PulseAugur
EN
LIVE 22:51:55

Cordon adds audit logging and gating for n8n MCP tool calls

Cordon is a new open-source gateway designed to provide audit logging for n8n workflows that interact with MCP tools. It sits between the n8n client and the MCP server, logging every tool call, its arguments, and the response. This visibility helps identify issues like agent loops or unexpected tool usage, which are not detailed in n8n's default execution logs. Cordon also offers policy-based gating, allowing users to block or pause potentially dangerous tool calls before they are executed. AI

IMPACT Enhances visibility and control for AI agents using external tools within n8n workflows.

RANK_REASON This is a new open-source tool release that adds functionality to an existing workflow product.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Cordon adds audit logging and gating for n8n MCP tool calls

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a new open-source tool release that adds functionality to an existing workflow product.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
121 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · Marco Arras ·

    Audit logging for n8n workflows that call MCP tools

    <p>If you run an n8n workflow that calls MCP tools, here's something you've probably hit. The execution log shows the MCP Client Tool node ran, but it doesn't show what the agent asked the tool to do, or what it got back.</p> <p>That's a gap. If the agent loops, or hits a tool yo…