RunBoth is a remote MCP server that gives an AI agent 3 tools, among them ask, list_sites, trust_lookup. It answers at https://runboth-agent-mgbxvs4loq-uc.a.run.app/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 4 of 4 times since 15 September 2026; the last check, on 20 October 2026, succeeded.
Ask runboth.dev in plain language: what RunBoth does, how to install it, and its limits.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ask | Ask runboth.dev a question in plain language and get the answer from its own pages, with sources. RunBoth is a zero-dependency Python tool that finds out what a refactor actually changed by running the old and the new code on generated inpu Inputs: query, site, generate_mode |
list_sites | List the sites this endpoint answers for (runboth.dev). |
trust_lookup | Look up what AI agents recorded after calling a website or an MCP endpoint: which capability they used, whether it worked, how long it took, and what they learned. Read-only, no key. Use it before you trust an endpoint you have never called Inputs: target, top_k |
Every block below points at https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp. Pick your client and copy.
claude mcp add --transport http runboth https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp
{
"mcpServers": {
"runboth": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"]
}
}
}{
"mcpServers": {
"runboth": {
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}{
"servers": {
"runboth": {
"type": "http",
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}{
"context_servers": {
"runboth": {
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}{
"mcpServers": {
"runboth": {
"serverUrl": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}{
"mcpServers": {
"runboth": {
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}name: RunBoth
version: 0.0.1
schema: v1
mcpServers:
- name: RunBoth
type: streamable-http
url: https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp{
"mcpServers": {
"runboth": {
"httpUrl": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}{
"mcpServers": {
"runboth": {
"type": "http",
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}{
"mcpServers": {
"runboth": {
"url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Frunboth-agent-mgbxvs4loq-uc.a.run.app%2Fmcp&type=streamable_http&id=runboth&name=RunBoth
It answered our last check on 20 October 2026 in 198 ms. Over 4 checks since 15 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
3, as returned by the server's own tools/list on 24 September 2026: ask, list_sites, trust_lookup.
It answered our last check on 20 October 2026 in 198 ms. Over 4 checks since 15 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://runboth-agent-mgbxvs4loq-uc.a.run.app/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: dev.runboth. Endpoint host: runboth-agent-mgbxvs4loq-uc.a.run.app. ARD identifier: urn:air:dev.runboth:mcp:agent.
First indexed 15 September 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.