by wfmedia
MCP security scanner - detect prompt injection in tool descriptions
npm:mcp-guardian · local package148/wkpublished 7 mo ago
Model access, evaluation and agent infrastructure.
MCP security scanner - detect prompt injection in tool descriptions
MCP server that loads ALTWEB signed context capsules into AI agents — verifies first, refuses unsigned, tampered, or untrusted context by default. Verify before you inject.
MCP Server Toolkit — create Model Context Protocol servers in minutes with tools, prompts, resources, auth, middleware, logging, metrics, CLI, and testing helpers.
A Model Context Protocol (MCP) server for OpenRouter API with Collective Intelligence - Multi-model consensus, ensemble reasoning, and collaborative problem solving
Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.
Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.
Model Context Protocol (MCP) server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.
Meta-MCP gateway: search, inspect and call any MCP server from the public registries.
101 tools for WooCommerce store management with field filtering and guided prompts.
MCP server that gives your coding agent on-demand access to thousands of community-vetted Claude Code skills - search Skillselion and load_skill a real SKILL.md (plus its scripts/refs) mid-task. Ranked by installs + GitHub stars. Works with Claude Code, C
MCP server exposing Tide operational guidance — canon, playbooks, skills, prompts, adapters, and scenarios for AI coding agents
Skill-discovery prompt builder for coding agents. Turns vague tasks into expert prompt text that searches local and ecosystem skills, recommends install/load steps, and tells the next agent which specialist skills to invoke and what evidence to collect. O
Metacognitive AI agent oversight: adaptive CPI interrupts for alignment, reflection and safety
Search 25,000+ meme templates and create shareable memes on memebo.at. Free, anonymous, no API key.
Stop shipping agents on vibes. Score every agent output for quality, safety, and cost.
Fail-closed MCP receipt middleware with exact-action binding, one-time consumption, strict receipt parsing, and escalation-only treatment of untrusted tool metadata.
Controlled A/B tests for agent SKILL.md files: blind grading, bootstrap confidence intervals, HELPS/PLACEBO/HARMS - effect size, not schema validation.
Guarded CLI and MCP client for JustHandled's x402 utility gateway
MCP server for interacting with EVM-compatible blockchains - supports 22 tools and 10 prompts across 60+ networks
MCP server for 1C:Enterprise — 32 tools across 11 modules: catalogs & documents CRUD, post/unpost, registers & accumulation balances, accounting, constants, batch ops, change-tracking, metadata discovery, shortcuts (+ 3 guided prompts) via OData 3.0. Basi