AI & LLM Tools MCP servers

Interact with TUI/CLI applications through a structured terminal state tree with element detection, like Playwright for terminals.

Text-to-speech for Claude Code using OpenAI's TTS API, with multiple voices and cross-platform playback.

Spawn multiple specialized Claude Code agents as MCP servers, each independently configured.

Developer tools for file editing, shell command execution and screen capture.

URL to LLM-ready markdown — plus per-page category, page_structure, and query-driven highlights.

Self-hosted digests of your Telegram channels over MCP: AI summaries, the last digest and raw per-channel messages, with OpenAI, Anthropic or Ollama.

MCP server for DataSinking — full-text financial reports (US, China, Japan, Korea, Taiwan) as clean Markdown, for Claude, Cursor and other AI agents.

Evidence-backed web research: real-time search with cited claims, confidence scores and a mode comparing raw LLM answers with evidence-backed ones.

MCP server that runs Claude Code as tools — start coding agents, poll their progress, and control permissions from any MCP client

Recursive Claude spawning for autonomous project builds with self-healing test loops

MCP server that helps Claude create other MCP servers with persistent knowledge

Persistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.

SSH control for Linux and Windows servers, with long-running commands and execution on multiple hosts at once.

Relays messages between two Claude Code sessions on different machines using the Channels API

MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — run REPLs, SSH, databases, Docker, and any interactive CLI with clean output and smart completion detection

Your clipboard, but Claude can read it. Type-classified, secret-encrypted. macOS + Linux.

Manage multiple Gmail accounts in Claude Desktop — search, send, reply, draft, and organize.

Policy-based governance for agent tool calls across LangChain, OpenAI, Anthropic and MCP: YAML policies, approval gates, risk assessment and audit logging.

Unified MCP server for multi-LLM consultation — routes Gemini, Codex, Claude, Grok, Ollama, and Antigravity behind runtime availability checks

Bridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions

Bridge Claude with OpenAI Codex CLI for AI-to-AI collaboration, code review, and second opinions

Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions

Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local

Compile browser automation into deterministic plans that run in your logged-in Chrome without runtime LLM calls, detecting drift when sites change.

MCP server for AI interaction with live Smalltalk images

MCP Server — Solana Glossary for AI agents. Exposes 1001 Solana terms to Claude, Cursor, and any MCP-compatible client.

Approval-first local terminal control: policy-based command planning and approval, DeepSeek as an advisor, and signed execution receipts.

An LLM Wiki for Claude Code, in your Obsidian vault.

MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations

MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR

One MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.

MCP server engine for the NiCE Cognigy Plugin (Claude Code, Codex, and more)

AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)

Give Claude live access to SAP ABAP via ADT: read, search, check, test, and edit objects.

Reasoning, code, anti-deception, memory harness MCP tools. Stdio or HTTPS api.ejentum.com/mcp

AI API cost tracking and budget enforcement across LLM providers: spend analytics, budget monitoring, session summaries and key management.

Spec-driven verification layer for AI coding agents — Claude Code · Codex · Gemini · Antigravity · Cursor. Intent in before it writes, result verified against your spec after. Reference implementation of the Ironclad standard.

Cross-LLM communication and memory sharing so different AI models can collaborate and share context across conversations.

Connect Claude to Fathom meeting recordings, transcripts, and summaries

DevOps and networking tools: network monitoring, system diagnostics, automation workflows and infrastructure management.

Task management for Claude Code with a visual Kanban board and orchestration for product teams and developers.

Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsurf a ranked, token-budgeted query surface — agents query structure (symbols, imports, call edges

Memory database for LLM agents — persistent semantic + keyword memory, project namespacing, served o

Load Claude Code skills into agents without copying files: discover, read and install skills on demand.

Task management for Claude agents: hierarchical tasks, dependencies, sprints, acceptance criteria and multi-agent coordination.

Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.

Full-text and semantic search over Claude Code transcript history, with exact thread recall and durable remembered facts in local SQLite.

MCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)