Harness Hub
All startups

Smithery

A registry and toolchain for MCP servers.

Smithery indexes and helps deploy MCP (Model Context Protocol) servers — a distribution layer for the tool ecosystem agents connect to.

Visit smithery.ai

Pros & cons

Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.

Pros

  • User reportsA major MCP registry: one MCP author says listing there (alongside the official registry and Glama) is where most discovery happens.[1]
  • User reportsIts registry feeds third-party installers and config managers; one claims access to 7,300+ servers through Smithery.[1][2]
  • DocsArcade.dev acquired it in August 2026, which pairs the registry with Arcade's tool-authorization runtime.[1]

Cons

  • DocsA banner on the site says Smithery's MCP Proxy and managed identity shut down on 31 October, so hosted connections must be migrated.[1]
  • Independent testGitGuardian found a hosting bug, from June 2025, that leaked an overprivileged Fly.io token giving access to more than 3,000 hosted apps. It was patched quickly, and GitGuardian found no evidence of exploitation.[1]
  • DocsArcade's acquisition post does not say what happens to Smithery hosting, Connect or pricing.[1]
  • MetadataThe CLI repo moved to arcadeai-labs, is AGPL-3.0 and was last pushed on 31 May 2026.[1]
Best for
Listing and discovering MCP servers.
Watch out for
Avoid new production dependencies on Smithery hosting or Connect until Arcade publishes its plans.

Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction

People

In research (2)

The integration layer: hundreds of managed tools your agents can call.

Composio handles auth, schemas, observability and reliability for the external SaaS tools an agent uses — 'plumbing for agentic actions' across Slack, GitHub, Salesforce and 250+ other surfaces.

4 pros · 4 cons

Exa

Search API purpose-built for AI agents.

Exa (formerly Metaphor) provides neural search and web-crawl APIs tuned for agent consumption — live, cited knowledge for agents instead of stale training data.

4 pros · 4 cons

Search and extraction API optimized for LLMs and agents.

Tavily gives agents a single API for search, crawling and in-depth extraction, returning clean, cited results — a common tool in research-agent harnesses.

4 pros · 4 cons

Connections

Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.

Built on · 1

Similar entries · 6

The Harness Hub newsletter

New harness companies, projects, releases and the monthly State of Harness report, in your inbox.