Cost-Controlled Tool Selector Connector for AI agents.
3 live capabilities
Optimize agentic capability selection for speed and accuracy
Waiting for input…
Why people use Cost-Controlled Tool Selector
Stop wasting compute with Cost-Controlled capability Selector optimization
This MCP turns that guesswork into a math problem. Instead of manually tweaking prompts to tell your agent which capability to use, you give it a set of constraints. It looks at the available options and picks the one that hits your accuracy target with the least amount of delay. You get predictable, repeatable performance every time.
What Vinkius changes
You get a mathematically sound way to choose the right capability for every task without manual tuning.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Reducing latency in high-frequency agent loops
An agent needs to process thousands of small requests.
- Real-world use case 02
Ensuring accuracy for high-stakes reasoning
When a user asks a complex legal question, the agent uses list_qualified_variants to ensure it only picks capabilities that meet a strict 0.
- Real-world use case 03
Cost-saving for massive scale deployments
A developer uses compare_variant_efficiency to prove that a slightly less accurate capability is actually more efficient for their specific high-volume use case.
Complete set · 3capabilities
The complete Cost-Controlled Tool Selector capability set.
These are the exact actions your AI can choose when you ask it to work with Cost-Controlled Tool Selector.
01—03
3 capabilities in this set.
Part of 3 available through Cost-Controlled Tool Selector.
- 01 Capability
Compare variant efficiency
Compares how much accuracy you get for every millisecond spent between two capability options. It helps you decide if a more expensive capability is actually worth the extra time.
- 02 Capability
List qualified variants
Shows you every capability that is capable of meeting a specific accuracy target. It ignores cost to show you what is actually possible for the task.
- 03 Capability
Select optimal variant
Finds the single best capability variant based on your specific efficiency and accuracy constraints. It picks the fastest option that still hits your quality bar.
Set up in minutes
One URL. Then ask Cost-Controlled Tool Selector to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Cost-Controlled Tool Selector 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_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Cost-Controlled Tool Selector for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector URL.
- Step 03
Save and start
Save the connection and enable Cost-Controlled Tool Selector in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"cost-controlled-tool-selector": {
"url": "https://edge.vinkius.com/vk_preview_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector
Open Agent mode in chat and ask: "Using Cost-Controlled Tool Selector, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"cost-controlled-tool-selector": {
"url": "https://edge.vinkius.com/vk_preview_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector
Ask Copilot: "Using Cost-Controlled Tool Selector, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"cost-controlled-tool-selector": {
"url": "https://edge.vinkius.com/vk_preview_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector
Open Cascade and ask: "Using Cost-Controlled Tool Selector, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"cost-controlled-tool-selector": {
"url": "https://edge.vinkius.com/vk_preview_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector
Ask Cline: "Using Cost-Controlled Tool Selector, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add cost-controlled-tool-selector --transport http "https://edge.vinkius.com/vk_preview_EcT3WLB2s90OH9keGSnCvbvlarTyEOUA0zFmootW/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 Cost-Controlled Tool Selector
Ask Claude: "Using Cost-Controlled Tool Selector, show me...". 3 tools are ready
Where the request belongs
Work Cost-Controlled Tool Selector can move forward.
This is for engineers and researchers building autonomous agents where latency and API costs actually matter.
AI Engineer
Optimizing agentic workflows to reduce latency and token spend during production runs.
MLOps Engineer
Managing the resource allocation and cost-efficiency of large-scale model deployments.
Agent Developer
Building complex multi-step reasoning loops that need to switch between fast and precise capabilities.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
Receiving Dock Capacity Calculator
Analyze dock capacity, identify throughput bottlenecks, and optimize docking infrastructure.
Subscription Cashflow Aligner
Find the safest day of the month to set subscription billing dates and minimize overdrafts.
First-Fit Decreasing Cutter
Optimize material usage by calculating the most efficient cutting plans for raw stock.
Claude Verbosity Optimizer
A deterministic engine to detect and compress verbose LLM outputs to preserve context window budget.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep Cost-Controlled Tool Selector 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 Cost-Controlled Tool Selector.
The practical details behind the request, access and result.
How can I reduce my agent's latency with Cost-Controlled Capability Selector?
You can use the selection logic to identify the fastest capability variant that still meets your minimum accuracy requirements, preventing your agent from using unnecessarily slow models.
Does Cost-Controlled Capability Selector help with API costs?
Yes. By selecting the most efficient capability variant based on your constraints, you avoid using high-cost, high-precision models for simple tasks that don't require them.
Can I use Cost-Controlled Capability Selector with any AI client?
Yes, this MCP works with any compatible client like Claude, Cursor, or Windsurf, allowing your agent to make better decisions within those environments.
How does Cost-Controlled Capability Selector decide which capability is best?
It uses a deterministic approach to compare the execution time and accuracy of available options against the specific thresholds you define for a task.
Is Cost-Controlled Capability Selector useful for high-accuracy tasks?
Absolutely. You can use it to filter out all capabilities that don't meet a strict accuracy threshold, ensuring your agent only uses capable capabilities for sensitive work.
How does the capability decide which variant is best?
The engine first filters all variants to find those that meet the min_accuracy requirement. From that subset, it selects the variant with the lowest estimated_cost_ms. If costs are tied, it selects the one with higher accuracy.
Can I see all capabilities that meet my accuracy needs?
Yes, you can use the list_qualified_variants capability to retrieve a list of all available variants that satisfy your minimum accuracy threshold.
What happens if no capability meets the accuracy requirement?
If no capability variants meet the specified min_accuracy, the select_optimal_variant capability will return an error indicating that no suitable variant was found.
One connection away
Give your agent a direct line to Cost-Controlled Tool Selector.
Connect Cost-Controlled Tool Selector once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available