chore: update n8n to 2.35.x (v2.73.0)

CHANGELOG.md

@@ -7,6 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [2.73.0] - 2026-08-19
+
+### Changed
+
+- **n8n dependencies updated to 2.35.x** — `n8n-nodes-base` 2.34.4 → 2.35.3, `n8n-core` 2.34.4 → 2.35.3, `n8n-workflow` 2.34.3 → 2.35.2, `@n8n/n8n-nodes-langchain` 2.34.4 → 2.35.3. The node database is rebuilt against them: 2,541 nodes (832 core, up from 831, plus 1,709 community nodes, up from 1,583). The single core addition is `nodes-base.confluence`, which n8n currently ships as a hidden shell — `hidden: true`, no properties, no operations, its actions landing in later releases. It is indexed the same way the other hidden `n8n-nodes-base` entries (Function, Cron, Item Lists, Read Binary File and the rest) always have been, so `get_node` returns it with an empty schema until n8n fills it in.
+- Node-level changes users will see through this server: the Slack node moves to typeVersion 2.7 and uses Slack's Real-time Search API for message search; the GitHub node gains a timeout option on Dispatch and Wait for Completion; the Salesforce Trigger gains OAuth2 JWT authentication; the Google Ads node migrates from the sunset v21 API to v25, including the renamed video-views metric; Microsoft Teams regains the `Group.ReadWrite.All` OAuth2 scope; the X (formerly Twitter) node's OAuth2 and API endpoints move to `x.com`; and the Merge node picks up "Append" and "Combine" search aliases, which `search_nodes` now matches. Eighteen core node schemas changed in total.
+- **The Kafka node now has a version 2** built on n8n's new Kafka library, with compression options. n8n keeps `defaultVersion: 1`, so `get_node` and validation still report version 1 — that is the typeVersion the editor instantiates. The database will follow when n8n flips the default.
+- Community nodes refreshed: 1,437 verified nodes from the n8n registry plus 141 node rows from 65 npm packages, with 6 rows dropped for packages that no longer declare them. 139 missing READMEs were fetched and 126 AI documentation summaries generated, bringing documentation coverage to 1,696 of 1,709 community nodes.
+
 ## [2.72.0] - 2026-08-18
 
 ### Added

Dockerfile

@@ -20,7 +20,7 @@ RUN --mount=type=cache,target=/root/.npm \
     echo '{}' > package.json && \
     npm install --no-save typescript@^5.8.3 @types/node@^22.15.30 @types/express@^5.0.3 \
         @modelcontextprotocol/sdk@1.30.0 dotenv@^16.5.0 express@^5.1.0 axios@^1.18.1 \
-        n8n-workflow@2.34.3 uuid@^11.1.1 @types/uuid@^10.0.0 \
+        n8n-workflow@2.35.2 uuid@^11.1.1 @types/uuid@^10.0.0 \
         openai@^4.77.0 zod@3.25.76 lru-cache@^11.2.1 @supabase/supabase-js@^2.57.4
 
 # Copy source and build

README.md

@@ -4,18 +4,18 @@
 [![GitHub stars](https://img.shields.io/github/stars/czlonkowski/n8n-mcp?style=social)](https://github.com/czlonkowski/n8n-mcp)
 [![npm version](https://img.shields.io/npm/v/n8n-mcp.svg)](https://www.npmjs.com/package/n8n-mcp)
 [![codecov](https://codecov.io/gh/czlonkowski/n8n-mcp/graph/badge.svg?token=YOUR_TOKEN)](https://codecov.io/gh/czlonkowski/n8n-mcp)
-[![Tests](https://img.shields.io/badge/tests-5418%20passing-brightgreen.svg)](https://github.com/czlonkowski/n8n-mcp/actions)
-[![n8n version](https://img.shields.io/badge/n8n-2.34.4-orange.svg)](https://github.com/n8n-io/n8n)
+[![Tests](https://img.shields.io/badge/tests-6524%20passing-brightgreen.svg)](https://github.com/czlonkowski/n8n-mcp/actions)
+[![n8n version](https://img.shields.io/badge/n8n-2.35.3-orange.svg)](https://github.com/n8n-io/n8n)
 [![Docker](https://img.shields.io/badge/docker-ghcr.io%2Fczlonkowski%2Fn8n--mcp-green.svg)](https://github.com/czlonkowski/n8n-mcp/pkgs/container/n8n-mcp)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.com/deploy/n8n-mcp?referralCode=n8n-mcp)
 
-A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Deploy in minutes to give Claude and other AI assistants deep knowledge about n8n's 2,414 workflow automation nodes (831 core + 1,583 community).
+A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Deploy in minutes to give Claude and other AI assistants deep knowledge about n8n's 2,541 workflow automation nodes (832 core + 1,709 community).
 
 ## Overview
 
 n8n-MCP serves as a bridge between n8n's workflow automation platform and AI models, enabling them to understand and work with n8n nodes effectively. It provides structured access to:
 
-- **2,414 n8n nodes** - 831 core nodes + 1,583 community nodes (1,340 verified)
+- **2,541 n8n nodes** - 832 core nodes + 1,709 community nodes (1,441 verified)
 - **Node properties** - 99% coverage with detailed schemas
 - **Node operations** - 66.5% coverage of available actions
 - **Documentation** - 86% coverage from official n8n docs (including AI nodes)