All MCP Servers — Page 2

Search and get install details on MCP servers directly from your agent -- a unified marketplace index.

Local-first context-control plane and MCP server for AI coding agents. Selects evidence under a token budget, keeps omitted content byte-exactly recoverable via CCR handles, and emits auditable Context Receipts. Verify locally (no API key): entroly verify-claims (12/12 pass). Savings are workload-dependent. Apache-2.0.

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

Buy advertising outcomes from your AI assistant: Telegram channel subscribers and website traffic, billed per verified result from a prepaid balance. The assistant spends within a mandate you set and can never fund the balance or withdraw money.

Production-ready Shadcn dashboard kit built for modern teams

Free, keyless real-time air quality (US AQI, PM2.5, PM10, ozone, NO2, SO2, CO) for any city.

Free, keyless postal/ZIP code lookup: place names, state/region, and coordinates for any supported country.

Zero-config SEO and GEO checker: 21 technical-SEO and generative-engine checks for a live site.

Deterministic policy firewall for AI agents that evaluates tool calls before execution and returns ALLOW, WARN, or BLOCK decisions.

Independent, reproducible benchmark harness for agent-memory backends.

Proof-backed implementation memory for coding agents — search and retrieve verified primitives via HTTP API, MCP adapter guide included.

Web-intelligence API gateway: 17 APIs as 20 MCP tools for SEO and scraping. Pay-per-call via USDC.

Renders Mermaid diagram syntax to PNG or SVG images with configurable themes and backgrounds.

AI agent observability with deterministic record/replay for debugging agent failures.

Lets your AI agent place real phone calls from your own verified number — with transcripts, recordings, and enforced AI disclosure.

MCP server for US building-permit data — free metro/trade lead previews and address permit-history lookups, no signup; full datasets and settlement-oracle attestations billed per call via x402 (USDC on Base).

Ask your agent for an app and Homespun deploys it: its own URL, magic-link sign in, a shared database, per-role permissions and file uploads.

Keyless MCP server giving AI agents CVE lookups (NVD), package-vulnerability checks (OSV) and dependency-manifest audits. No API key; free tier.

A tiny MCP server that lets you praise your AI by typing ㅊㅊ (or cc). K-drama & Hollywood style compliments, 36 lines, ko/en. A Korean developer's experiment in AI kindness — built with an ensemble of AIs. Install: npx -y heungbu26-mcp

Keyless MCP server giving AI agents npm/PyPI/crates.io package intel: metadata, versions, popularity, dependencies, health and advisories. Free tier.

Smart personal finance companion to track spending, manage investments, and monitor budgets with AI-powered insights.

Drive iOS simulators from Claude Code, Cursor or Codex by accessibility label instead of screenshot-and-tap-coordinates, with leases and a warm pool so multiple agents can share one Mac.

Hosted push-notification service for AI agents: one MCP tool call sends the owner a content-free push notification to their phone, with an optional context_url to tap through.

The Mac window manager your agent can drive. Snap zones, saved workspaces, keep-awake, screenshots and on-device OCR — 19 MCP tools bridging to a loopback API on your own machine. No account, no cloud, no telemetry.

Browser automation framework with savable auth profiles and compliance options viable to enterprise developments.

Narrow code retrieval for coding agents — outlines, symbol bodies, dependency graphs, and persistent memory instead of whole-file reads.

Shows what is consuming your agent's context window before the conversation starts — skill descriptions ranked by token cost, duplicate skills, memory files and their imports, and every configured MCP server.

AI that builds and runs your business — 24/7

AI that builds and runs your business — 24/7

Shows what a checkout you did not write tells your agent to do before you run it — instruction files and their imports, hook commands wired to agent events, MCP servers the repo declares, and the skills and subagents it ships.