How does this MCP prevent mixing up different projects?

It uses deterministic hashing to create a unique identity for each project. This ensures that memories saved for Project A are never used when you are working in Project B.

What kind of information can I save?

You can save anything from build commands and environment variable requirements to specific debugging patterns and coding conventions.

Which AI clients can use this?

This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

Do I need to manually tell the AI to remember things?

You can use the index_learning capability to explicitly save an insight, or your agent can trigger it to persist important patterns it discovers.

How does the search function work?

The MCP uses keyword matching and Jaccard similarity to find the most relevant pieces of information from your stored memories.

How does the system ensure memories don't leak between projects?

The system uses a unique project hash generated from your CLAUDE.md and directory structure. This ensures that index_learning only stores and retrieves memories belonging to the specific project context.

Can I filter my search by specific categories?

Yes, when using query_memories, you can provide a categoryFilter to narrow down results to specific groups like build_commands or project_conventions.

What happens if I save a duplicate learning?

The system automatically detects near-duplicates. If a new learning has a Jaccard similarity greater than 0.9 with an existing one, it updates the existing entry instead of creating a new one.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Claude Session Memory Indexer to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Stop repeating yourself to your AI client every time you start a new session.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Claude Session Memory Indexer.

01
Get project context
This capability identifies the unique fingerprint of your current project. It ensures all saved memories stay isolated to the specific codebase you are working on.
02
Index learning
This capability saves a new insight or pattern into your long-term memory store. Use it to persist commands or architectural decisions you want the AI to remember later.
03
Query memories
This capability searches through your saved insights to find relevant past learnings. It uses similarity matching to pull up the right context based on your current question.

Real work

What teams actually run

Build Command Recall

The AI remembers the exact npm or make commands needed for a specific repo.

Debugging History

Your agent recalls how a specific error was fixed in a previous session.

Style Enforcement

The AI maintains consistent file naming and code style based on indexed project rules.

Environment Setup

The AI remembers which environment variables are required for a project to run.

One connector, every AI

Claude Session Memory Indexer works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Claude Session Memory Indexer to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

919ms average. Fast in production.

Claude Session Memory Indexer is checked daily against the live service.

Daily averagePeak 1149ms

Oct 3Today

Fastest day: 726ms
Slowest day: 1149ms
14-day trend: Stable-2%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Claude Session Memory Indexer, so you can see the experience inside your AI.

It does not authenticate your account with Claude Session Memory Indexer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Claude Session Memory Indexer Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_BjVkHByUnS0ST7LAlvTWGv4MSyAsDF6XkgfthZwR/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Claude Session Memory Indexer capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "claude-session-memory-indexer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_BjVkHByUnS0ST7LAlvTWGv4MSyAsDF6XkgfthZwR/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Claude Session Memory Indexer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Claude Session Memory Indexer owners hand off.

Software engineers and developers who work in complex, multi-repo environments and want their AI capabilities to stay informed.

01
Backend Engineers
They hand off environment configurations and database connection patterns to the AI.
02
Frontend Developers
They save UI component conventions and build scripts for the AI to use.
03
DevOps Engineers
They index deployment commands and infrastructure patterns to maintain consistency.

FAQ

Questions Claude Session Memory Indexer owners ask.

01
How does this MCP prevent mixing up different projects?
It uses deterministic hashing to create a unique identity for each project. This ensures that memories saved for Project A are never used when you are working in Project B.
02
What kind of information can I save?
You can save anything from build commands and environment variable requirements to specific debugging patterns and coding conventions.
03
Which AI clients can use this?
This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
04
Do I need to manually tell the AI to remember things?
You can use the index_learning capability to explicitly save an insight, or your agent can trigger it to persist important patterns it discovers.
05
How does the search function work?
The MCP uses keyword matching and Jaccard similarity to find the most relevant pieces of information from your stored memories.
06
How does the system ensure memories don't leak between projects?
The system uses a unique project hash generated from your CLAUDE.md and directory structure. This ensures that index_learning only stores and retrieves memories belonging to the specific project context.
07
Can I filter my search by specific categories?
Yes, when using query_memories, you can provide a categoryFilter to narrow down results to specific groups like build_commands or project_conventions.
08
What happens if I save a duplicate learning?
The system automatically detects near-duplicates. If a new learning has a Jaccard similarity greater than 0.9 with an existing one, it updates the existing entry instead of creating a new one.

Explore

More in Productivity

Connect Claude Session Memory Indexer to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Get project context

Index learning

Query memories

What teams actually run

Build Command Recall

Debugging History

Style Enforcement

Environment Setup

Building your own app? The connector is yours to use.

Claude Session Memory Indexer Connector

Claude Desktop

Backend Engineers

Frontend Developers

DevOps Engineers

How does this MCP prevent mixing up different projects?

What kind of information can I save?

Which AI clients can use this?

Do I need to manually tell the AI to remember things?

How does the search function work?

How does the system ensure memories don't leak between projects?

Can I filter my search by specific categories?

What happens if I save a duplicate learning?

Knowledge Management ROI Calculator AI Connector

Claude Context Window Budget Tracker AI Connector

Logseq (Knowledge Management) AI Connector

Mem AI (Knowledge Workspace) AI Connector

Suggestions

Memory Context Priority Pruner AI Connector

Memory Context Window Pruner AI Connector

Context Cache Invalidation Detector AI Connector

Agent Memory Hierarchy Calculator AI Connector