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.

Groundhog

PYPI · GROUNDHOG-MCP · SCANNED SEP 20

Search, read and research the web, with hidden text stripped by default and sources hashed

Available components

+15 this week 84 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 3 of 54 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 738 tokens (~184/item across 4 items; 4 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 Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 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
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Groundhog MCP server?

Groundhog runs locally as a PyPI package, launched with uvx groundhog-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · groundhog-mcp

# add to Claude Code
claude mcp add dmytrome-groundhog-mcp -- uvx groundhog-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "dmytrome-groundhog-mcp": {
      "command": "uvx",
      "args": [
        "groundhog-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "dmytrome-groundhog-mcp": {
      "command": "uvx",
      "args": [
        "groundhog-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add dmytrome-groundhog-mcp -- uvx groundhog-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dmytrome-groundhog-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "groundhog-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add dmytrome-groundhog-mcp --command uvx --arg groundhog-mcp
# ~/.hermes/config.yaml
mcp_servers:
  dmytrome-groundhog-mcp:
    command: "uvx"
    args: ["groundhog-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "dmytrome-groundhog-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "groundhog-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add dmytrome-groundhog-mcp -t stdio -c uvx -a groundhog-mcp
// mcp.json
{
  "mcpServers": {
    "dmytrome-groundhog-mcp": {
      "command": "uvx",
      "args": [
        "groundhog-mcp"
      ]
    }
  }
}
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.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 0
    • Stability: 0.90 → unverified security
    • Tool safety: pass → unverified security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Package version: 0.15.0 → 0.16.1 functional
  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +12
    • Malware scan: unverified → pass security
    • Stability: pass → 0.80 functional
  • 14 Sept 26 0
    • Stability: 0.97 → pass security
  • 13 Sept 26 −14
    • Malware scan: pass → unverified security
    • Package version: 0.14.0 → 0.15.0 functional
  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

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 · Analysed pypi/groundhog-mcp@0.16.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 54 packages
Packages resolved 54
Stale 2
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~738 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
read_url ~264

Fetch one web page through the stealth browser and return clean, grounded content with provenance. Hidden text injected for models but invisible to humans is stripped by default and reported in `threats`. Use this to ground answers in live web content, including sites that block plain fetchers. Reads a URL you already have: use `search` to find URLs, or `research` to search and read in one call. Fetches are rate limited per domain (5s apart by default), so several pages from one site are not instant.

NameTypeReqDescription
formatstring'markdown' extracts the article; 'text' returns the page's rendered text.
include_hiddenbooleanKeep text that is invisible to a human reader. It is reported in `threats` either way; this only controls whether it stays in the content.
max_tokensToken budget for the content. Omit to use the server's GROUNDHOG_MAX_TOKENS (20000 by default). Must be positive.
queryWhen set, `matches` carries the passages most relevant to it, each with its heading and offset for citation.
urlstringyesAbsolute http(s) URL. Private and loopback addresses are refused.
NameTypeReqDescription
fetched_atstringyes
final_urlstringyes
http_statusyes
markdownstringyes
matchesarrayyes
provenanceyes
set_asideintegeryes
statusstringyes
threatsarrayyes
titlestringyes
truncatedbooleanyes
urlstringyes

No examples provided.

research ~251

Search the web and return ranked passages drawn from several sources. One call does what `search` + repeated `read_url` would: finds pages, reads them through the stealth browser, and returns the passages most relevant to `query` — each attributed to its source, with that source's provenance receipt and any stripped injection payloads. A source that fails is reported in `sources` rather than failing the whole call. Prefer `read_url` when you already have the URL, and `search` when you only want links. This reads `max_sources` pages, rate limited per domain, so it is the slowest of the three and the one to avoid for a single known page.

NameTypeReqDescription
max_sourcesintegerHow many pages to read. Values outside 1-10 are clamped rather than rejected. Each source is a full page fetch, so this is the main cost and latency control.
max_tokensToken budget for the returned passages. Omit to use the server's GROUNDHOG_MAX_TOKENS (20000 by default). Must be positive.
querystringyesThe question to research. Passages are ranked against it.
NameTypeReqDescription
backendstringyes
passagesarrayyes
querystringyes
sourcesarrayyes
truncatedbooleanyes

No examples provided.

search ~174

Search the web and return ranked hits (title, url, snippet, engine). Not for reading: it returns links, never page content. Use `read_url` for one known URL, or `research` when you want the answer rather than the links. Use this to find pages, then pass the URLs you want to `read_url` for safe, grounded content. Results come from a self-hosted SearXNG instance when `SEARXNG_URL` is set, otherwise from a search page rendered through the stealth browser. Hits are links only — nothing is fetched until you ask.

NameTypeReqDescription
limitintegerHow many hits to return. Values outside 1-25 are clamped rather than rejected.
querystringyesWhat to search for. Must not be empty.
NameTypeReqDescription
backendstringyes
hitsarrayyes
querystringyes

No examples provided.

status ~49

Check whether Groundhog can reach the stealth browser. Call this to diagnose setup before fetching: if `browser_reachable` is false, follow `hint` to start the browser, then retry.

Input schema present but exposes no named parameters.

NameTypeReqDescription
browser_reachablebooleanyes
cdp_urlstringyes
hintyes

No examples provided.

Common questions

What is the Groundhog MCP server?

Groundhog is an MCP server listed in the public MCP registry as io.github.dmytrome/groundhog-mcp. Search, read and research the web, with hidden text stripped by default and sources hashed. This page covers its PyPI package (groundhog-mcp).

Is the Groundhog MCP server safe to use?

Groundhog scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. 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 Groundhog MCP server expose?

Groundhog exposes 4 tools: read_url, research, search, status. Their descriptions and schemas cost roughly 738 tokens of context every time the server is loaded.

Is the Groundhog MCP server still maintained?

Groundhog 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.