Overview
Learn how Sazabi uses the Model Context Protocol (MCP) to integrate with external AI tools and connect to third-party services.
The Model Context Protocol (MCP) is an open standard that enables AI assistants to use external tools and data sources. Sazabi supports MCP in two ways: as a server that external AI tools can connect to, and as a client that connects to external MCP servers.
What is MCP?
MCP is an industry standard protocol that allows AI systems to discover and use tools provided by external services. Think of it as a universal adapter that lets different AI tools and services work together seamlessly.
With MCP, an AI assistant can:
- Discover what tools a service provides
- Understand how to use those tools
- Call the tools and process results
This creates an ecosystem where AI capabilities can be extended without custom integrations for each combination of tools.
Two sides of MCP
Sazabi implements both sides of the MCP protocol, giving you flexibility in how you integrate AI into your workflows.
Sazabi as an MCP server
When Sazabi acts as an MCP server, external AI tools can use Sazabi's capabilities. This means you can:
- Use Claude Code to ask questions about your production systems
- Use Cursor to investigate issues while coding
- Use Claude Desktop for conversational debugging
- Use ChatGPT or Codex to access your observability data
Your favorite AI tool gains the ability to search logs, query metrics, and analyze your systems through Sazabi.
Sazabi MCP Server
Set up external AI tools like Claude Code, Cursor, and ChatGPT to use Sazabi.
Sazabi connecting to MCP servers
When Sazabi acts as an MCP client, it can connect to external services and use their tools. This means Chat can:
- Create Linear issues when it detects problems
- Send messages to Slack channels
- Create incidents in incident.io
- Query data from Datadog or Supabase
- Interact with any service that exposes an MCP server
This extends Sazabi's capabilities beyond observability, letting it take actions in your other tools as part of investigating or resolving issues.
MCP Connectors
Connect Sazabi to Slack, Linear, Datadog, and other services via MCP.
Why MCP matters
Extensibility
MCP lets you extend Sazabi's capabilities without waiting for native integrations. If a service exposes an MCP server, Sazabi can use it immediately.
Interoperability
Because MCP is an open standard, the same integrations work across different AI tools. Connect Sazabi to Linear once, and both Sazabi's assistant and external tools like Claude Code can use that connection.
Ecosystem
As more services adopt MCP, the ecosystem of available tools grows. Sazabi benefits from every new MCP server in the ecosystem, and other AI tools benefit from Sazabi's MCP server.