AI & Agents MCP Servers for Codex CLI

Thin MCP relay for agent-to-agent communication with Director/Agent roles

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

26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.

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

Analyze LLM API costs: token waste detection, caching savings estimates, model comparison

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.

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

Beta MCP server for typed SOTA consultation, model fan-out, and judge synthesis for autonomous agents.

The prediction MCP — score your prompt before you generate, so you never waste a credit.

Work-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery

MCP server for building and managing Flowise chatflows and agentflows. Provides AI assistants with comprehensive knowledge of Flowise nodes

GeraClone MCP — discover expert clones, check operator's clone status, start expert chats (consent).

Inspect and score any MCP server 0-100 on publishability, schema and protocol before publish.

Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

Ask TypeSafe Jev yes/no, choice and score questions and receive structured model judgments.

Grade MCP servers A to F with the open behavioral litmus. npm: full toolset; hosted: lookups only.

Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.

MEOK AI Labs - neural-health-monitor MCP server extracted from SOV3

MEOK AI Labs - quantum-scoring MCP server extracted from SOV3