Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

RunBoth

REMOTE · RUNBOTH-AGENT-MGBXVS4LOQ-UC.A.RUN.APP · SCANNED SEP 20

Ask runboth.dev in plain language: what RunBoth does, how to install it, and its limits.

59 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 681 tokens (~227/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability check failed: schema churn in the 5 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 1 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the RunBoth MCP server?

RunBoth is a hosted endpoint at https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · runboth-agent-mgbxvs4loq-uc.a.run.app

# add to Claude Code
claude mcp add --transport http dev-runboth-agent 'https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "dev-runboth-agent": {
      "url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dev-runboth-agent": {
      "type": "http",
      "url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.dev-runboth-agent]
url = "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-runboth-agent": {
      "type": "remote",
      "url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dev-runboth-agent --url 'https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  dev-runboth-agent:
    url: "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dev-runboth-agent": {
      "Transport": "http",
      "Url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
    }
  }
}
# add to Vellum
assistant mcp add dev-runboth-agent -t streamable-http -u 'https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp'
// mcp.json
{
  "mcpServers": {
    "dev-runboth-agent": {
      "type": "http",
      "url": "https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 16 Sept 26 −2
    • Stability: unverified → fail security
    • A breaking change shipped without a version bump: still 1.0.0 security
    • Tool “who” was removed security
    • The server rewrote its instructions, which are the text every model session reads security
    • The server changed its declared name: nlweb-mcp-server → runboth.dev security
    • Tool “ask” rewrote its description, which is the text the model reads security
    • Tool “list_sites” rewrote its description, which is the text the model reads security
    • Schema quality: pass → fail functional
    • New tool “trust_lookup” functional
    • “ask” reworded the description of “query” cosmetic
  • 15 Sept 26 61

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.a.run.app CN=WR2,O=Google Trust Services,C=US 4 Sept 2026 27 Nov 2026 ECDSA 256 SHA256-RSA a6993fec773504b312550b7de9609011
SANs: *.a.run.app, run.app, *.africa-south1.run.app, *.asia-east1.run.app, *.asia-east2.run.app, *.asia-northeast1.run.app, *.asia-northeast2.run.app, *.asia-northeast3.run.app, *.asia-south1.run.app, *.asia-south2.run.app, *.asia-southeast1.run.app, *.asia-southeast2.run.app and 93 more
CN=WR2,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7ff005a07c4cded100ad9d66a5107b98
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of runboth-agent-mgbxvs4loq-uc.a.run.app. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
run.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp Verified 200
http (plaintext) http://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp HTTPS enforced 302 https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp
MCP tools · 3 exposed · ~367 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ask ~240

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 inputs and comparing seven behaviour channels, rather than reading the diff. Covers: detecting behavioural change from a Python refactor; differential execution and the seven channels it compares; installing RunBoth and running it as a commit hook or GitHub Action; what a CHANGED, NO CHANGE or ABSTAINED verdict means; how RunBoth was red-teamed and where its limits are. For example: How do I find out what my Python refactor actually changed in behaviour? Answers come back as ranked pages from runboth.dev with a URL, a score and a one-line reason each.

NameTypeReqDescription
generate_modestringThe type of response to generate
querystringyesThe question, in plain language. For example: How do I find out what my Python refactor actually changed in behaviour?
sitearrayOptional list of sites to search. If not provided, searches all configured sites

No output schema declared.

No examples provided.

list_sites ~20

List the sites this endpoint answers for (runboth.dev).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

trust_lookup ~107

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, including this one.

NameTypeReqDescription
targetstringyesA domain or endpoint URL, for example runboth.dev or https://host/mcp
top_kintegerHow many records to return, 1 to 25

No output schema declared.

No examples provided.

Common questions

What is the RunBoth MCP server?

RunBoth is an MCP server listed in the public MCP registry as dev.runboth/agent. Ask runboth.dev in plain language: what RunBoth does, how to install it, and its limits. This page covers its hosted endpoint (https://runboth-agent-mgbxvs4loq-uc.a.run.app/mcp).

Is the RunBoth MCP server safe to use?

RunBoth scores 59 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the RunBoth MCP server expose?

RunBoth exposes 3 tools: ask, list_sites, trust_lookup. Their descriptions and schemas cost roughly 367 tokens of context every time the server is loaded.

Does the RunBoth MCP server require authentication?

No. We connected to RunBoth without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the RunBoth MCP server still maintained?

RunBoth is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.