luthersystems-com-mcp.yml
Luther Systems ships THREE provider-built MCP servers and documents each one itself. (1) AgentSearch — a hosted Streamable HTTP endpoint at https://agentsearch.luthersystems.com/api/mcp (protocol version 2025-06-18, serverInfo agentsearch 0.1.0, capabilities {tools: {listChanged: false}}) that answered initialize and tools/list anonymously on 2026-09-19 with FIVE read-only tools carrying real inputSchemas (saved verbatim to mcp/luthersystems-com-agentsearch-mcp-tools.json), plus the same five tools as a stdio package, @luthersystems/agentsearch on npm (0.1.2, 2026-05-21, MIT, source github.com/luthersystems/agentsearch/mcp). (2) InsideOut (Riley) — a hosted Streamable HTTP endpoint at https://app.luthersystems.com/v1/insideout-mcp (protocol version 2025-06-18, serverInfo insideout-agent v2.0.0, capabilities logging + prompts + tools with listChanged, session via Mcp-Session-Id, responses as SSE) that answered initialize, tools/list (24 tools with inputSchemas, saved verbatim to mcp/luthersystems-com-insideout-mcp-tools.json) and prompts/list (one prompt, `usage`) anonymously; the same server ships as a stdio package (@luthersystems/insideout-mcp on npm, 0.50.1, 2026-05-31, UNLICENSED) and a Docker image (luthersystems/insideout-mcp, 48k pulls, updated 2026-08-26). Design and pricing tools need no credential; deployment tools require the user to connect cloud credentials in a browser and subscribe (credawait), and every call after convoopen carries a per-session token embedded in the session_id. (3) shirotester — a LOCAL-ONLY stdio MCP server inside the @luthersystems/shirotester CLI (npm 2.236.0, 2026-09-01, Apache-2.0) for Substrate/ELPS development on the Luther Enterprise platform; 15 tools are documented, no hosted endpoint exists, and the package was verified on npm but not executed.
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.