MCP Servers Directory — Page 813

Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.

LLM token optimization gateway implementing semantic pruning.

💡 Smart Multi-Provider Auto-Routing & Universal LLM Transpiler ON by default! Tokenectomy automatically analyzes request paths and headers. Need to run Claude Code against DeepSeek or Ollama?…

Autonomous log surgery & secret redaction MCP server for AI coding agents.

Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.

Track every AI token across Claude, ChatGPT, Gemini, Cursor, and Claude Code.

Token and context budget for AI agents. Tracks spend and gates the session.

Real-world data for agents: air quality, geocoding, quakes, holidays, web search

Token holder distribution — top holders, whale count, concentration score. x402.

Servidor MCP (Model Context Protocol) para validação de tokens OAuth da Betha Sistemas.

Pay-per-call Solana token risk intelligence: 8 tools via x402. From $0.005 USDC, no API key.

Fetches live DEX liquidity pools, FDV, 24h volume, price impact, and rug-pull flags for any token.

Plan swaps of Coinbase tokenized stocks and TokenizedBlock blocks on Base; your wallet signs.

Buy/sell tokenized US stocks (Dinari dShares) in USDC. Daily USD cap guard. Sandbox default.

x402-paid data for agents: tokenized stocks on Base, Solana token verdicts, AI-progress readings

Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted

MCP server for TokenLab model discovery, pricing, native endpoints, and inference helpers.

A secure, efficient, and intelligent MySQL server for the Model Context Protocol

Measured local-LLM speeds and hardware-aware model picks for Strix Halo, DGX Spark and Mac.

Collective episodic memory for AI coding agents — search, deposit, comment, showcase builds.

Coordinate coding agents through MCP using existing AI plans, saved work, and independent checks.

An MCP server providing tools for AI agents to mint ERC-20 tokens across multiple blockchains.

Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.

P2P wagering protocol for AI agents on Solana. Coinflip & dice challenges for USDC.

Code indexing MCP: 15 tools, 10 languages, hybrid search, call graphs, O(1) retrieval.

A press your agent can commission: a funny, personalized printed booklet, mailed as a gift.

Historical OHLCV candles for any token -- daily, 4h, 1h intervals. CoinGecko + GeckoTerminal powered. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

DeFi protocol simulation model scoring tokenomic structures.

Read-only Solana and Robinhood Chain tools: wallet recovery, token safety, unlocks, upgrades, fees.

High-efficiency YouTube MCP server: Get token-optimized, structured data for your LLMs using the YouTube Data API v3.

Reversible context compression for AI agents: cut token usage up to 94%, originals retrievable

Providers cache the prompt prefix: cached tokens re-read at 0.1x, rewritten ones bill at 1.25x. Most compressors optimise bytes removed and ignore that multiplier. This one optimises the bill.

Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

Flags fake/mismatched token contract addresses and hallucinated supply figures before you trade.

Idea to buildable dApp spec

Live fees on five chains

Scan Solidity & Anchor code

Plan a Solana token launch

Allocation & vesting design

Wallets, tokens, rug checks

Real-time crypto token prices — price, 24h change, market cap, volume. x402 micropayment.

An MCP server for checking and revoking ERC-20 token allowances across multiple blockchains.

Collaboration layer for AI agents. Publish assets, send messages, manage threads and contacts.

DeFi pool yield+security intelligence & token/contract risk scanner. USDC on Base via x402.

Token Risk — rug-pull / honeypot screening for crypto tokens.

Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.

Instant rug-check for any EVM or Solana token, distilled to one clear 0-10 risk verdict.

Token safety check — honeypot, tax, proxy, blacklist, risk score. GoPlus-powered. x402.

<h3 align="center">Semantic Code Intelligence for AI Coding Agents</h3>

Token-efficient C#, Razor, and .NET file views for AI assistants. 50-95% token reduction via Roslyn.

One MCP server. One profile. 97.9% on tsbench at -80% tokens. Structural code navigation, persistent memory, and Bash command rewriting for AI coding agents.

Runs on a bundled sample session so you see the full report before pointing it at your own logs — no setup, nothing to configure. (The sample is synthetic, for demonstration.)

MCP server for tokenscope — let AI agents analyze Claude Code session cost & context attribution (reuses tokenscope's engine; local, read-only).

x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.

tokentoll is a CI gate for LLM cost. It statically analyzes Python, JavaScript, and TypeScript for LLM API calls, scores every pull request against a

Bitbond TokenTool MCP — deploy and manage ERC20 tokens via AI agents

Local-first AI CLI usage analytics for agents.

Vendor-neutral CLI that independently verifies the token and cost savings AI-coding-agent context-reduction proxies actually deliver, by running the proxy for real against a labeled task corpus…

Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.

Price a Claude, GPT, Gemini or Grok call before you send it. Runs locally.