Read RPC docs from Node.js with mcp-use—without a model or API key

A developer published a Node.js example using the mcp-use client (pinned to version 2.4.5) to query BlockVectra's documentation-only MCP endpoint over Streamable HTTP without a model, API key, wallet, or local server. The script lists the two exposed tools, search_docs and read_doc, searches for "quickstart" with a one-result limit, and prints the returned Markdown, failing on empty or malformed results with 15-second call timeouts. A November 11 internal check on Node.js 26.8.1 recorded four HTTP 200 responses across discovery, tool listing, search, and read.

You can retrieve RPC setup documentation through MCP without starting a model-driven agent. This Node.js example lists the available documentation tools, searches for quickstart , and prints the Markdown returned by read doc . It reads instructions; it does not execute the RPC or account steps inside them. The endpoint is BlockVectra's documentation-only https://docs.blockvectra.com/mcp/docs , served over Streamable HTTP. It exposes only search docs and read doc . No BlockVectra account, API key, wallet, model API, or local MCP server is needed. You need Git, npm, and Node.js 22.22.2 or newer . Start from this exact revision so the code and committed dependency lockfile match: git clone https://github.com/blockvectra/agent-quickstart.git cd agent-quickstart git checkout --detach c4c0d5c81c5518add7f0f204a77f42934d183588 cd examples/mcp-use-docs npm ci --ignore-scripts npm start The example pins @mcp-use/client to 2.4.5 . Installation needs network access to the npm registry; it happens before the script starts. npm start runs node remote-docs.ts . The example disables SDK anonymous telemetry before importing the client module: process.env.MCP USE ANONYMIZED TELEMETRY = "false"; const { MCPClient } = await import "@mcp-use/client" ; The first output line lists the two documentation tools. The script then searches in English with a one-result limit: js const search = await connection.callTool "search docs", { query: "quickstart", lang: LANG, limit: 1 }, { timeout: TIMEOUT } ; Here, LANG is "en" and TIMEOUT is 15000 milliseconds. The script parses the search result's text as JSON and checks that its first result contains a usable path . It passes that actual returned value to read doc with the same language—not a document ID, a full URL, or a guessed filename. Look for first result: followed by the selected path, then the page's Markdown. Empty or malformed search results stop the script rather than silently substituting a page. Tool errors and missing text also fail the run; the client closes in finally on success or failure. Calls have 15-second timeouts. A November 11 internal check using Node.js 26.8.1 recorded four HTTP 200 responses for discovery, tool listing, search, and read; that is one tested configuration, not a performance benchmark or a model-agent walkthrough. The complete source https://github.com/blockvectra/agent-quickstart/blob/c4c0d5c81c5518add7f0f204a77f42934d183588/examples/mcp-use-docs/remote-docs.ts keeps the connection and error handling together. Documentation success does not establish business RPC or Data API success: those use the full connection and their own public-method or authentication policies. For client setup, see the MCP server guide https://docs.blockvectra.com/en/guides/mcp-server/?ref=dev-node-mcp-use-1112 docs-only-remote-http .