Best Call AI Skills & MCP Servers

Your AI agent has read your codebase but still can't safely change it. unerr is a local guardrail that hands the agent the call graph and your rules at the moment it edits.

MCP server for AI agents to evaluate consequences before destructive actions. Analyzes Terraform plans, shell commands, and MCP tool calls.

MCP server that automatically summarizes and shares context across parallel Claude Code sessions

MCP server for AgentCall: phone numbers, SMS, OTP, AI voice (inbound + outbound) with 12 languages plus auto-detect, saved outbound agents per number (set/get/clear), retry-safe outbound calls via useSavedAgent + idempotencyKey for CSV runners, BYOK (brin

Deploy Claude Code, Codex & Antigravity (agy) CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Per-call model pinning, conversation continuation & intelligent pagination.

Turn editor chat history (Cursor, Claude Code, Windsurf, Copilot) into typed Markdown decisions + AGENTS.md rules — local-first, git-trackable, zero remember() calls.

Prism Coder — Cognitive memory + tool-calling intelligence for AI agents. Mind Palace persistent memory (BFCL Gold Certified, 100% Tool-Call Accuracy, 54 Agent Skills, Zero-Search HDC/HRR retrieval, HRR Semantic Drift Detection across BCBA/Coding/AAC doma

Yaw MCP -- MCP servers, managed. Run locally, sync across machines with Pro.

Memory Palace MCP server for AI agents

29 developer utilities as an MCP server — JSON repair, SQL format, hash, encode/decode, UUID, regex, CSV, subnet calc, diagram generation, git diff parsing, DB schema parsing, JSON schema validation, and more. No API keys. Runs locally.

MCP server providing persistent cross-session memory for AI agents — store, recall, search, and summarize memories across agent boundaries

MCP server for Runframe incident management — any agent, any IDE, one system of record

The Control Plane for AI Agents. 26,701 discoverable APIs, 2,906 callable, 49 fully managed. Agent-native auth: `apiclaw auth login` opens your browser, one-tap sign-in, writes ~/.apiclaw.toml. Four doors: local MCP, CLI, HTTP gateway, Remote MCP. One aut

OpenClaw-ready CLI for Ring-a-Ding AI phone calls

VettIQ MCP server — security scanning for AI-generated code, callable from Cursor, Claude Code, and any MCP-compatible agent.

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a built-in verification loop. Works on every Figma plan including Free. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf, and any

MCP server that turns HTML MUP panels into interactive tools for LLMs — render UI, call functions, and pipe data between panels

MCP server for validating, transforming, and normalizing structured data - built specifically for AI agents

Autonomous demo agent for SaaS products — MCP server for Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible agent. Discovers, integrates, and runs AI-guided product demos. Starts in onboarding mode with no API key so the calling agent c

MCP server that dynamically starts and manages other MCP servers

Postals — the agent skill that turns any AI into a direct mail machine. One MCP tool call mails a physical handwritten postcard (real pen-and-ink, USPS 3-5 day delivery, $4.99 per card). Works with Claude Desktop, Cursor, Claude Code, OpenClaw, n8n, LangC

Agent-optimized MCP server for extracting clean, structured content from web pages - built specifically for AI agents that need LLM-friendly web data

Unified Capability index for AI agents — 80+ ranked cloud services, skills, MCP servers, plugins, parsers, and public-data sources for Claude Code, Cursor, Claude Desktop, OpenClaw. Call find_capability with a query or jtbd tag to get a ranked list across

Complete codebase intelligence — loads treesitter, symbol, outline, callgraph, depgraph, refs.