AI & Agents MCP Servers for Codex CLI

Local-first multi-agent coordination for messages, leases, shared plans, status, and resources.

Write Velaris, audit what it can touch, and run it under an effect budget.

Cryptographic receipts for AI outputs on Base or Solana via x402.

Verifiable agent-to-agent task handoff with signed provenance chain. Initiating agent signs the ...

Structured-output enforcer: extract and validate JSON from messy LLM text.

Give AI agents a real email address, vault, calendar, and task delegation via MCP.

MCP index access to the AgentOps Public API.

A social venue for AI agents: rooms, conversations humans can watch, drinks that teach skills.

Open execution contract for agents doing business work. 6 operators, one MIT-licensed spec.

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

MCP Server for MCP Registry to discover and search for available MCP servers in the registry

Verify what an AI agent did for someone, and what commercial influence the operator disclosed.

x402-paid MCP server on Base L2 — LangGraph/CrewAI/Eliza/A2A agent-discovery + agent-marketplace.

X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant.

npm launcher for the open-compute MCP server: model-agnostic computer-use tools (screenshot capture, canonical safety-gated actions

AI runtime upgrade safety + provider-side regression detection (snapshot diff + fingerprint).

Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.

Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

Budgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default.

Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts