AI & Agents MCP Servers for Claude Code

MCP server for Antigravity Claude Proxy — use Claude Opus 4.6, Sonnet 4.6, and Gemini 3 via any MCP client. TypeScript, tested, zero-config.

Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.

Manage IBM Watson Orchestrate tools, agents, connections from Cursor, Copilot, Claude.

MCP server for YandexGPT — completions, embeddings, classification, summarization (Russia)

Look up AI agents on Arc: ERC-8004 identity, feedback, validations and USDC-backed trust scores.

Compact, source-linked context packs that reduce token waste for coding agents.

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents.

Turn a written policy into rules a program can check, and get the same answer every time.

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

Deterministic pre-execution verification tools for AI agents with x402 USDC pay-per-call on Base

An MCP server that provides a smart proxy to other mcp servers

Agent MCP Router MCP — one router for the whole MEOK fleet. Holds 62 MEOK MCPs behind one

Agent Token Budget MCP — hard per-session token + spend cap with signed budget-exhausted

See each coding-agent subscription's live limits and offload work to one with headroom.

MCP stdio proxy that logs the tool-call seam to the ledger without the agent's cooperation

Checks what an agent did NOT read. Coverage over a retrieval step or a folder.

Trust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.

MCP server for spawning Claude Code agents in cloned repos — branch your agents

Inject, parse, and strip [N] citation markers in RAG outputs.

Claude Code token usage, cost, and plan limits from local logs and Anthropic's usage API.