transport:streamable http protocol:2025-11-25 tools:13

Connect your agent to the public MCP server.

The launch endpoint is stateless MCP Streamable HTTP. It exposes the same Python adapter, resources, prompts, schemas, and structured errors as the local server.

Your agent may lazy-load the tools, so make sure it crawls the full toolset. Typical cold-start is ~5K tokens of context.

Connection URL https://semantic-rails.com/mcp

MCP Inspector

Inspect before integrating.

Run npx @modelcontextprotocol/inspector.
Select Streamable HTTP as the transport.
Enter https://semantic-rails.com/mcp and connect.
Initialize, list tools, then start with capabilities or catalog.
For answer tests, load capabilities, catalog, discover, plan, validate, compile, and execute.
For tight QA loops, use plan(detail="query") then execute(row_format="columns"); call validate when editing IR or reviewing diagnostics.

initialize.sh

curl https://semantic-rails.com/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -H 'MCP-Protocol-Version: 2025-11-25' \
  --data '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"curl","version":"1"}}}'

Agent-first governance.

Default to compact or minimal responses, then request more detail only when needed.

capabilitiescatalogdiscover inspectbuild-optionsvalid-values planvalidatecompileexecute segment-validatesegment-explainsegment-preview

Try in the browser Agent quickstart Read the API reference