Search

Precision-first security scanner for Model Context Protocol servers.

MCP server for local retrieval over markdown documentation

An MCP server that lets your assistant consult other LLMs — ask them, compare their answers, and synthesize a conclusion.

Verified dev-error fixes sold per-lookup to AI agents on-chain. Free search; 3 free samples.

MCP server for public Ashby job boards. Resolve a company to its board, search its openings, read one posting and its pay. No API key required.

Deterministic calendar rhythm for agents: today, flow-month, sky, personal day.

MCP tools for package-risk: dependency maintenance, licence and advisory checks, paid per call via x402.

Camunda 7 / CIB Seven MCP module: operations tools, widget tools, and cockpit widgets.

Security-first MCP server for the SendGrid v3 API: two-phase sends, dry-run by default, recipient allowlists, rate limits, audit log, no BCC.

MCP server and Agent Plugin packaging for goal-acceptance criteria

MCP server for Opensolr — managed Apache Solr with hybrid BM25+kNN search, server-side embeddings, and RAG answers as agent tools

Zero-dependency MCP server + OAuth 2.1 authorization server in one package, for Claude, Gemini, and Codex connectors

Read-only runtime management panel for the official DeepSeek Harness MCP client: /mcp command, a Settings page MCP tab with connection status, recent errors, reconnect counts and tool inventory (sanitized for display), controlled enable/disable patch sugg

Ultra-fast Model Context Protocol (MCP) server for browser automation powered by Bun.WebView

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.

MCP server exposing the ClipMaster public API as tools for Claude and other MCP clients

Servidor MCP con las medidas de seguridad del ENS (Anexo II del RD 311/2022): Anexo II, Declaración de Aplicabilidad y alcance de auditoría, sin conexión

Four free MCP tools to check whether AI engines can find, read and recognise a website. No account, no API key, no LLM calls.

n8n community node for spintax templates — render, validate, lint what came out, measure pool uniqueness, generate N variants, protect foreign placeholders, and build LLM authoring/repair prompts. Use AI to create the template once; use spintax to generat

MCP server that inspects local GGUF and safetensors model files — architecture, quantization, parameters, tensors, and VRAM-fit estimates from headers only, without loading the model