3073 Model Context Protocol servers — searchable, rated, ready to install.
Local, payload-free AI cost visibility for agents. Query spend by model, route, or tagged work.
Traced LLM Proxy
Generate reproducible image, video, and audio assets with leading models and your own provider keys.
Compare LLM API and cloud compute pricing, estimate workload costs, pick a model within budget.
LLM Orchestration JWT Agent
Plan trips directly into TravelOwl from a conversation with Claude.
Compose and render video from one JSON template. Deterministic, runs locally, no generative model.
Ask Claude or ChatGPT about your own crypto trading: performance, patterns and behaviour.
Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.
Manage your Odichat WhatsApp/IG/FB inbox from Claude: conversations, contacts, pipeline, reports.
GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.
Get a used car's market-price range (min/max/median) by model and year from carsensor.net.
Remove the Claude text watermark by rewriting text, and strip C2PA/EXIF metadata from images.
Financial Modeling Prep API as MCP tools — quotes, statements, prices, and ~240 endpoints.
Public read-only discovery of agent, model, training, task, and verification opportunities.
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
Local, privacy-preserving PII toolkit over MCP — shape to the model, substance stays local.
Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.
Persistent, governed institutional memory for Claude Code — specs, decisions, learnings.
Animica chain data, free keyless AI inference, quantum randomness, x402 discovery, mining stats.
Search the Claude Code Ultimate Guide and machine-readable references from any MCP client.
BridgeNode — x402 pay-per-request AI inference. OpenAI-compatible API + MCP, Solana USDC, gas-free.
Real UK MOT failure data by car model and mileage, aggregated from official DfT test results.
MCP-native LLM councils for debates, juries, blind panels, refinement, and custom deliberation.
POST /mcp