Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/PROJECT-B-26/groundroute-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/project-b-26/groundroute-mcp/web-search)<a href="https://agentmods.dev/mcp/project-b-26/groundroute-mcp/web-search"><img src="https://agentmods.dev/badge/mcp/project-b-26/groundroute-mcp/web-search/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/project-b-26/groundroute-mcp/web-search"><img src="https://agentmods.dev/badge/mcp/project-b-26/groundroute-mcp/web-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
web-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{ "web-search": { "url": "https://api.groundroute.ai/mcp", "type": "streamable-http" } }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 6 lines scan A 53d0a8e9aac3
web-search is an MCP server published in the GitHub repository PROJECT-B-26/groundroute-mcp (1 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
web-search
Live web search and clean-markdown page fetch over the Keenable web index. Runs locally from the @keenable/mcp npm package. Needs 1 environment variable to run.
openai-responses-mcp
Lightweight MCP server (Responses API core). OpenAI integration + websearch. Runs locally from the openai-responses-mcp npm package.
mcp-serp
MCP Server for Google SERP Search via AceDataCloud API. Runs locally from the mcp-serp Python package. Needs 1 environment variable to run.
deep-web-research-mcp
High-quality multi-source web research MCP server: deep-research pipelines, Wikipedia, arXiv, Hacker News, Stack Exchange, Crossref, Brave, Tavily, and any URL on the web. Runs locally from the deep-web-research-mcp Python package.
trawlia-mcp
Web search and page extraction for agents, returned as readable text rather than raw JSON. Runs locally from the trawlia-mcp npm package. Needs 2 environment variables to run.
local-websearch-mcp
MCP server "local-websearch-mcp" as configured in kefyusuf/local-websearch-mcp. Runs locally from the local-websearch-mcp npm package.