rudder-mcp-workflow

Name: rudder-mcp-workflow
Author: rudderlabs

18stars0forks

How to install rudder-mcp-workflow?

rudderlabs/rudder-agent-skills/rudder-mcp-workflow

$npx -y skills add rudderlabs/rudder-agent-skills --skill rudder-mcp-workflow

Installs into the current project.

Summary

Connects AI agents to RudderStack via MCP tool calls for catalog, sources, destinations, transformations, and live events. Use when connecting an AI agent to RudderStack's MCP server, driving RudderStack via MCP, or mentions of mcp.rudderstack.com.

Files · 1

View on GitHub

SKILL.md

1	# RudderStack MCP Workflow
2
3	RudderStack's hosted MCP server at `mcp.rudderstack.com` exposes a RudderStack workspace as an MCP endpoint so AI agents (Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, or any MCP client) can inspect and drive workspace resources via tool calls. Authoritative docs: https://mcp.rudderstack.com/docs.
4
5	## When to use
6
7	The user wants an AI agent to drive RudderStack, mentions RudderStack + MCP, asks about `mcp.rudderstack.com`, or wants to configure MCP tool access for a RudderStack workspace.
8
9	## Preflight
10
11	Before running any workflow, verify:
12
13	- [ ] Your MCP client is configured to connect to `https://mcp.rudderstack.com/mcp`. See `rudder-mcp-setup` for the Claude Code walkthrough; the official docs cover Claude Desktop, Cursor, VS Code, Windsurf, and the claude.ai web UI.
14	- [ ] OAuth flow completed (browser sign-in to your RudderStack account on first tool use).
15	- [ ] `mcp.rudderstack.com` is reachable on port 443 from your network.
16
17	## Client configuration
18
19	Claude Code `mcpServers` block (HTTP transport via `mcp-remote`):
20
21	```json
22	{
23	"mcpServers": {
24	"rudderstack": {
25	"command": "npx",
26	"args": ["-y", "mcp-remote", "https://mcp.rudderstack.com/mcp"]
27	}
28	}
29	}
30	```
31
32	For other clients (Claude Desktop, Cursor, VS Code, Windsurf, claude.ai connectors), use the snippets at https://mcp.rudderstack.com/docs.
33
34	## Tool catalog
35
36	The server exposes tools across five categories. Exact names are discovered dynamically by your MCP client — inspect your client's tools panel (or ask Claude "what RudderStack tools do you have?") for the authoritative list. The names below are representative.
37
38	### Data sources
39	List sources and fetch a specific source's details, definitions, event schemas, event metrics, and the tracking plan(s) bound to it. Useful for: "what's broken in source X?", "what events does source X emit?".
40
41	### Destinations
42	List destinations and fetch a specific destination's details, definitions, event metrics, latency metrics, and recent errors. Useful for: "why is destination X dropping events?", "compare event volume across destinations".
43
44	### Transformations
45	List transformations and libraries, fetch a specific transformation, create or update transformations, and test them against captured payloads. Useful for: "draft a transformation for use case X", "test this transformation against last week's events".
46
47	### Events
48	Stream and inspect live events flowing through your workspace. Useful for: "show me the last 10 events from source X", "did the 'Order Completed' event land with the right properties?".
49
50	### Documentation
51	Search RudderStack documentation from inside your client. Useful for: "how does RETL handle late-arriving rows?", "what destination types support transformations?".
52
53	## Common workflows
54
55	Patterns to ask Claude — phrased as a user would say them:
56
57	- "What's broken in my sources?" — list sources, then for each one check event metrics and tracking-plan violations.
58	- "Draft a transformation and test it." — find similar existing transformations, draft a new one, run it against captured payloads, then save.
59	- "Live-debug this connection." — inspect live events for the source and correlate with recent destination errors.
60
61	## Instrumentation Verification Workflow
62
63	After instrumenting events (via CLI, Terraform, or code), verify they reach destinations:
64
65	```
66	1. APPLY TRACKING PLAN
67	└── e.g. rudder-cli apply -l ./
68
69	2. TRIGGER EVENTS
70	└── Run your app, trigger the instrumented events
71
72	3. VERIFY LIVE EVENTS
73	└── Ask Claude: "show recent live events from source <id>"
74	└── Confirm event name, properties, context match the tracking plan
75
76	4. VERIFY DESTINATION
77	└── For warehouse destinations: query the warehouse
78	(Snowflake, BigQuery, Redshift, etc.) for the event
79	└── For SaaS destinations: check the destination UI
80
81	5. CHECK FOR VIOLATIONS
82	└── Ask Claude: "any tracking-plan violations on source <id>?"
83	└── Review violations to identify schema mismatches
84	```
85
86	### Example: Verifying an "Audience Created" event
87
88	```
89	1. Apply tracking plan with "Audience Created" event
90	2. Create an audience in the web app
91	3. Ask Claude: "any Audience Created events on source <id> in the last hour?"
92	4. Verify properties: audience_id, audience_name, condition_count
93	5. Confirm the event landed in your warehouse destination
94	```
95
96	## Dev vs Prod Workspace Pattern
97
98	Recommended for safe iteration:
99
100	\| Workspace \| Purpose \| Governance \|
101	\|-----------\|---------\|------------\|
102	\| Dev \| Testing, iteration \| `unplannedEvents: log` \|
103	\| Prod \| Production traffic \| `unplannedEvents: block` \|
104
105	Workflow:
106
107	```
108	1. Point your MCP client at the D

