Citeguard is answering right now. Last checked 27 min ago. 64 installs a week from npm. It exposes 3 tools. Last commit 8 Aug 2026.
Verify citations in AI text: fetches each cited source, returns verdicts with evidence quotes.
Today is the operative word: we check Citeguard every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 27 min ago.
claude mcp add citeguard --transport http https://citeguard.boundy.workers.dev/mcp
{
"mcpServers": {
"citeguard": {
"url": "https://citeguard.boundy.workers.dev/mcp"
}
}
}
[mcp_servers.citeguard]
url = "https://citeguard.boundy.workers.dev/mcp"
{
"mcpServers": {
"citeguard": {
"url": "https://citeguard.boundy.workers.dev/mcp"
}
}
}
{
"mcpServers": {
"citeguard": {
"url": "https://citeguard.boundy.workers.dev/mcp"
}
}
}
This one needs environment variables set before it will start:
CITEGUARD_JUDGE_PRESET (LLM judge preset: qwen | openai | anthropic), CITEGUARD_JUDGE_KEY (API key for the judge LLM (required for verify_claims/check_document; check_links works without it)).
The author declared them in the registry entry; get the values from the project itself.
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
check_document
check_links
verify_claims
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://citeguard.boundy.workers.dev/mcp | streamable-http | answering | 167 ms | 27 min ago |
Search scholarly sources, verify references, and export citations with traceable evidence.
Food verification for people and AI agents: evidence-backed verdicts, with sources and dates.
Christian source evidence for AI agents, with provenance, tradition coverage, and citation checks.
Research stocks and futures with quotes, charts, news, scans, and source-backed evidence.
Evidence-backed web research for AI agents with citations and confidence scores.
Evidence-backed decision briefs with citations — recommendation, confidence, risks, sources.
Verified reference data; each record carries its source URL and quote. verify_quote checks claims.
Pre-install security scans for npm packages, MCP servers, and AI agents with cited verdict evidence.
Answers built from our own checks of this server.