What is Digma?

Digma is a code-observability MCP (Model Context Protocol) server that enables dynamic code analysis through OpenTelemetry/APM to assist with code reviews and performance optimization.

How to use Digma?

1. Deploy Digma to process your observability data
2. Configure your MCP client (Claude, Cursor, etc.) to connect to Digma's MCP server
3. Use the agent to query runtime performance data and analyze code issues
4. Set rules/policies for structured code review processes

Key features of Digma?

• Observability-assisted code reviews: Find runtime issues during PR checks
• Performance optimization: Identify and fix inefficient code using runtime data
• Distributed tracing: Track code execution across services
• Cross-environment analysis: Check behavior across dev, staging, and production

Use cases of Digma?

1. Code review automation: Detect runtime issues during pull requests
2. Performance troubleshooting: Find and fix slow database queries
3. Impact analysis: Understand ripple effects of code changes
4. Test generation: Create tests based on runtime behavior
5. Breaking change detection: Catch API changes that might affect other services

FAQ from Digma?

• What environments can Digma analyze?

Digma can analyze code performance across development, staging, and production environments.

• What languages does Digma support?

Digma works with any language that has OpenTelemetry instrumentation.

• How does Digma integrate with my workflow?

Digma connects through MCP clients like Claude or Cursor, or via tools like SuperGateway.

• Is Digma free to use?

Digma is currently available through an early access program.

• What kind of observability data does Digma use?

Digma uses distributed tracing, metrics, and APM data to analyze code performance.

Digma Code Observability MCP Server

A Model Context Protocol (MCP) server implementation for enabling agents to access observability insights using Digma for code observability and dynamic code analysis

Key Features 🚀

• 🗣️ Observability-assisted code reviews: Check the PR branch for any issues discovered by pre-prod observability.
• 🔎 Find code inefficiencies with dynamic code analysis: Identify issues in the code/queries that are slowing the app down
• 🔭 Utilize code runtime usage data from distributed tracing: Check for breaking changes or generated relevant tests

Example prompts 💬

• help me review the code changes in this branch by looking at related runtime issues
• I want to improve the performance of this app. What are the three most severe issues I can fix?
• I'm making changes to this function, based on runtime data. What other services and code would be affected?
• Are there any new issues in this code based on the Staging environment?
• Which database queries have the most impact on the application performance?

See it in action 📺

---

Get early access 👀

Digma pre-processes your observability data to identify issues, track code performance and runtime data - for dynamic code analysis. Visit our MCP page to sign up for early access to our MCP server.

Installation ⚙️

Configure your MCP Client (Claude, Cursor, etc.) to include the Digma MCP. The Digma deployment includes the MCP SSE server. You can configure it using its URL in your client, or use an MCP tool such as SuperGateway to run it as a command tool. The MCP URL path is composed of the Digma API Key as follows: https:///mcp/>/sse ### Example MCP XML If your client supports SSE servers, you can use the following syntax: json { "mcpServers": { "digma": { "url": "https:///mcp/DIGMA_API_TOKEN>/sse", } // ... other servers might be here ... } } To use the MCP server as a command tool, use the SuperGateway tool to bridge to the URL as seen below: json { "digma": { "command": "npx", "args": [ "-y", "supergateway", "--sse", "https:///mcp/DIGMA_API_TOKEN>/sse" ] } } --- ## Using rules 👨‍💼 The agent is autonomous and selects when to use the data provided by Digma as needed, however, some clients allow setting rules and policies to set a more structured process. Here is an example rules file which you can add to your cursor .cursor/rules directory markdown # Digma Memory File - Code Review Instructions ## Runtime Analysis Settings - Environment: TEST ## Code Review Protocol 1. For any code or branch review request: - Get the list of changed files and methods in the current branch using `git diff` - Check for ALL runtime issues in TEST environment (not just for the method in context) - Check if any runtime issue may be related to the changed code - Check the runtime usage of the changed methods (based on the `git diff`) - Check if any of the changed methods (based on the `git diff`) have a high risk based on their performance impact - Synthesize the data with standard code review analysis ## Note This file is used by the AI assistant to maintain consistent review protocols across sessions. ## License 📜 MIT License. See LICENSE file.