LLMKit

io.github.OlsOls4/llmkit

Token counting, RAG chunking, truncation, HTML to Markdown and JSON repair

View repository →Homepage →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Cursor · HTTP clients.

{
  "mcpServers": {
    "llmkit": {
      "url": "https://llmkit-token-counter-rag-chunker-json-repair.p.rapidapi.com/mcp"
    }
  }
}

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
AI & ML
Version
1.1.0
Registry
active
Published
10/14/2026

Remotes

  • streamable-httphttps://llmkit-token-counter-rag-chunker-json-repair.p.rapidapi.com/mcp

More AI & ML servers

Browse all AI & ML →

OpenNodes

opennodes-io

Discover verified AI inference nodes, get the best node+model per task, pre-price chains.

AI & MLAdded 2 weeks ago

io.github.paiml/pmcp

paiml

High-quality Rust SDK for Model Context Protocol (MCP) with full TypeScript SDK compatibility

AI & MLAdded 1 week ago

io.github.pdaxt/pqvault

pdaxt

Post-quantum secrets manager for AI agents. ML-KEM-768 + X25519 + AES-256-GCM.

AI & MLAdded 8 months ago

Skimless

pedroofrancaa

Reading order for big pull requests: what to read first, what can wait. Offline, no model.

AI & MLAdded 1 month ago

MCP Cost Optimizer

petrovicistefan

Local-first LLM cost analysis and model-switch savings estimates for AI agents.

AI & MLAdded 3 weeks ago

io.github.pgalyen1987/gate402-mcp

pgalyen1987

x402 pay-per-call agent APIs: LLM inference, Base trading data, SEC filings & scraping

AI & MLAdded 1 month ago

Add the badge to your site

Show visitors that LLMKit is listed here — it’s also the link we check for a free listing.

LLMKit — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-olsols4-llmkit?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="LLMKit — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![LLMKit — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-olsols4-llmkit?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.