47,545 indexed projects · 74 endpoint candidates · 2 endpoints previously checked ; 301 projects with runtime measurements. Listed projects are not necessarily monitored. Coverage last verified 2026-10-06T23:06:28.946Z. Cached coverage; confirmed live means previously observed, not a current uptime guarantee. UNRATED means not measured.
47,545 projects indexed · Last verified 2026-10-06T23:06:28.946Z. Cached count; live statistics are not checked on this page.
Dominion Observatory compares tool names, descriptions and input schemas between captures of compatible public MCP endpoints. Scheduled monitoring supports email and optional webhook alerts on detected changes. Manifest history is public; new captures are Ed25519-signed, while legacy captures remain unsigned. There is no guaranteed detection interval, and a changed definition alone does not establish a security issue.
Read the monitoring guide · Inspect a synthetic change report
# Fail-closed policy: UNRATED, NOT FOUND, errors and scores below 70 block.
# Requires curl 7.76+ and jq. Set MCP_URL to the intended server URL.
: "${MCP_URL:?Set MCP_URL first}"
if ! response=$(curl --fail-with-body --silent --show-error --get --data-urlencode "url=$MCP_URL" "https://dominionobservatory.com/api/trust"); then
echo "Blocked: registry request failed" >&2; exit 1
fi
if ! printf '%s' "$response" | jq -e '
type == "object" and .found == true and .runtime_measured == true
and (.error == null) and (.trust_score | type == "number")
and (.trust_score >= 70 and .trust_score <= 100)' >/dev/null; then
echo "Blocked: UNRATED, missing, invalid response or below policy" >&2; exit 1
fi
echo "Measured score meets policy; this does not guarantee safety."
This example fails closed. A fail-open policy may log a warning and continue after independent review, but must never label an unknown or failed lookup as a passing trust check.
47,545 projects indexed. Behavioral scores are available only for servers with measured runtime data. Other projects are UNRATED, with a null trust score. Receipts support evidence review; they do not guarantee safety or compliance.
Servers with measured runtime data can receive behavioral scores based on observed reliability. Indexed projects without measurements are UNRATED (not measured). An API error is an unavailable assessment, not a passing result.
Tamper-evident, machine-readable runtime records designed to support audit evidence, internal governance, and applicable record-keeping assessments. Legal compliance depends on your organisation, system classification, and deployment context — a Dominion receipt alone does not establish compliance.
Route any MCP server through Observatory. Trust checks happen transparently. No code changes needed — just change the URL.
Cross-ecosystem reliability baselines built from agent-reported telemetry. Data that ages into compounding value.
Agent Information Optimization — check any MCP server's discoverability to AI agents. Scores llms.txt, agent.json, registry presence, and more. Try it free →
Scan your first server free. CI/monitoring plans for platform teams, and a Compliance tier with signed attestations for audit and vendor-risk reviews. See pricing →
Install a package. Add one line. Trust checks are automatic.
pip install langchain-mcp-trust-gatepip install crewai-dominion-trustpip install openai-agents-trust-gatepython -m pip install dominion-trust-checkTrust scores that moved in the last 72 hours · Feed refreshed 2026-10-07T20:33:12.941Z
Scan one server free. Pay when MCP trust becomes part of how your team ships.
A signed, dated, independently-verifiable trust badge for your README — $29 one-time, self-serve, no sales call.
Get verified — $29 →Run a registry, gateway, or marketplace? License the trust feed and show a trust score on every server you list.
Scan your first server free — no signup. Add it to CI when you're ready.
Scan a Server Free