Best Code AI Skills & MCP Servers

Cross-agent permission policy specification for AI coding agents

CLI-first infrastructure intelligence platform — analyzes DynamoDB, PostgreSQL, MySQL, MongoDB, SQS, SNS, SSM, Secrets Manager, Lambda, CloudWatch Logs and exposes findings as an MCP server for Claude Code

MIND MCP Server — 28 tools. The most complete AI memory layer with the Focus → Project → Outcome → Task hierarchy (mind_focuses + extended mind_life with item_type/parent_id/focus_id and cross-account project sharing via share/list_shares/revoke_share), d

Personalized GitHub issue finder with multi-strategy search, deep vetting, and viability scoring — CLI, library, MCP server, and Claude Code plugin

The MCP toolkit for AI agents. Voice MCP gives your AI a phone line through your own Twilio. Coder MCP gives it a memory across every Claude Code, Codex CLI, and Cursor session. One npm package, two capability modules, local SQLite, no SaaS in the middle.

Deploy Claude, Codex & Gemini CLI agents to demolish your work before users do. Real file analysis. Brutal honesty. Now with conversation continuation & intelligent pagination.

CLI + MCP server for Fluxra — scrape comments, generate viral hooks, run AI research from the terminal or any MCP host (Claude Desktop / Code, Cursor, OpenClaw).

Knit — second brain for any MCP-speaking AI coding agent (Claude Code, Cursor, Codex CLI, Cline, Continue, GitHub Copilot). Per-project memory, tier-routed workflow protocol, parallel team worktrees.

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

Unified CLI to manage MCP servers across Claude Code, OpenCode, and more

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

Lossless, project-scoped memory for AI coding tools. Durable context across sessions with 56 MCP tools, FTS5 search, conductor orchestrator, loop/watch monitoring, snapshot capture, pre-flight overlap checks, Claude/Codex/OpenCode wrappers, Linear sync, a

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

Cross-agent permission policy specification for AI coding agents

MCP stdio server + WebSocket primary for browserops — drives the browserops Chrome extension. Install `browserops` for the user-facing CLI.

Mobile control plane for AI agents. Approve, answer, and hand off work for Codex, Claude, MCP-ready tools, and A2A from one phone.

MCP server for rendering DGMO diagrams — SVG/PNG output, browser preview, HTML reports, and 35+ chart types. Works with Claude Desktop, Claude Code, and any MCP client.

Save up to 80% tokens when AI reads code — MCP server for token-efficient code navigation, AST-aware structural reading instead of dumping full files into context window

MCP server for multi-terminal Claude Code orchestration with DAG task management, parallel execution, and self-improvement

Model Context Protocol server for AgentMinds — gives Claude Code, Cursor, Zed, and other MCP-aware AI clients native access to the AgentMinds cross-site collective intelligence pool. Push agent reports, pull personalised recommendations, browse the networ

MCP server for RepoMap — code intelligence via AST-based repository analysis

User stories as structured AI coding context — scope-check via get_active_story (Claude Code, Cursor, Windsurf)

ContextECF CodeLedger — deterministic context selection for AI coding agents. Safe unscoped alias for @codeledger/cli; avoid the unrelated codeledger package.

Local-first code intelligence — MCP server for Claude Code, Cursor, Windsurf, Zed. Symbol graph, blast-radius, git-pinned memory. 43× fewer tokens than naive grep on the public bench. MIT, zero-config.