Inspect and Query Stateless Model Context Protocol Endpoints with mcp-explorer and llm-mcp-client
Following the Model Context Protocol 2.0 stateless HTTP specification, new developer CLI tools simplify probing and interacting with Model Context Protocol servers without maintaining server-side session state. Developers can now inspect tool schemas instantly via uvx and query tools directly inside terminal LLM workflows using alpha llm-mcp-client.
Why it matters
Stateless MCP eliminates the need for managing server session state or complex connection routing, making it significantly easier to build and audit agent tool integrations.
TL;DR
- 01MCP 2.0 simplifies tool calling down to a single HTTP POST request.
- 02mcp-explorer enables quick schema discovery and execution via uvx.
- 03The alpha llm-mcp-client integrates remote MCP endpoints directly into CLI LLM workflows.
Stateless HTTP Simplified Model Context Protocol
Legacy Model Context Protocol implementations required an initial HTTP request to create a session ID followed by a second request carrying the Mcp-Session-Id header. The July 2026 stateless specification condenses tool discovery and execution into a single HTTP POST call, eliminating backend session tracking.
Inspecting Endpoints with mcp-explorer
Using uvx, developers can query remote Model Context Protocol servers directly from the shell without manual installation:
uvx mcp-explorer list https://agentic-mermaid.dev/mcp
uvx mcp-explorer call https://agentic-mermaid.dev/mcp render_ascii '{"source":"graph TD; A-->B;"}'Direct LLM CLI Tool Invocation
The alpha llm-mcp-client plugin exposes remote Model Context Protocol endpoints directly to local LLM prompts, allowing agents to execute tools such as SQL databases or diagram generators:
llm -T 'MCP("https://datasette.simonwillison.net/-/mcp")' 'count the notes'