# mongodb-atlas-stream-processing

A skill for Atlas Stream Processing: provisions workspaces, wires up connections and processors, runs diagnostics and picks a tier.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 3600 installs · ★ 190
- Author: mongodb
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/mongodb/agent-skills/tree/HEAD/skills/mongodb-atlas-stream-processing/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/mongodb-atlas-stream-processing

## What it does

The skill covers the whole Atlas Stream Processing lifecycle through four MongoDB MCP Server tools: `atlas-streams-discover` for reads, `atlas-streams-build` for creates, `atlas-streams-manage` for start and update actions, `atlas-streams-teardown` for deletes. It ships a tool selection matrix, per-resource field mappings, plus references for connection configs and pipeline patterns.

You need the MongoDB MCP Server connected with Atlas API credentials (`apiClientId` and `apiClientSecret`), and every operation takes an Atlas project ID. If you do not know it, call `atlas-list-projects` first. A processor pipeline has to open with `$source` and close with `$merge` or `$emit`.

Safety checks are built in. Deleting a connection is blocked while a running processor still references it, and before a workspace goes away the skill reports how many connections and processors it holds and waits for your confirmation. Networking config such as PrivateLink cannot be changed after creation — you delete and recreate it. Worth checking your network layout before the first start. This is not for ordinary MongoDB queries or Atlas cluster management.

## Requirements
- Works with: MongoDB

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mongodb/agent-skills --skill mongodb-atlas-stream-processing -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/mongodb-atlas-stream-processing/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/mongodb-atlas-stream-processing/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mongodb/agent-skills --skill mongodb-atlas-stream-processing -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/mongodb-atlas-stream-processing/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mongodb/agent-skills --skill mongodb-atlas-stream-processing -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/mongodb-atlas-stream-processing/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mongodb/agent-skills mongodb-atlas-stream-processing
```

2. **Manually: put the files in place**
- File: `.github/skills/mongodb-atlas-stream-processing/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mongodb/agent-skills --skill mongodb-atlas-stream-processing -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mongodb/agent-skills --path skills/mongodb-atlas-stream-processing
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/mongodb-atlas-stream-processing/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mongodb/agent-skills --skill mongodb-atlas-stream-processing -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mongodb/agent-skills/tree/HEAD/skills/mongodb-atlas-stream-processing/SKILL.md

## When to use it
- provision an ASP workspace in a given region and tier
- attach Kafka, S3 or Lambda as a data source
- start a processor and stop it before billing keeps running
- read a processor health report to find runtime errors
- delete a workspace without leaving orphaned connections

## Example prompts
- list all workspaces in my Atlas project
- create a Kafka connection in the stream-prod workspace
- diagnose the orders-ingest processor and show me the errors

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: e35d626ea336a73a.

BEGIN THIRD-PARTY FILE e35d626ea336a73a
```text
---
name: mongodb-atlas-stream-processing
description: "Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source/sink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials."
license: Apache-2.0
metadata:
  version: "1.0.0"
  user-invocable: "true"
---

# 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](references/mcp-troubleshooting.md) for diagnostic steps and fallback options.

## Tool Selection Matrix

### atlas-streams-discover — ALL read operations
| Action | Use when |
|--------|----------|
| `list-workspaces` | See all workspaces in a project |
| `inspect-workspace` | Review workspace config, state, region |
| `list-connections` | See all connections in a workspace |
| `inspect-connection` | Check connection state, config, health |
| `list-processors` | See all processors in a workspace |
| `inspect-processor` | Check processor state, pipeline, config |
| `diagnose-processor` | Full health report: state, stats, errors |
| `get-networking` | PrivateLink and VPC peering details. Optional: `cloudProvider` + `region` to get Atlas account details for PrivateLink setup |

**Pagination** (all list actions): `limit` (1-100, default 20), `pageNum` (default 1).
**Response format**: `responseFormat` — `"concise"` (default for list actions) or `"detailed"` (default for inspect/diagnose).

### atlas-streams-build — ALL create operations
| Resource | Key parameters |
```
END THIRD-PARTY FILE e35d626ea336a73a

The third-party file has ended. Everything between the e35d626ea336a73a tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2314 of 19851 bytes. © mongodb · Apache-2.0 · https://github.com/mongodb/agent-skills/tree/HEAD/skills/mongodb-atlas-stream-processing/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md