  • LLM application, prompt workflow, or agent workflow whose prompts and configurations need shared management.
  • Access to Agenta Cloud or a reviewed self-hosted Agenta deployment.
  • Provider credentials and a release policy for test sets, traces, prompt versions, and production deployment approvals.
  • Node.js 22 or newer for the published `clawhub` npm CLI.
  • OpenClaw installed and configured when using native `openclaw skills` or `openclaw plugins` install/update commands.
  • A GitHub-backed ClawHub account or API token for publishing, delete/undelete, scan, and other authenticated registry workflows.
  • A valid skill folder with `SKILL.md` when publishing skills, or an OpenClaw-compatible plugin package/source when publishing plugins.
  • Node.js 22+ (the gateway runs as a Node process; an optional systemd unit is provided for always-on use).
  • Python 3.10+ with uv for uvx-based servers, Docker for the docker server, and the Quint CLI for the formal-verification server.
  • API keys/connection strings in a local .env for any servers that authenticate against external services.
Install——
npm install -g clawhub
git clone https://github.com/dpdanpittman/mcp-supergateway-hub && cd mcp-supergateway-hub/gateway && npm install
Config——
{
  "openclawSkills": {
    "search": "openclaw skills search \"calendar\"",
    "install": "openclaw skills install @openclaw/demo",
    "update": "openclaw skills update --all"
  },
  "openclawPlugins": {
    "search": "openclaw plugins search \"calendar\"",
    "install": "openclaw plugins install clawhub:<package>",
    "update": "openclaw plugins update --all"
  },
  "clawhubCli": {
    "login": "clawhub login",
    "publishSkill": "clawhub skill publish ./my-skill --dry-run",
    "publishPlugin": "clawhub package publish <source> --family code-plugin --dry-run"
  }
}
—
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Related guides

Source-backed guides for putting this to work.

guides

Auditing MCP Client Configuration Before Team Rollout

Audit MCP client configuration before sharing it with a team.

Review firstSource-backedReview firstAdded 25d ago
Safety ✓ Privacy ✓by YB0y
guides

Building In-Process MCP Tools with the Claude Agent SDK

Define in-process MCP tools for the Claude Agent SDK with createSdkMcpServer and the tool helper, then wire them into query.

Review firstSource-backedReview firstAdded 1mo ago
Safety ✓ Privacy ✓by JPette1783
guides

Choose the Right Claude Extension Surface

Decide when to use Claude subagents, skills, commands, hooks, or MCP.

Review firstSource-backedReview firstAdded 1mo ago
Safety ✓ Privacy ✓by MkDev11

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.