A local tool that searches the live web, fetches pages, and packages cited evidence for AI models. It connects through MCP, a standard way for AI tools to use external services.

Research tasks that need current web information, fetched page content, and cited supporting evidence.

It reduces the need to manually search, open, and collect sources before asking an AI to answer a question. It also keeps the collected evidence within a token limit.

grounder — MCP server for Claude Code and Codex by rozetyp

Install

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.

Clone the repo

git clone --depth 1 https://github.com/rozetyp/grounder-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/rozetyp/grounder-mcp/grounder.svg)](https://agentmods.dev/mcp/rozetyp/grounder-mcp/grounder)

Your own site

<a href="https://agentmods.dev/mcp/rozetyp/grounder-mcp/grounder"><img src="https://agentmods.dev/badge/mcp/rozetyp/grounder-mcp/grounder.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

grounder 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 7d 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.

server.json · 11 lines

What it actually says

{
  "grounder": {
    "command": "uvx",
    "args": [
      "grounder-mcp"
    ],
    "env": {
      "GROUNDER_API_KEY": ""
    }
  }
}

Changes

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.

7d ago First seen · 11 lines scan A 5e598bde5586

Subscribe to this mod's changes

grounder is an MCP server published in the GitHub repository rozetyp/grounder-mcp (0 stars, last pushed 25d 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.

LLM Research ai-agents claude cursor grounding lm-studio

local-history

MCP server "local-history" as configured in xxczaki/local-history-mcp. Runs dist/index.js with node. Needs 1 environment variable to run.

xxczaki/local-history-mcp · not measured

chrome-mcp-server

MCP server "chrome-mcp-server", hosted remotely at 127.0.0.1, as configured in iloveitaly/llm-ide-rules.

iloveitaly/llm-ide-rules · not measured

stripe

Stripe's hosted MCP server: lets the agent work with customers, products, prices and payment links. Remote server at mcp.stripe.com.

iloveitaly/llm-ide-rules · not measured

greedy-token

MCP server "greedy-token" as configured in svasenkov/greedy-token. Launched with greedy-token-mcp. Needs 1 environment variable to run.

svasenkov/greedy-token · not measured

toolradar

MCP server for Toolradar — search, compare, and get pricing for 8,600+ software tools. Works with Claude Desktop, Claude Code, Cursor, and any MCP-compatible AI assistant. Runs locally from the toolradar-mcp npm package. Needs 1 environment variable to run.

Nadeus/toolradar-mcp · not measured

qobrix-crm-mcp

MCP server "qobrix-crm-mcp" as configured in gca-ltd/qobrix-crm-mcp. Runs locally from the qobrix-crm-mcp npm package.

gca-ltd/qobrix-crm-mcp · not measured