Skip to content
kc@kumarChandrachooda.com:~$ cd /policy/connected-ai && read --section="top" 0%
Policy

Connected AI and the MCP server

When you add this site to your own assistant, what your assistant can read, and what each side sees.

Version 1 Effective 08 Nov 2026 Under review

What the connector is

The site runs an MCP server at kumarchandrachooda.com/mcp. If you add it to Claude, ChatGPT or another assistant, your assistant can search the blog, list its series, read a post's summary with a link to the post, and find the CV a visitor can download, where the site offers one. It never gets a post's full text, only the summary and the link. It cannot see drafts, accounts, the CV editions I share with a pass holder, or anything not already public. It needs no account and no sign-in.

What the site sees

The site sees the requests your assistant sends. They say which tool it called, what it searched for, your IP address and the name your assistant gives itself. The site answers them. Its log, kept 30 days, records which tool your assistant called and the name it gives itself, never what it searched for or your IP address.

To keep the service fair, the site counts each client's calls. It counts them under a salted hash of your IP address and your assistant's name, never the address itself, and each count is kept in a MongoDB database for one minute.

What your assistant's company sees

Whatever you say to your assistant, and what the site sends back. That is under your agreement with them, not under this site's.

Fair use

Twenty calls a minute per client. Do not use the connector to copy the archive wholesale.

Changes and contact

This page changes when the features do. Each version is dated, and earlier versions stay readable at their own address. Questions to kumarchandrachooda@gmail.com.

Which CV would you like?

Pick the one closest to the role. Each is two pages and carries the same facts.

Applied AI

Agentic AI & Cloud Engineer · multi-agent systems, RAG and MCP on AWS

Cloud & .NET

C#, .NET 10 and ASP.NET Core microservices on AWS and Azure · Terraform & AWS CDK

Data Engineering

AWS lakehouse · Kinesis, Glue (PySpark), Apache Iceberg, Lake Formation

Everything

All three domains, with the standout project from each