MCP server

The Model Context Protocol server exposes the same governed marketplace as the REST API, but as tools an agent runtime — Claude Code, Cursor, or any MCP-speaking client — can call directly over stdio. It adds no authority of its own: every call runs under the calling API key's principal, scopes, and budgets.

Connect it (Claude Code)

One-command install — the plugin ships the MCP server, a search-before-build skill, and an optional prompt hook that checks the marketplace before your agent rebuilds something that already exists:

claude plugin marketplace add michaelcho87/aimarketplaceos-plugin
claude plugin install ai-marketplace-os

Any other MCP client (Cursor, etc.): clone the plugin repo and point your config at the bundled server:

{
  "mcpServers": {
    "ai-marketplace-os": {
      "command": "node",
      "args": ["<path>/aimarketplaceos-plugin/servers/amos-mcp.mjs"],
      "env": {
        "AMOS_API_KEY": "amos_agent_..."
      }
    }
  }
}

Issue AMOS_API_KEYfor an agent principal from your organization’s agent settings — not your personal login key — so scopes and budgets stay scoped to that agent, not to you.

Tools (17)

Discovery & planning

6 tools

Understand the catalog before spending anything.

search_catalog
Natural-language search. Returns grounded, explained results, inferred needs, and gaps the catalog can't cover.
inspect_product
Full detail for one product: manifest, capabilities, offers, licenses, trust passport, versions, advisories, relationships.
compare_products
Compare 2–6 products across a capability matrix with offers and trust.
plan_solution
Assemble a compatible multi-product stack for an objective — real catalog products only; unfilled gaps reported honestly.
check_compatibility
Check declared compatibility and conflicts between 2–10 products.
estimate_total_cost
Estimate one-time and recurring cost for a set of offers.

Commerce

5 tools

Priced, policy-evaluated, auditable — every step.

get_quotescope: quote
Create a formal quote with server-side pricing.
request_purchasescope: purchase:request or purchase:auto
Request a purchase from a quote. Clears immediately within policy (demo payment + entitlements returned); otherwise returns approval_requested for a human to decide. Idempotent on idempotencyKey.
get_purchase_status
Get an order's state. Resumes payment and entitlement issuance idempotently once a human has approved it.
list_entitlements
List the organization's active entitlements and machine-readable rights.
provision_product
Provision a purchased product (DEMO: instant simulated provisioning).

Invocation

1 tool

Actually calling a product your organization purchased.

invoke_servicescope: invoke
Invoke a purchased product's demo API. Entitlement-gated, metered, and audited.

Trust & updates

5 tools

Stay current, and feed real outcomes back into Trust Passports.

check_updates
Updates and security advisories relevant to owned entitlements.
subscribe_to_updates
Subscribe the organization to a product's update channel (stable, beta, or security).
list_security_advisories
List published security advisories, optionally scoped to one product.
report_installation_outcome
Report whether an installation succeeded — feeds Trust Passports and ranking.
report_runtime_outcome
Report runtime health (uptime, error rate) for a product this org runs — feeds maintenance signals.

A read-only resource, amos://catalog/overview, is also published (catalog statistics by product type) — resources are for ambient context, not actions, so they aren’t counted among the tools above.

The governance model

MCP is a transport, not a trust boundary. Every tool call resolves to an agent principal — a governed identity distinct from the human who owns the organization — and every commerce action is evaluated server-side before anything spends.

Scopes

Each agent principal carries an explicit scope list (e.g. quote, purchase:request, invoke). A tool call missing a required scope fails closed with an explicit error, never a silent downgrade.

Budgets

Per-transaction caps, daily and monthly spend caps, and a separate cap on newly committed recurring spend are all checked before a purchase clears. Exceeding any of them routes to approval instead of failing outright.

Approvals

When policy requires approval, the order sits in approval_requested until a human decides. Agents cannot approve their own purchase requests — the decision path explicitly rejects any credential carrying an agent-principal id.

Every quote, order, invocation, and decision is written to an audit trail readable via GET /audit-events in the REST API — MCP convenience never comes at the cost of visibility.