kgninja-dev-mcp.yml
KG-NINJA operates ONE remote MCP server at https://agent-economy.kgninja.dev/mcp — the same origin as its website, OpenAPI and A2A endpoint. It is stateless Streamable HTTP, POST only (GET returns 405 with details.allowed "POST"), negotiated protocol version 2025-06-18 in a live initialize (the server card declares 2026-07-28, 2025-11-25, 2025-06-18 and 2025-03-26 as supported), identifies itself as serverInfo {name: dev.kgninja/agent-verification-utility, version: 0.4.3}, and answers initialize and tools/list anonymously with five tools that carry real JSON Schema 2020-12 inputSchemas AND MCP tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint). resources/list and prompts/list return -32601 Method not found. Four tools are free; verify_evidence is paid: an unpaid call returns a tool error whose _meta["x402/error"] carries an x402 v2 PaymentRequired document plus a paid verification binding, and the identical call is retried with the encoded payment in _meta["x402/payment"]. Anonymous tools/list succeeded, so authorship is knowable: the tool names, the dev.kgninja namespace and the _meta extension keys (dev.kgninja/offer-generation, dev.kgninja/decision-support, dev.kgninja/x402) are specific to this provider and match no shared platform fingerprint — this is a provider-built server, not a Wix/Shopify/Mintlify/WordPress-plugin surface.
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
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.