Agent identity was always the goal for @SmitheryDotAI.
We talked about it in our blog posts about building "Google for a new internet", the new internet being one in which tool calls outpace human clicks.
With @TryArcade being deployed at multiple F100s including big six megabanks (and raising a $60m series A!), they've found the clearest path to enterprise value in the same space.
Thrilled to be joining such a capable team to bring the Smithery developer experience to the enterprise, and the enterprise-grade robustness and security to the Smithery platform :)
The @Auth0 MCP server is now available on @SmitheryDotAI.
Manual configs kill velocity. Smithery acts as an AI package manager to remove that friction.
Install the server so your AI can handle tenant setup & users.
https://t.co/XeOB9gypn2
Auth0: https://t.co/AnSAY3HcdJ
Trying something out, pretty experimental.
Get a fully typed SDK (including output schemas!) for *any* of our 5,000+ servers on @SmitheryDotAI.
Code mode, gen UI, and any workflow with only one API key needed: your Smithery API key (OAuth built-in!)
We're launching Uplink to let cloud agents access local resources on your computer.
Works with any local MCP server, including our new OSS Mouseless MCP! 👇
"It's official: @StatsReceipt is now AI-Ready. 🧾🤖
Our Trust Engine just passed the @SmitheryDotAI verification. Now agents like Claude and Cursor can natively verify your metrics via MCP.
Kill the fake screenshots. Embrace the proof. Try it: https://t.co/RUaPa8SFAM
We're open-sourcing Smithery Connect's vault!
agentpw is a framework for building your own "1Password for Agents".
It handles OAuth plumbing and secret sharing for APIs and MCPs to help agents get connected.
Create scoped tokens that agents can use but can't exfiltrate. 👇
We are now listed on @SmitheryDotAI
This is one of the premiere MCP marketplaces that exist in the world.
Discoverability is going up, and each day, someone new hears about us
See our auto-updating MCP here:
https://t.co/7QE0WUQuQF
We're settling the MCP vs. CLI debate by benchmarking Codex and Claude Code across 3 different APIs, totaling 756 runs.
We also cover skills, code mode, pretraining bias, and how MCP fits in the broader picture.
The results might surprise you👇
🚢 MCP CLI now has profiles!
You can use profiles to segregate your connections by functionality.
Profiles can also be hierarchical. In the example below, eng/ inherits connections from work/.
wild that in 2026, nearly six months after skills were released...
you still have to *manually upload a zip file* to add a skill to claude desktop
no CLI option, no URL, no github repo. we support zip files in @SmitheryDotAI but hoping this is a short-term thing!
We launched a little something... Connect your agents to *ANY* MCP server and call it directly through our CLI. Comes with tool search so your context doesn't explode. Check it out at https://t.co/cTmLAKwnDY
You can now connect to Granola @meetgranola with any CLI agent Codex / Claude Code / @openclaw in 1 command:
`npx -y @smithery/cli connect add granola`
Then your agent will interact with Granola via CLI.
With over 100K+ Skills on Smithery, how does your agent know which is better?
We built Yelp for agents.
Your agent can now leave a review on a Skill after trying it!
Try it in @openclaw / claude code 👇
Your agent needs better IAM. Using just the new @SmitheryDotAI skill, Claude:
🔐 Safely authenticates me into Linear
👥 Shares my identity across all agents like Cursor
‼️ (NEW): Can leave agent reviews on skills!
Check it out 👇 npx skills add smithery/cli