Connect Embedded Docs and your agent gets 3 tools, among them get_context, request_document, search_docs. It answers at https://mcp.byteask.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Page-cited retrieval over primary-source embedded/firmware references for coding agents.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_context | Expand a previous search hit to its full verbatim section (markdown). Args: result_id: The result_id from a search_docs hit. effort: Internal diagnostics tag; clients should leave this unset. Inputs: result_id, effort |
request_document | Request that a document be ADDED to the corpus - use this when search_docs returns 'no confident match' for material it should cover (a standard, protocol spec, SCPI or instrument manual, MCU / hardware datasheet, or library reference). Thi Inputs: request, effort |
search_docs | Search the indexed embedded / firmware / hardware reference corpus; return verbatim, page-cited evidence. The indexed corpus covers: grid-interconnection & DER standards (IEEE 1547 / 1547.1 / 2030.5, SunSpec Modbus profiles, ENA G98/G99 and Inputs: query, limit, effort |
Every block below points at https://mcp.byteask.ai/mcp. Pick your client and copy.
claude mcp add --transport http embedded-docs https://mcp.byteask.ai/mcp
{
"mcpServers": {
"embedded-docs": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.byteask.ai/mcp"]
}
}
}{
"mcpServers": {
"embedded-docs": {
"url": "https://mcp.byteask.ai/mcp"
}
}
}{
"servers": {
"embedded-docs": {
"type": "http",
"url": "https://mcp.byteask.ai/mcp"
}
}
}{
"context_servers": {
"embedded-docs": {
"url": "https://mcp.byteask.ai/mcp"
}
}
}{
"mcpServers": {
"embedded-docs": {
"serverUrl": "https://mcp.byteask.ai/mcp"
}
}
}{
"mcpServers": {
"embedded-docs": {
"url": "https://mcp.byteask.ai/mcp"
}
}
}name: Embedded Docs
version: 0.0.1
schema: v1
mcpServers:
- name: Embedded Docs
type: streamable-http
url: https://mcp.byteask.ai/mcp{
"mcpServers": {
"embedded-docs": {
"httpUrl": "https://mcp.byteask.ai/mcp"
}
}
}{
"mcpServers": {
"embedded-docs": {
"type": "http",
"url": "https://mcp.byteask.ai/mcp"
}
}
}{
"mcpServers": {
"embedded-docs": {
"url": "https://mcp.byteask.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.byteask.ai%2Fmcp&type=streamable_http&id=embedded-docs&name=Embedded%20Docs
It answered our last check on 17 October 2026 in 503 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by byteask.ai and served from mcp.byteask.ai, the vendor's own domain: https://mcp.byteask.ai/mcp.
3, as returned by the server's own tools/list on 7 September 2026: get_context, request_document, search_docs.
It answered our last check on 17 October 2026 in 503 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.byteask.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.byteask. Endpoint host: mcp.byteask.ai. ARD identifier: urn:air:ai.byteask:mcp:embedded-docs.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.