Use Token Counter and Budget Enforcer with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Estimates token usage and enforces strict cumulative budget limits for AI agents.
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.
Complete set · 3 capabilities
The complete Token Counter and Budget Enforcer capability set.
These are the exact actions your AI can choose when you ask it to work with Token Counter and Budget Enforcer.
01-03
3 capabilities in this set.
Part of 3 available through Token Counter and Budget Enforcer.
- 01
Estimate tokens
Calculates the estimated token count for a provided text string
- 02
Track and enforce usage
Updates the cumulative usage for an agent and a conversation, then checks against set limits
- 03
Get usage summary
Retrieves current cumulative totals without consuming new tokens
Observed, not estimated
821ms average. Fast in production.
Token Counter and Budget Enforcer is checked daily against the live service.
- Fastest day
- 690ms
- Slowest day
- 929ms
- 14-day trend
- Slowing+6%
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 Token Counter and Budget Enforcer, so you can see the experience inside your AI.
It does not authenticate your account with Token Counter and Budget Enforcer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Token Counter and Budget Enforcer Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_Fntor1z8zuXrJce6K2HdextT8uXupjEA6h8NsXAn/mcpClaude 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 — Token Counter and Budget Enforcer capabilities are ready to use.
{
"mcpServers": {
"token-counter-and-budget-enforcer-mcp": {
"url": "https://edge.vinkius.com/vk_preview_Fntor1z8zuXrJce6K2HdextT8uXupjEA6h8NsXAn/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
FAQ
Questions Token Counter and Budget Enforcer owners ask.
- 01
How are tokens estimated?
Tokens are estimated using a deterministic character-to-token ratio: approximately 4 characters per token for English text and 3.5 characters per token for code blocks.
- 02
Can I set different limits for agents and conversations?
Yes. You can use track_and_enforce_usage to apply specific limits for both the unique agent identifier and the specific conversation identifier.
- 03
How do I check my current usage?
You can use the get_usage_summary capability to retrieve the cumulative token totals for a specific agent or conversation without consuming any new tokens.
Explore
More in Utility
Token Count Estimator AI Connector
Deterministic LLM token estimation using character-based heuristics.
ViewChar-to-Token Estimator AI Connector
Predict token usage for different LLMs using language-specific character ratios.
ViewURL and Email Token Detector AI Connector
Detect URLs and emails to calculate potential LLM token savings.
ViewPrompt Length Classifier AI Connector
Estimate token usage and context window saturation.
View
Suggestions
LLM Token Counter AI Connector
Calculate exact and estimated token counts for GPT-4, GPT-4o, Claude, and Llama models.
ViewAI Token Counter AI Connector
Give AI Agents self-awareness of context limits. Count exact OpenAI/Claude tokens local to prevent fatal API t
ViewDeterministic Timeout Enforcer AI Connector
Prevents agent hang-ups by enforcing strict execution time boundaries and token budgets.
ViewLangfuse (LLM Tracing & Evals) AI Connector
Monitor LLM apps via Langfuse — track traces, manage prompt templates, and audit evaluation scores.
View
