Best Calls AI Skills & MCP Servers

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

BLACK_WALL MCP server — a pre-action risk check your AI agent calls before any irreversible action (send email, move money, run SQL, delete data).

Transparent proxy CLI for MCP servers — tracks tool calls, latency, and cost via MCPSpend.

MCP server for the Smallest AI platform — manage agents, debug calls, view analytics from your IDE

GitHub Action for evaluating MCP server tool calls using LLM-based scoring

MCP server for Gong.io - access calls, transcripts, and users

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

Query FDA data on drugs, food, devices, and recalls via openFDA. STDIO or Streamable HTTP.

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

MarketIntelLabs fork of the Paperclip adapter for Hermes Agent — with adapter-owned status transitions, an in-process MCP tool server (paperclip-mcp) that replaces curl-in-prompt with structured tool calls, MIL heartbeat prompt templates, and OpenRouter m

Vexp — Context Engine for AI Coding Agents. Pre-indexes your codebase into a dependency graph and delivers ranked context to any MCP-compatible agent. 58% lower cost per task, 90% fewer tool calls (SWE-bench Verified). Works with Claude Code, Cursor, Copi

HITL infrastructure for AI agents. Your agent calls awaitHuman(), a human reviews via Slack/email/dashboard, agent resumes with a typed response.

MCP stdio server for AI TTS Microservice — connects AI agents, IDEs, and MCP-compatible clients to the unified TTS API via tool calls

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en

Decode VINs, search recalls, complaints, crash ratings, and investigations via MCP. STDIO or Streamable HTTP.

MCP server that combines Read+Edit operations into single tool calls — 80-95% fewer tool calls for multi-file refactoring

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

MCP Hub is a local web UI for testing LLMs and MCP servers. Connect providers, inspect tool calls, and run multi-turn chats in one place.

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.

MCP server for OsmTalk — make phone calls via Claude Desktop using voice AI agents

MCP quality scanner and tool discovery for autonomous agents. Search 27,843+ indexed tools, check AEO (answer-engine-optimization) readiness scores, validate MCP server quality, find alternatives — the standard tool-validation layer before any agent calls

MCP (Model Context Protocol) server for Grackle — translates MCP tool calls to ConnectRPC

TES SDK — LLM observability and lifecycle tracking via Pentatonic Thing Event System. Track token usage, tool calls, and conversations. Manage things through event-sourced lifecycle stages with AI enrichment and vector search.