Agent MCP Server

Agent MCP server exists for a simple reason — assistants are far more useful when they can act on Agent directly instead of describing what you should do. Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<100...

What you get

Per-agent-pair IAM for A2A. Define policies ('orchestrator may call billing only when amount<1000'), gate every A2A call via evaluate_call. EU AI Act Art 14 + ISO 42001 Annex A.7 evidence with signed policy-decision attestations.

Setting it up

The server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Agent is connected, these are the calls the assistant has available:

• Per-agent — pair IAM
• Free — generous daily limit (100-1,000 depending on operation)
• Pro — ** £79/mo — Full MCP suite + EU AI Act tracking
• Enterprise — ** £499/mo — Custom dev + SLA + Dedicated support
• Domain — Purpose
• Tier — Price

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the agent mcp server does with a few real requests.

Choosing this one

This sits in the payments and commerce group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Agent's toolset — Per-agent, Free, Pro and 3 more — is a fair guide to whether it matches your workflow. It is maintained by CSOAI-ORG; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agent's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.