People who liked this also viewed

6 picks

Type

rudder-mcp-workflow

18stars0forks

View on GitHub

How to install rudder-mcp-workflow?

rudderlabs/rudder-agent-skills/rudder-mcp-workflow

$npx -y skills add rudderlabs/rudder-agent-skills --skill rudder-mcp-workflow

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# RudderStack MCP Workflow
2
3	RudderStack's hosted MCP server at `mcp.rudderstack.com` exposes a RudderStack workspace as an MCP endpoint so AI agents (Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, or any MCP client) can inspect and drive workspace resources via tool calls. Authoritative docs: https://mcp.rudderstack.com/docs.
4
5	## When to use
6
7	The user wants an AI agent to drive RudderStack, mentions RudderStack + MCP, asks about `mcp.rudderstack.com`, or wants to configure MCP tool access for a RudderStack workspace.
8
9	## Preflight
10
11	Before running any workflow, verify:
12
13	- [ ] Your MCP client is configured to connect to `https://mcp.rudderstack.com/mcp`. See `rudder-mcp-setup` for the Claude Code walkthrough; the official docs cover Claude Desktop, Cursor, VS Code, Windsurf, and the claude.ai web UI.
14	- [ ] OAuth flow completed (browser sign-in to your RudderStack account on first tool use).
15	- [ ] `mcp.rudderstack.com` is reachable on port 443 from your network.
16
17	## Client configuration
18
19	Claude Code `mcpServers` block (HTTP transport via `mcp-remote`):
20
21	```json
22	{
23	"mcpServers": {
24	"rudderstack": {
25	"command": "npx",
26	"args": ["-y", "mcp-remote", "https://mcp.rudderstack.com/mcp"]
27	}
28	}
29	}
30	```
31
32	For other clients (Claude Desktop, Cursor, VS Code, Windsurf, claude.ai connectors), use the snippets at https://mcp.rudderstack.com/docs.
33
34	## Tool catalog
35
36	The server exposes tools across five categories. Exact names are discovered dynamically by your MCP client — inspect your client's tools panel (or ask Claude "what RudderStack tools do you have?") for the authoritative list. The names below are representative.
37
38	### Data sources
39	List sources and fetch a specific source's details, definitions, event schemas, event metrics, and the tracking plan(s) bound to it. Useful for: "what's broken in source X?", "what events does source X emit?".
40
41	### Destinations
42	List destinations and fetch a specific destination's details, definitions, event metrics, latency metrics, and recent errors. Useful for: "why is destination X dropping events?", "compare event volume across destinations".
43
44	### Transformations
45	List transformations and libraries, fetch a specific transformation, create or update transformations, and test them against captured payloads. Useful for: "draft a transformation for use case X", "test this transformation against last week's events".
46
47	### Events
48	Stream and inspect live events flowing through your workspace. Useful for: "show me the last 10 events from source X", "did the 'Order Completed' event land with the right properties?".
49
50	### Documentation
51	Search RudderStack documentation from inside your client. Useful for: "how does RETL handle late-arriving rows?", "what destination types support transformations?".
52
53	## Common workflows
54
55	Patterns to ask Claude — phrased as a user would say them:
56
57	- "What's broken in my sources?" — list sources, then for each one check event metrics and tracking-plan violations.
58	- "Draft a transformation and test it." — find similar existing transformations, draft a new one, run it against captured payloads, then save.
59	- "Live-debug this connection." — inspect live events for the source and correlate with recent destination errors.
60
61	## Instrumentation Verification Workflow
62
63	After instrumenting events (via CLI, Terraform, or code), verify they reach destinations:
64
65	```
66	1. APPLY TRACKING PLAN
67	└── e.g. rudder-cli apply -l ./
68
69	2. TRIGGER EVENTS
70	└── Run your app, trigger the instrumented events
71
72	3. VERIFY LIVE EVENTS
73	└── Ask Claude: "show recent live events from source <id>"
74	└── Confirm event name, properties, context match the tracking plan
75
76	4. VERIFY DESTINATION
77	└── For warehouse destinations: query the warehouse
78	(Snowflake, BigQuery, Redshift, etc.) for the event
79	└── For SaaS destinations: check the destination UI
80
81	5. CHECK FOR VIOLATIONS
82	└── Ask Claude: "any tracking-plan violations on source <id>?"
83	└── Review violations to identify schema mismatches
84	```
85
86	### Example: Verifying an "Audience Created" event
87
88	```
89	1. Apply tracking plan with "Audience Created" event
90	2. Create an audience in the web app
91	3. Ask Claude: "any Audience Created events on source <id> in the last hour?"
92	4. Verify properties: audience_id, audience_name, condition_count
93	5. Confirm the event landed in your warehouse destination
94	```
95
96	## Dev vs Prod Workspace Pattern
97
98	Recommended for safe iteration:
99
100	\| Workspace \| Purpose \| Governance \|
101	\|-----------\|---------\|------------\|
102	\| Dev \| Testing, iteration \| `unplannedEvents: log` \|
103	\| Prod \| Production traffic \| `unplannedEvents: block` \|
104
105	Workflow:
106
107	```
108	1. Point your MCP client at the D

People who liked this also viewed

6 picks

Type