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/azmartone67/dchub-mcp-serverWrote 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/plugins/azmartone67/dchub-mcp-server/gemini-extension)<a href="https://agentmods.dev/plugins/azmartone67/dchub-mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/azmartone67/dchub-mcp-server/gemini-extension/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/plugins/azmartone67/dchub-mcp-server/gemini-extension"><img src="https://agentmods.dev/badge/plugins/azmartone67/dchub-mcp-server/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dchub 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 5d 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
{
"name": "dchub",
"version": "2.12.37",
"description": "Live data center market, power/grid, energy and fiber intelligence for site selection — 94 tools.",
"mcpServers": {
"dchub": {
"httpUrl": "https://dchub.cloud/mcp"
}
},
"contextFileName": "GEMINI.md"
}
What ships with it
48 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/agent_beat.sh 4.9 KB runs code
- scripts/canon-floor.mjs 10 KB runs code
- scripts/canon-freeze.mjs 4.2 KB runs code
- scripts/chatgpt-test-cases.mjs 5.4 KB runs code
- scripts/check-served-manifest.mjs 8.5 KB runs code
- scripts/claude_directory_listing.txt 5.7 KB
- scripts/cloud.dchub.distribution.plist 1.7 KB
- scripts/cloud.dchub.rank-probe.plist 1.9 KB
- scripts/cloud.dchub.smithery-freshness.plist 1.6 KB
- scripts/distribution_master_shell.sh 4.9 KB runs code
- scripts/distribution_radar.py 5.4 KB runs code
- scripts/dxt-bundle.mjs 8.7 KB runs code
- scripts/ecosystem-sync.mjs 66 KB runs code
- scripts/emit-pack-manifests.mjs 7.2 KB runs code
- scripts/hard-gate-no-network.mjs 2.8 KB runs code
- scripts/hooks/pre-commit 1.9 KB
- scripts/install-hooks.mjs 2.2 KB runs code
- scripts/install-prepush-gate.sh 1.1 KB runs code
- scripts/introspect_probe.py 1.4 KB runs code
- scripts/listing-canon.mjs 8.6 KB runs code
- scripts/listing-copy.mjs 10 KB runs code
- scripts/prepush-gate.mjs 6.1 KB runs code
- scripts/probe-chatgpt-directory.mjs 11 KB runs code
- scripts/rank_defense_master_shell.sh 11 KB runs code
- scripts/refresh-canon-phrases.mjs 13 KB runs code
- scripts/refresh-listing.mjs 1.9 KB runs code
- scripts/refresh-problem-taxonomy.mjs 8.2 KB runs code
- scripts/refresh-tier-limits.mjs 10 KB runs code
- scripts/refresh-tool-maturity.mjs 12 KB runs code
- scripts/refresh-toolspec.mjs 6.1 KB runs code
- scripts/registry_monitor.py 103 KB runs code
- scripts/registry_stale_guard.py 6.5 KB runs code
- scripts/registry_version_bump_guard.py 9.3 KB runs code
- scripts/registry-autopublish.mjs 7.6 KB runs code
- scripts/registry-description.mjs 8.7 KB runs code
- scripts/registry-discover.mjs 31 KB runs code
- scripts/registry-pr-submit.mjs 41 KB runs code
- scripts/registry-verify-listed.mjs 13 KB runs code
- scripts/server-json-baseline.mjs 7.3 KB runs code
- scripts/smithery_description.txt 868 B
- scripts/smithery_drift_guard.py 10 KB runs code
- scripts/smithery-freshness-heartbeat.sh 7.4 KB runs code
- scripts/sync_cf_worker_manifest.py 20 KB runs code
- scripts/sync-tools-manifest.mjs 85 KB runs code
- scripts/tier3_presence.sh 6.3 KB runs code
- scripts/verify_smithery_converged.py 8.3 KB runs code
- scripts/verify-release-bundle.mjs 3.6 KB runs code
- scripts/web_bot_auth.py 6.6 KB runs code
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.
- 5d ago Changed bef59f689a1e
- 6d ago Changed c70706c7e49b
- 7d ago Changed 451384ec03f5
- 8d ago Changed 762e9a1d2fbb
- 10d ago Changed 039e320b3f27
- 12d ago Changed 4ec7ce250da9
- 15d ago First seen · 12 lines scan A 282a9e6227a0
dchub is a plugin published in the GitHub repository azmartone67/dchub-mcp-server (3 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-04.
Other plugins, from other repositories
secedgar-mcp-server
Query SEC EDGAR filings, XBRL financials, and company data via MCP. STDIO or Streamable HTTP.
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
kadam
Kadam ad network — manage campaigns, creatives, audiences, bids, and analytics via AI.
claude-webcache
Cross-session WebFetch cache for Claude Code. WebFetches disappear after 15 minutes — claude-webcache makes them persist.
wikimoth
Deterministic, token-minimal memory for Claude Code: capture each session as a [[wikilink]] note (edges computed by code, not a model) and recall connected notes at boot.
linkedctl
LinkedIn API toolkit — MCP server and workflow guidance for Claude Code.