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/statzhero/zotero-fulltextWrote 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/statzhero/zotero-fulltext/zotero)<a href="https://agentmods.dev/mcp/statzhero/zotero-fulltext/zotero"><img src="https://agentmods.dev/badge/mcp/statzhero/zotero-fulltext/zotero/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/statzhero/zotero-fulltext/zotero"><img src="https://agentmods.dev/badge/mcp/statzhero/zotero-fulltext/zotero.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
zotero 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 9d 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
{
"zotero": {
"command": "uvx",
"args": [
"zotero-fulltext"
],
"env": {
"ZOTERO_LIBRARY_TYPE": "${ZOTERO_LIBRARY_TYPE:-user}",
"ZOTERO_LIBRARY_ID": "${ZOTERO_LIBRARY_ID:-0}",
"ZOTERO_API_BASE_URL": "${ZOTERO_API_BASE_URL:-http://127.0.0.1:23119/api}",
"ZOTERO_API_KEY": "${ZOTERO_API_KEY:-}",
"ZOTERO_CACHE_DIR": "${ZOTERO_CACHE_DIR:-~/.cache/zotero-fulltext}"
}
}
}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.
- 9d ago First seen · 15 lines scan A 6aee24f91af6
zotero is an MCP server published in the GitHub repository statzhero/zotero-fulltext (0 stars, last pushed 1mo 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
zotero-mcp
Model Context Protocol server for Zotero. Runs locally from the zotero-mcp Python package. Needs 4 environment variables to run.
mcp-server-zotero-dev
MCP server enabling AI assistants to build, test, and debug Zotero plugins. Runs locally from the @introfini/mcp-server-zotero-dev npm package. Needs 2 environment variables to run.
cite-caddy
Remote MCP server for full read/write access to a Zotero library. Remote server at citecaddy.herbertkokholm.dk.
zotero-mcp
Model Context Protocol server for Zotero. Runs locally from the zotero-mcp Python package.
strata
MCP server for progressive tool usage at any scale (see https://klavis.ai). Remote server at strata.klavis.ai.
adeu
MCP server "adeu" as configured in dealfluence/adeu. Runs locally from the adeu-server Python package.