Let your agents use 30,000+ tools across 600+ apps, from Salesforce to GitHub, through one MCP gateway. AgentKit handles auth and integrations, so every action runs as the user who asked, within the scopes they granted. Give each agent only the tools its job needs with Virtual MCP Servers. Add internal APIs as custom connectors. Use Triggers to start an agent the moment an email lands. Built for developers taking agents to production: every call is logged. Free tier: 10,000 tool calls a month.
I'm Ravi, co-founder of Scalekit. Today we're launching AgentKit, an MCP gateway that handles auth and tool-calling for AI agents in production.
Why now? Over the last year, wiring an agent to a tool got easy. MCP standardized the interface, and any agent can now call Gmail or Salesforce after an afternoon of work.
But the tool call is only the surface. Once an agent ships to real users, everything underneath it shows up:
whose credentials each call executes with
which tools each agent should have in context
the internal systems no catalog covers
what happens when an upstream API pushes back
who's accountable for every action
That layer decides whether an agent makes it to production. It's what we built AgentKit for.
Try it free:scalekit.com. The free tier includes 10,000 tool calls a month and all 600+ connectors. Make your first tool call from the dashboard, or start from your terminal with npx @ scalekit-inc/cli setup.
Here's what it looks like in practice.
Say you're shipping a sales agent inside your product. A rep types: "Prep me for the Acme renewal. Pull the deal, the last three email threads, what the team said in Slack, when we last met them, and how much they've used the product this quarter."
Four apps, one ask. Getting it working for one rep in a demo is easy. Here's what's underneath when it runs for every rep at every customer:
Thousands of OAuth grants, not four. 40 customers × 30 reps × Salesforce, Gmail, Slack and Calendar = 4,800 connected accounts. Each needs its tokens stored, isolated per customer, and refreshed before they expire mid-run. → AgentKit manages connected accounts end to end. Users authorize through an auth link you surface in your app. Tokens live in a per-tenant AES-256 vault, refresh automatically, and are injected at execution time. They never touch your code, logs, or prompts.
Every call has to execute as the right user. The agent should see what that rep can see at that customer, and nothing more. Not a shared service account with org-wide access to every inbox. → Every tool call executes with the end user's own credentials, within the scopes they granted.
Every tool definition costs context. Gmail alone exposes ~30 tools; four apps put over a hundred on the table. At ~200 tokens per definition, 40 tools burn ~8,000 tokens before the agent does any work, and tool selection gets worse as the list grows. Your prep agent needs about ten tools. Your outbound agent needs a different ten. → Virtual MCP Servers let you compose a tool set per agent role, across connectors. Each role gets one static MCP URL; you mint a short-lived session token per user per run. Smaller context and least-privilege access: ten tool definitions (~2,000 tokens) instead of over a hundred (20,000+).
The data you need has no connector. Usage lives in your customer's internal analytics service. No catalog covers it, so you'd build that integration yourself, auth included. → Define it as a custom connector (OAuth 2.0, API key, bearer token, RSA or basic auth), or point AgentKit at a remote MCP server. It runs on the same gateway with the same credential handling and logs as the 600+ built-in connectors.
It has to hold up and be auditable. Rate limits, timeouts, upstream errors the model can't act on. Then a deal stage changes and someone asks whether the rep did it or the agent did. → Retries and rate limits are handled on every call. Every call is logged with agent, user, tool and response, and logs stream to Datadog or Splunk.
None of this shows up in a demo. All of it shows up in production. AgentKit handles that layer: 30,000+ tools across 600+ apps behind one MCP gateway. And with Triggers, an agent can start on its own the moment an email lands.
Python and Node SDKs. Works with the Anthropic and OpenAI SDKs, LangChain, Google ADK, Vercel AI SDK, Mastra, and Claude Code. You keep your framework and backend.
Which of these five has slowed your agent down the most?
Really interesting product, congrats on the launch! Letting agents act only within what the user actually allowed is a great idea. Best of luck with it 🚀
Whose credentials, by a mile. We caught a nasty version of it this week before it hit anyone: our scheduled agents ran under the person who approved them, so removing that person from the org would have stopped all their jobs, even though the admin review looked finished. If every call here runs as the user who asked, what happens to scheduled agents and Triggers when that user leaves or loses a scope? Does the agent stop, and who hears about it?
Congrats Satya, Ravi and team!
We worked with Scalekit previously for our Auth services and are super excited about trying Agentkit soon too - for the better control and visibility it could bring us.
Congratulations on the launch @satya_deva549 and @ravibits! We are early adopters of Agentkit, which has been instrumental in helping us scale to over 200 connectors.
Great launch! The production layer around agents is just as important as the tools they can call. Excited to see where AgentKit goes!
Congrats on the launch @ravibits@satya_deva549. How is this different from connecting an MCP server directly to my agent?
Great product from Satya and Ravi. I've seen the story from the beginning, and this one just ups the game from what I know they've already been building.
Congrats folks on the launch. This is really exciting, are you planning to support browser agents too in the future?
