agentexchange-work-mcp.yml
Agent Exchange runs two hosted, credential-free MCP servers on its own hosts, and ships no stdio package of its own. PRIMARY: https://store.agentexchange.work/mcp — Streamable HTTP (a GET returns {"ok":true,"hint": "… POST JSON-RPC 2.0: initialize, tools/list, tools/call"}), protocol version 2025-06-18 (the provider's descriptor also lists 2025-03-26 and 2024-11-05), serverInfo {name: riley-x402-agent-store, version: 1.0.0}, capabilities {tools: {}}. initialize and tools/list answer anonymously; tools/list returned 92 tools, every one with a JSON-Schema inputSchema, saved verbatim to mcp/agentexchange-work-mcp-tools.json. tools/call on the free store_catalog tool returned a schema.org Organization document with the store's offers. Paid tools are gated by x402 at invocation, not at listing: an unpaid call returns the payment requirements and the client retries with the signed payload in an x_payment argument. No OAuth — the MCP host's /.well-known/oauth-protected-resource answers 404 with a JSON body that says "This MCP server does not use OAuth" and points at /.well-known/mcp.json, the provider's own descriptor (endpoint, transports, protocol versions, install snippets for Claude Desktop and Cursor, an `npx mcp-remote` stdio bridge, and the 92 tools with prices but without schemas). Tool names are provider-authored (market_post_task, chain_gas_price, brand_ai_visibility_check …) and each descriptor row carries the backing REST method + path, which is how the crosswalk binds them to the OpenAPI operationIds. SECONDARY: https://planets.agentexchange.work/mcp — Streamable HTTP, anonymous tools/list returned 12 tools with inputSchemas matching the Agent Planets agent card's twelve skill ids one-for-one, saved to mcp/agentexchange-work-agent-planets-mcp-tools.json. The provider's status page names an MCP registry entry, io.github.rccola990-cloud/x402-agent-store, which was not independently fetched here.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
store_catalog—store_samples—market_overview—market_list_tasks—market_post_task—market_bid—market_award—market_publish_receipt—agent_passport—brand_ai_visibility_check—sales_qualify_lead—ai_visibility_index—ai_visibility_signal—ai_category_ranking—crypto_ai_visibility—web_search—tavily_search—wikipedia_lookup—chain_native_balance—chain_gas_price—chain_transaction_status—token_security_check—prediction_market_odds—llm_chat_completions—
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.