Categories › AI & Agents › Multi-agent, orchestration & workflows
Procure governed AI capabilities: machine-readable price, scope, trust, gateway-delegation terms.
Remote server: your requests and data go to mcp.gatecoreai.com. Claude Code: claude mcp add --transport http gatecore-marketplace https://mcp.gatecoreai.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
discover_listings — Discover governed GateCore marketplace capabilities with machine-readable pricing, required scopes, and minimum trust terms. Results preservget_listing — Fetch one governed marketplace listing and its machine-enforceable contract terms: price, required scopes, minimum trust, target, and data cprocure — Request governed procurement for a listing. In public full mode, identity comes from the MCP access key, trust comes from GateCore's baselinauthorize_access — Authorize signed access to a governed listing. Purpose is forwarded unchanged when present; policy at the gateway decides whether the declarcomplete_access — Hash seller output locally, attest completion with the buyer agent key, and return the terminal signed receipt. Seller output itself is nevelist_procurements — List procurement decisions for the credential tenant in public modes.request_listing_access — Submit an idempotent listing-access request for the credential's tenant and agent.submit_lead — Submit a consented consumer lead to a supported published listing.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.