Agent Context Window Manager Connector for AI agents.
3 live capabilities
Manage token limits and conversation health for long-running AI sessions
Waiting for input…
Why people use Agent Context Window Manager
Stop context bloat with Agent Context Window Manager
This MCP changes that by giving you a way to manage the conversation's health. Instead of hitting a wall, you can see exactly how much room is left and proactively shrink the history. You get to decide what stays and what gets summarized, keeping the agent focused on the task at hand without the constant friction of context overflow.
What Vinkius changes
You get a precise way to prevent your AI from getting 'stupid' due to context bloat.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,400+ Connectors
- Real-world use case 01
Managing long coding sessions
When a coding agent has read dozens of files, use plan_compression to summarize the early architecture discussions so it doesn't forget the core requirements.
- Real-world use case 02
Debugging agentic loops
If an agent is stuck in a loop, use analyze_fragmentation to see if massive capability outputs are drowning out the original goal.
- Real-world use case 03
Cost-conscious development
Use calculate_remaining_context to track how close you are to the limit, preventing expensive re-runs of massive context windows.
Complete set · 3capabilities
The complete Agent Context Window Manager capability set.
These are the exact actions your AI can choose when you ask it to work with Agent Context Window Manager.
01—03
3 capabilities in this set.
Part of 3 available through Agent Context Window Manager.
- 01 Capability
Analyze fragmentation
Checks if capability outputs are crowding out the actual conversation. It helps you see if your agent is becoming too capability-heavy.
- 02 Capability
Calculate remaining context
Tells you exactly how many tokens are left in the current window. Use this to avoid sudden context overflows.
- 03 Capability
Plan compression
Creates a strategy to shrink your chat history. It helps you decide what to keep and what to summarize.
Set up in minutes
One URL. Then ask Agent Context Window Manager to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Agent Context Window Manager from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Agent Context Window Manager, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Agent Context Window Manager for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Agent Context Window Manager URL.
- Step 03
Save and start
Save the connection and enable Agent Context Window Manager in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-context-window-manager": {
"url": "https://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Agent Context Window Manager
Open Agent mode in chat and ask: "Using Agent Context Window Manager, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-context-window-manager": {
"url": "https://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Agent Context Window Manager
Ask Copilot: "Using Agent Context Window Manager, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-context-window-manager": {
"url": "https://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Agent Context Window Manager
Open Cascade and ask: "Using Agent Context Window Manager, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"agent-context-window-manager": {
"url": "https://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Agent Context Window Manager
Ask Cline: "Using Agent Context Window Manager, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add agent-context-window-manager --transport http "https://edge.vinkius.com/vk_preview_BPghAk5oXGL3BsDHMefc5S6Sn9VO570vQFs9Cbiv/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Agent Context Window Manager
Ask Claude: "Using Agent Context Window Manager, show me...". 3 tools are ready
Where the request belongs
Work Agent Context Window Manager can move forward.
This is for anyone building or managing complex, multi-turn interactions where the history is too large to ignore.
AI Engineer
Managing long-running agentic loops that perform heavy capability use.
Prompt Engineer
Optimizing how much context is passed to models to save on costs and improve accuracy.
Product Manager
Ensuring AI-driven features don't break or hallucinate during extended user sessions.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
Agent Resource Contention Calculator
High-precision queueing theory calculator for multi-agent system performance.
Prompt Distillation Calculator
Calculate efficiency, quality, and cost of prompt distillation.
Ramen Shop Queue Estimator
Predict wait times and congestion for Japanese-style ramen shops using queueing theory.
Product Empties Predictor
Predict when your skincare or household products will run out based on usage patterns.
Agent Handoff Protocol Calculator
Model the efficiency, stability, and performance impact of multi-agent handoffs.
Conversation Budget & Escalation Engine
A deterministic engine for managing LLM conversation lifecycles and predicting escalation triggers.
Bring your own AI
Change the model, client or framework. Keep Agent Context Window Manager connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Agent Context Window Manager.
The practical details behind the request, access and result.
How can Agent Context Window Manager prevent my AI from forgetting things?
It allows you to monitor your token usage and proactively compress your conversation history. By summarizing old parts of the chat, you keep the most important information within the active window.
Can I use Agent Context Window Manager with Claude or Cursor?
Yes, as long as your client is MCP-compatible, you can connect this to Claude, Cursor, Windsurf, and VS Code to manage your conversation health.
How does Agent Context Window Manager help with token costs?
By helping you plan when to compress or prune your history, it prevents you from sending massive, redundant blocks of text to your AI client, which keeps your token usage efficient.
What does it mean if my conversation is 'Capability Heavy'?
This means the data returned by your capabilities is taking up most of your context window, leaving very little room for the actual conversation. You can use this to decide when to clear out old capability results.
Does Agent Context Window Manager work for long coding sessions?
Absolutely. It is specifically designed for long-running tasks where the history of file reads and code edits can quickly overwhelm the AI's memory.
How does the system calculate remaining tokens?
The calculate_remaining_context capability subtracts system prompts, capability definitions, conversation history, and multimodal tiles from the total window size.
What is context fragmentation?
Fragmentation is the ratio of tokens used by capability calls and outputs compared to the actual conversational text. You can monitor this with analyze_fragmentation.
When should I trigger a compression event?
A compression event is recommended when usage reaches the Yellow Tier (70-80%) and is mandatory at the Orange Tier (80-95%).
One connection away
Give your agent a direct line to Agent Context Window Manager.
Connect Agent Context Window Manager once. Keep it beside 6,400+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available