AI & Agents MCP servers

Run the agents, teams and workflows of your Agentivity workspace from your AI assistant.

Free agent messaging: shared/private threads, participant search and inbox. Bearer token; no OAuth.

Procurement agent for AI agents: free quote, buys verified x402 data services, pay per task in USDC.

Free repository documentation for MCP and A2A agents. Bounded no-signup trial with shared cache.

Self-hosted participant resolution agent with an MCP server for agent workflows.

Marketplace where AI agents hire other agents, paid per call in USDC. Plus LLM inference.

Self-hosted MCP gateway. Turn any REST API into MCP tools via YAML (DADL). Authz, audit, policies.

Agent messaging inbox (A2A, EIP-712 signed), ERC-8004 directory, status and text hashing for Monad.

Free search and declared-price review of public MCP and x402 service catalogs. Experimental pilot.

Managed long-term memory for AI agents, with evolving facts and relevant retrieval through MCP.

Build & govern AI agents for regulated industries: EU/GCC residency, governance, audit.

Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.

The decision layer for AI agents: act, escalate or refuse, and every decision comes back signed.

Cross-device AI memory with encrypted activity capture and context handoff between AI tools

Persistent memory for AI agents. Free, no LLM, no SDK. Open Worker you can self-host in 2 commands.

Your team's shared, verified knowledge for AI agents: ask what's true, record what you learn.

Hosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.

Tracks conversation health in real time — drift, desync, and causal collapse — for any AI agent.

Discover available AI models and delegate analysis or code review from your existing agent.

Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows

Free API discovery for AI agents; execution may require USDC/x402 payments on Arc Mainnet.

Personal memory for AI agents from a vault on your Mac, with per-agent scopes and approvals

Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.

Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.

Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.

Hosted MCP for source-backed project context, memory, code impact, and agent workflow continuity.

Process monitoring for AI agents: start runs, submit per-task evidence, complete runs.

Auto-generate a hosted MCP server from any SaaS product URL in minutes. No code required.