Mongodb Atlas Stream Processing

Handles the full lifecycle of MongoDB Atlas Stream Processing pipelines through four MCP tools: discover (read ops), build (create), manage (start/stop/modify), and teardown (delete). Covers workspace provisioning, connecting data sources and sinks (Kafka, Atlas clusters, S3, Lambda), processor management with aggregation pipelines, and network config including PrivateLink. The tool selection matrix is nicely organized, and there's a critical callout to validate pipeline syntax against knowledge base before creating processors since field names vary by sink type. Good safety rails like auto-stopping processors before deletion and blocking connection deletion if processors reference them. Requires MongoDB MCP Server with Atlas API credentials to work.

skills.sh installs: 3.9K
GitHub stars: 197
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mongodb/agent-skills --skill mongodb-atlas-stream-processing --agent claude-code

Installs into .claude/skills of the current project.

Files

MongoDB Atlas Streams

Build, operate, and debug Atlas Stream Processing (ASP) pipelines using four MCP tools from the MongoDB MCP Server.

Prerequisites

This skill requires the MongoDB MCP Server connected with:

Atlas API credentials (apiClientId and apiClientSecret)

The 4 tools: atlas-streams-discover, atlas-streams-build, atlas-streams-manage, atlas-streams-teardown.

All operations require an Atlas project ID. If unknown, call atlas-list-projects first to find your project ID.

If MCP tools are unavailable

If the MongoDB MCP Server is not connected or the streams tools are missing, see references/mcp-troubleshooting.md for diagnostic steps and fallback options.