2277 Model Context Protocol servers — searchable, rated, ready to install.
Escáner GEO: analiza si una web es legible y citable por ChatGPT, Perplexity, Gemini y Claude.
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
Local privacy-first tools: redact secrets, decode JWTs, compare LLM costs. No network calls.
Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.
Interface observations and explicit GOMS/KLM, Fitts, Hick–Hyman and cognitive walkthrough models.
Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.
Robert Blust: One model, true everywhere
Every EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.
Eqvitta MCP: GST billing, ledgers, invoices, stock and financial reports for Claude.
MCP server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils.
Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
Redact PII from text before it reaches a model. Nothing stored, no third-party AI.
Simulate farms, validate GardenScript and compare policies with Rust. No outbound LLM calls.
A coding and development harness on local models or hosted APIs, for code, review, research and ops.
Draft, check and schedule posts to your connected social accounts from Claude, ChatGPT or Cursor.
Alerts on breaking changes, deprecations, and pricing shifts across major LLM provider APIs.
Synap (pool.linkrra.com/v1), Linkrra's OpenAI-compatible LLM API, as an MCP server.
Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.
Dead-man's switch for Anthropic API spend: kills the key the instant it crosses a limit you set.
Model Context Protocol (MCP) server for programmatic PowerPoint creation and editing
Run one LLM instruction over every row to classify, extract or summarise into new columns.
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
AI Model Experiments MCP ('Model Lab') — run the same prompts across many
POST /mcp