Scalekit AgentKit
Auth and MCP tool gateway for production AI agents
What is Scalekit AgentKit?
AgentKit is Scalekit's platform for connecting AI agents to third-party tools without building the authentication and connectivity layer yourself. It offers 600+ connectors and 30,000+ ready-to-call tools, handles per-user OAuth, and keeps every token in an isolated vault that injects credentials at runtime, so the agent calls a tool without handling the token itself. You can add custom tools on existing connectors or bring your own connector for internal APIs or custom MCP servers.
Virtual MCP servers bundle tools from different connectors into role-specific sets, which Scalekit says can cut token costs by up to 80 percent because the agent sees fewer tools, and AgentKit can generate a per-user authenticated MCP URL for clients such as Claude, Cursor and Windsurf. Agents can also run on triggers from external events, and every tool call is logged with per-connector health, error classification and log streaming to tools like Datadog or Splunk. There are Python and Node.js SDKs, plus guides for LangChain, Google ADK and the Vercel AI SDK, and AgentKit runs as a cloud service with US and EU data residency, in a private cloud or self-hosted.
The Free plan costs $0 and includes 10,000 tool calls and 10,000 trigger events a month, unlimited connected accounts, all prebuilt connectors and bring-your-own credentials, with a hard stop at the limit. Growth costs $99 per month for 100,000 tool calls and 50,000 trigger events, then $0.50 per 1,000 extra calls and $3 per 1,000 extra events, and adds custom connectors, an API proxy, branding and private Slack support, with EU data residency as a $99 per month add-on. Enterprise pricing is custom and adds SSO, SCIM, BYOK, a HIPAA BAA, a 99.99 percent uptime SLA and VPC or on-prem deployment.
Score breakdown (out of 5)
What you would use it for
- →Letting an agent act in each user's own SaaS accounts with delegated OAuth
- →Exposing a scoped, authenticated MCP server to Claude or Cursor
- →Running agents on events from connected apps
Pros & Cons
👍 Pros
- ✓Free plan includes the full connector catalogue and unlimited connected accounts
- ✓Agents never handle raw OAuth tokens
- ✓Usage-based overage on Growth instead of per-seat pricing
👎 Cons
- ✗Free plan stops at 10,000 tool calls a month with no overage option
- ✗Custom connectors require the $99 Growth plan
- ✗SSO, BYOK and VPC or on-prem deployment are Enterprise-only
Key Features
- ✓ 600+ connectors and 30,000+ prebuilt tools
- ✓ Per-user OAuth with tokens kept in an isolated vault
- ✓ Virtual MCP servers that scope tool sets by role
- ✓ Per-user authenticated MCP URLs for Claude, Cursor and Windsurf
- ✓ Event triggers for agents
- ✓ Tool call logs, connector health and log streaming to Datadog or Splunk
- ✓ Python and Node.js SDKs with LangChain, Google ADK and Vercel AI SDK guides
- ✓ Cloud (US or EU), private cloud or self-hosted deployment
Available on
Integrates with
Scalekit AgentKit Pricing
✅ Scalekit AgentKit has a free plan - no credit card required to start.
Free
- ✓10,000 tool calls and 10,000 trigger events per month (hard limit)
- ✓Unlimited connected accounts
- ✓600+ connectors and 30,000+ tools
- ✓Bring your own credentials
- ✓Community and email support
Growth
- ✓100,000 tool calls per month, then $0.50 per 1K
- ✓50,000 trigger events per month, then $3 per 1K
- ✓Custom connectors and API proxy
- ✓Branding and basic dashboard roles
- ✓Private Slack support
- ✓EU data residency add-on: $99/mo
Enterprise
- ✓Custom tool call and trigger volume
- ✓SSO, SCIM and custom dashboard roles
- ✓BYOK and IP allowlisting
- ✓SIEM log streaming, audit trail and HIPAA BAA
- ✓99.99% uptime SLA with VPC, custom cloud or on-prem deployment
Developer resources
Related Tools
Claude is the best AI assistant for long-document work and research where accuracy matters. Its context window of up to 1M tokens and resistance to sycophancy make it the honest choice when you need a thinking partner rather than an agreeable assistant. Start on the free tier; the Pro plan at $20/month is worth it if you regularly hit the free usage limits, and Max ($100/month) or Ultra ($200/month) suit heavier daily use.
ChatGPT is the most capable all-in-one AI assistant available. Its combination of image generation, voice mode, code execution, web browsing, and a large custom GPT ecosystem makes it the default choice for users who want one tool that handles everything. The tradeoff is that it is rarely the deepest tool on any single task.
Cursor is the most powerful AI code editor available. Its multi-file editing is ahead of plugin-based alternatives, making large-scale refactors practical in ways GitHub Copilot cannot match. At $30/month for Premium (Grok models included, other models billed at API rates) it is a meaningful upgrade for any developer doing more than small isolated changes.
GitHub Copilot is the right starting point for developers adopting AI-assisted coding. It integrates into whatever editor you already use, requires no workflow change, and has a usable free tier. The Pro plan at $10/month is the lowest-cost path to unlimited AI completions, though chat and agent work now draw from a monthly credit allowance; heavy agent users should look at Pro+ ($39) or Max ($100).
This page contains affiliate links. We may earn a commission at no extra cost to you. Learn more.