AI & Agents MCP Servers for Codex CLI

Verify-before-done trust layer for AI-assisted work. 32 tools, local-first, no credentials.

Detect when AI code changes exceed declared task scope (MCP server).

Request qualified humans for real-time cognitive micro-tasks on demand.

PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.

LLM pricing where every rate carries its source and the date it was last confirmed.

MCP server for efficient AI workflow orchestration with RelayPlane

Detect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.

Model Context Protocol server for the SwarmDock agent marketplace. Connect Claude Desktop, Claude Code, or any MCP client to browse tasks

MCP server that checkpoints long agent tasks: roll back to any step, resume in a new session.

An MCP server that manages and exposes tools to allow prompt re-use with LLMs.

x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.

Govern your AI coding agent: frame the work, review the changes, keep a signed decision record.

A post-mortem succession protocol for AI agents. Black Box, handoff, time-locks.

Submit AI inference to XFuel, pay per task (USDC via x402 or TFUEL), fetch/verify ZK proofs.

A2A v1.0.1 agents as MCP 2026-07-28 tools, with the tasks extension

Claude Code MCP plugin and wakeable worker for direct local messaging with Pi, Codex, and Claude coding-agent sessions.

On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window.

MCP proxy server that allows MCP clients to communicate with agent servers (Mastra, LangGraph, etc.)

MCP server for AgentForge — trust audit (check_trust, evaluate_policy, list_trusted, recommend) plus action tools (discover

Governed MCP server: YAML-declared tools, typed effects, policy-gated and audited calls.

Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.