AI & Agents MCP Servers

Token and context budget for AI agents. Tracks spend and gates the session.

Agent-to-agent communication bridge for multi-agent systems

MCP server that cuts AI coding agent token usage via framework-aware context optimization

A Model Context Protocol server for integrating with any OpenAI SDK compatible Chat Completion API

MCP server enabling LLMs to consult with Google's Gemini models for additional insights and alternative perspectives

FIBER decision-context compiler with honest omission accounting: 259 evidence-bearing MCP tools.

Every number in an AI answer traces back to the rows that produced it.

Durable local-first MCP relay for independent coding agents.

Real-time cost awareness for MCP agent workflows

MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients

Render branded PDFs and PNG images from templates or raw HTML via the DocJet API. Free tier.

Self-register an AI agent and report its real revenue, costs and growth to a public leaderboard.

Smart LLM routing across every major provider via one OpenAI-shape API.

Drop-in spend governance + cross-agent dedup proxy for AI agent fleets, with x402 settlement.

MCP server for the xAI Grok Build CLI (grok) — exposes Grok to any MCP client by wrapping the local grok CLI's headless mode.

Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.

Webhook & callback layer for AI agents: create a URL, wait_for_callback, and verify over MCP.

MCP server that sends work to Cursor Agent over ACP and returns the session id needed to continue.

Autonomous AI agent runtime — TypeScript + SQLite + React

Multi-LLM router MCP server — smart complexity routing, budget-aware model selection, 20+ providers (Claude, OpenAI, Gemini, Ollama, etc.)

Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.