The per-tenant token vault plus Virtual MCP Servers per role is a sensible split. One thing I'm curious about: when a user revokes a grant in Salesforce directly, how fast does AgentKit notice, and what does the agent see on its next call, a clean auth error or a silent failure?
This is pretty cool - congratulations on the launch @satya_deva549 @ravibits @shrimithranr!
This is great idea, and very necessary for any AI-native SaaS app. Maintaining integrations is challenging. Keeping it all secure is more than a full-time job.
Congrats on the launch! As founders building infra for developers, we know how much time enterprise auth eats: SSO, SCIM, and now securing agents and MCP servers. Scalekit turns months of plumbing into an afternoon so teams can focus on their actual product. Excited to see it go live 🚀
Whose credentials each call runs with, that's the one for us. Our agents never get a password, I do every sign-in myself, so when a session drops in the middle of a run nothing moves until I sign back in. If a token can't be refreshed mid-run, does the agent get an error it can pass back, or does the call just fail?
About AgentKit by Scalekit on Product Hunt
“MCP gateway for production agents that acts on your behalf”
AgentKit by Scalekit launched on Product Hunt on November 3rd, 2026 and earned 411 upvotes and 96 comments, earning #1 Product of the Day. Let your agents use 30,000+ tools across 600+ apps, from Salesforce to GitHub, through one MCP gateway. AgentKit handles auth and integrations, so every action runs as the user who asked, within the scopes they granted. Give each agent only the tools its job needs with Virtual MCP Servers. Add internal APIs as custom connectors. Use Triggers to start an agent the moment an email lands. Built for developers taking agents to production: every call is logged. Free tier: 10,000 tool calls a month.
AgentKit by Scalekit was featured in API (98.8k followers) and Developer Tools (522.4k followers) on Product Hunt. Together, these topics include over 104.4k products, making this a competitive space to launch in.
Who hunted AgentKit by Scalekit?
AgentKit by Scalekit was hunted by fmerian. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how AgentKit by Scalekit stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
fmerian
Hey Product Hunt,
I'm Ravi, co-founder of Scalekit. Today we're launching AgentKit, an MCP gateway that handles auth and tool-calling for AI agents in production.
Why now? Over the last year, wiring an agent to a tool got easy. MCP standardized the interface, and any agent can now call Gmail or Salesforce after an afternoon of work.
But the tool call is only the surface. Once an agent ships to real users, everything underneath it shows up:
whose credentials each call executes with
which tools each agent should have in context
the internal systems no catalog covers
what happens when an upstream API pushes back
who's accountable for every action
That layer decides whether an agent makes it to production. It's what we built AgentKit for.
Here's what it looks like in practice.
Say you're shipping a sales agent inside your product. A rep types: "Prep me for the Acme renewal. Pull the deal, the last three email threads, what the team said in Slack, when we last met them, and how much they've used the product this quarter."
Four apps, one ask. Getting it working for one rep in a demo is easy. Here's what's underneath when it runs for every rep at every customer:
Thousands of OAuth grants, not four. 40 customers × 30 reps × Salesforce, Gmail, Slack and Calendar = 4,800 connected accounts. Each needs its tokens stored, isolated per customer, and refreshed before they expire mid-run. → AgentKit manages connected accounts end to end. Users authorize through an auth link you surface in your app. Tokens live in a per-tenant AES-256 vault, refresh automatically, and are injected at execution time. They never touch your code, logs, or prompts.
Every call has to execute as the right user. The agent should see what that rep can see at that customer, and nothing more. Not a shared service account with org-wide access to every inbox. → Every tool call executes with the end user's own credentials, within the scopes they granted.
Every tool definition costs context. Gmail alone exposes ~30 tools; four apps put over a hundred on the table. At ~200 tokens per definition, 40 tools burn ~8,000 tokens before the agent does any work, and tool selection gets worse as the list grows. Your prep agent needs about ten tools. Your outbound agent needs a different ten. → Virtual MCP Servers let you compose a tool set per agent role, across connectors. Each role gets one static MCP URL; you mint a short-lived session token per user per run. Smaller context and least-privilege access: ten tool definitions (~2,000 tokens) instead of over a hundred (20,000+).
The data you need has no connector. Usage lives in your customer's internal analytics service. No catalog covers it, so you'd build that integration yourself, auth included. → Define it as a custom connector (OAuth 2.0, API key, bearer token, RSA or basic auth), or point AgentKit at a remote MCP server. It runs on the same gateway with the same credential handling and logs as the 600+ built-in connectors.
It has to hold up and be auditable. Rate limits, timeouts, upstream errors the model can't act on. Then a deal stage changes and someone asks whether the rep did it or the agent did. → Retries and rate limits are handled on every call. Every call is logged with agent, user, tool and response, and logs stream to Datadog or Splunk.
None of this shows up in a demo. All of it shows up in production. AgentKit handles that layer: 30,000+ tools across 600+ apps behind one MCP gateway. And with Triggers, an agent can start on its own the moment an email lands.
Python and Node SDKs. Works with the Anthropic and OpenAI SDKs, LangChain, Google ADK, Vercel AI SDK, Mastra, and Claude Code. You keep your framework and backend.
Which of these five has slowed your agent down the most?