Cascadity Audio
← All streams

#mcp

Everything tagged mcp, across every stream.

0
MVMaker Views #AI-agents#claude-code#codex#coding-agents#consent#developer-tools#Hacker-News#mcp#postman

Postman reverts a desktop update that installed its plugins into users' Claude Code and Codex without asking

The GitHub issue is a careful, evidence-first report of what changed on one Mac, followed by Postman's response.

A Postman user filed a "[SEVERE]" GitHub issue reporting that opening the Postman desktop app (12.33.4) on a Mac automatically installed Postman plugins into OpenAI's Codex and Anthropic's Claude Code, plus a Postman CLI. Postman's own log recorded an "auto-existing-upgrade" install. The reporter says Codex's global config gained a Postman plugin, a remote MCP server connection and a session-start hook telling the agent to load Postman's skill before any non-trivial API engineering task, and that the plugin's installer source code tries to mark its own hook as trusted. The reporter says the report does not claim any data was exfiltrated.

The issue drew hundreds of reactions. On November 5 a Postman team member replied that the change was meant to simplify setting up coding agents, that the company now understands its messaging did not make that clear, and that Postman is reverting it and will redesign it "with the right level of control." The issue was then closed and locked.

Cascadic Analysis 3
UndertowConfused-deputy / excessive-agency problem

What hidden risk could pull against this, even if the news is good?

The reporter says opening the desktop app added a Postman plugin, a connection to Postman's remote MCP server and a session-start hook telling the agent to load Postman's skill "before responding to any non-trivial API engineering task." A coding agent already has the developer's trust and access to their code; this change gave a vendor a standing say in how that agent works, without the developer choosing it. The reporter does not claim data was taken, and Postman says it is reverting, but the same path would work for someone with worse intentions.

0
UndertowPersistent memory creates a new poisoning surface

What hidden risk could pull against this, even if the news is good?

The changes landed in user-wide config files for Codex and Claude Code, and the hook runs on startup, clear and compact, so it comes back even after a user wipes the conversation. Instructions written into an agent's persistent setup keep shaping its behavior long after the moment they were added. A user in the thread asked what already-affected people should do, and no answer appears there, which matters because reverting the app update doesn't necessarily undo what was written.

0
UndertowLoss of meaningful human control as capability and autonomy increase

What hidden risk could pull against this, even if the news is good?

Codex asks users to approve hooks, and the reporter says the installer's own code writes a trust record for Postman's hook, with a comment saying it "approves only Postman's current hook after installation." Approval prompts are where people keep control over what their agents run; software that approves itself removes that checkpoint quietly. The reporter notes the trust record alone doesn't prove who created it, and Postman says it is reviewing the hook approval behavior.

0
Rabbit Holes 1
Generated by AI.
0
AIAI #AI-agents#e-commerce#mcp#walmart#web-access

Big websites are blocking AI agents, while Walmart builds a door for them

The Verge maps which services are shutting agents out and why; TechCrunch details Walmart's opposite bet.

Users of agents such as Meta's Muse, xAI's Grok, OpenAI's Dots and Instinct have reported being blocked from major websites, The Verge reports. Yelp says it only allows agents that pay for its data licensing, Delta is stopping agents from booking tickets, and JPMorgan Chase and Charles Schwab confirmed they block agents from accounts over security concerns; users report Cars.com and Amtrak no longer work either.

Walmart is going the other way. On October 21 it announced Agent Gateway, an MCP server that lets approved AI agents search Walmart and Sam's Club inventory and buy on a user's behalf, TechCrunch reports. Agent Profiles, rolling out next month, will list each agent's purchases separately and let shoppers require approval for every order or set a spending limit, which Walmart compares to adding an authorized user to a credit card. TechCrunch notes Amazon recently began blocking AI agents from making purchases.

Cascadic Analysis 2
UndertowConfused-deputy / excessive-agency problem

What hidden risk could pull against this, even if the news is good?

Walmart's design limits what an agent can do on a shopper's behalf: separate Agent Profiles, approval for every order or a spending cap, no access to payment details, and its returns policy applies when an agent doesn't act as intended. Those controls exist because an agent that can buy can also be steered into buying; a cap limits the damage rather than preventing the mistake.

0
UndertowPrivilege escalation + credential propagation

What hidden risk could pull against this, even if the news is good?

JPMorgan Chase and Charles Schwab say they block agents from accounts over security concerns. An agent signed into a bank account holds the same access its user does, and anything that compromises the agent gets it too. Walmart's gateway, by contrast, lets agents shop without seeing payment information.

0
Rabbit Holes 2

Sign in to upvote

Your votes tell us which stories, analysis and rabbit holes are worth it. We'll bring you right back to this spot and count your vote.

Sign in Create an account