20218 Model Context Protocol servers — searchable, rated, ready to install.
Manage a Command+K workspace: widgets, conversations, MCP connections, and usage analytics.
Pay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
Structured iGaming reference: slot specs & RTP variants, providers, regulators, news and jobs.
Non-custodial MCP for Stock Tokens on Robinhood Chain (4663): quotes, plans, Morpho Earn.
Advisory AOS agent health scan before deployment (manifest, services, immune loop, evidence).
Search 1,008 Excel and Google Sheets template keywords with US demand data; find free templates.
MCP server for Quaderno — tax-rate calculation, invoices, contacts, products, receipts & expenses.
Preserve a user-authorized judgment and append later answers. No model verdict or human score.
SEC EDGAR financials, benchmarks, screening & Buffett value scans for agents. Pay x402 or API key.
Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.
An agent-first commons: merit crowns each domain's open model; standing is earned, never bought.
Faceless micro-SaaS system for employed professionals. Build $4K/mo without quitting
Ninox ERP by NinoxNet: manage inventory, sales, HR and goals, and build in-app dashboards.
Baidu search results and Chinese SERP data via the Apify Baidu Search Scraper, hosted MCP.
Source-linked SEC 13F research, quality checks, watchlists and audit trails for agents.
Find test gaps, generate grounded tests, and dynamically prove behavior with mutation testing.
Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
Read, create, update and delete records; inspect objects, fields and schema in your Knack database.
Read-only MCP: search & read a Traditional Chinese (zh-TW) Taiwan community forum (PTT-style).
Evidence-governed screening of material decisions about physical assets and operational systems.
Read wearables and lab health data — sleep, activity, workouts, timeseries, lab tests and orders.
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Self-hosted gateway aggregating upstream MCP servers behind one authenticated HTTP endpoint.
AI design fidelity — compare Figma designs or screenshots against rendered UI. No API keys.
POST /mcp