Update to RudderStack

Changed files

Choose a file to see its text changes. Binary or large files show metadata only.

.codex-plugin/plugin.json →

.codex-plugin/plugin.json

− removed · + added

--- before
+++ after
@@ -1,7 +1,7 @@
 {
   "name": "rudderstack",
-  "version": "0.43.0",
-  "description": "Debug your event pipeline from your agent: errors, violations, failed loads. Official hosted MCP server for RudderStack.",
+  "version": "0.44.1",
+  "description": "Connect your AI agents to RudderStack platform and manage your pipelines, warehouses and activate your audiences",
   "author": {
     "name": "RudderStack",
     "email": "mcp@rudderstack.com",
@@ -23,8 +23,8 @@
   "mcpServers": "./.mcp.json",
   "interface": {
     "displayName": "RudderStack",
-    "shortDescription": "Debug your data pipelines",
-    "longDescription": "RudderStack MCP connects ChatGPT and Codex to your RudderStack workspace, so you can debug customer data pipelines by asking instead of clicking through dashboards.\n\nWhat you can do:\n- Debug delivery: destination errors with sample events and API responses, success and failure rates, latency, and a live tail of events.\n- Check warehouse and Reverse ETL syncs: upload history, failed loads, table-level detail and sync runs.\n- Enforce your tracking plan: violations per event, tracking plan versions, the Data Catalog, and duplicate or misspelled event names.\n- Build audiences: explore your data graph, preview an audience's size, create it, and sync it to an activation destination.\n- Investigate changes: audit logs, source and destination configuration, Profiles runs and RudderStack status incidents.\n- Ask the docs: answers from RudderStack documentation with citations.\n\nWho it's for: data engineers, analytics engineers and growth engineers who run event pipelines on RudderStack.\n\nHow it handles your data: you sign in with RudderStack OAuth, and every call runs with your RudderStack permissions in workspaces you can already access. Some tools redact or hash sensitive fields in event payloads before they reach the model.\n\nLimitations: most tools only read. A few write, to transformations, audiences and their destination connections, and each tool declares whether it reads or writes so ChatGPT can confirm before acting. Tools for features that aren't enabled in your workspace return empty results. You need a RudderStack account.",
+    "shortDescription": "Connect AI agents to your CDP",
+    "longDescription": "RudderStack MCP connects ChatGPT and Codex to your RudderStack workspace so you can debug customer data pipelines by asking instead of clicking through dashboards.\n\nDebug delivery: get destination errors with sample events and the destination's API response, success and failure rates, latency, and a live tail of events across sources, transformations and destinations.\n\nCheck warehouse and Reverse ETL syncs: upload history, failed loads, table-level detail and sync runs.\n\nEnforce your tracking plan: violation counts and samples per event, tracking plan versions, the Data Catalog, and duplicate or misspelled event names.\n\nBuild transformations: start from a template, write JavaScript or Python, test it on sample events, then save it and connect it to a destination.\n\nBuild audiences: explore your data graph, preview an audience's size, create it, and sync it to an activation destination.\n\nInvestigate changes with audit logs, configuration details, Profiles runs and RudderStack status incidents, and ask RudderStack's docs anything.\n\nChatGPT and Codex act with your RudderStack permissions, only in workspaces you can already access. Some tools hash or redact sensitive fields in event payloads before they reach ChatGPT or Codex.",
     "developerName": "RudderStack",
     "category": "Developer Tools",
     "capabilities": [