← Index

Sequesign

io.github.Sequesign/sequesign·v0.2.0·Other

Cryptographically verifiable receipts of an agent's delegated work, verified offline.

Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

Environment variables
SEQUESIGN_MODE

Transport: 'direct' (default; sign locally, an independent witness co-signs) or 'managed' (route through the Sequesign broker for a registered identity).

SEQUESIGN_API_KEY
secret

Sequesign write-class API key (from the dashboard). Required for managed mode; in direct mode it authenticates the hosted witness.

SEQUESIGN_AGENT_PRIVATE_KEY
secret

Ed25519 PKCS#8 private-key PEM for the agent. In managed mode, the key registered to your API key. In direct mode, omit to mint an ephemeral key per session.

SEQUESIGN_PACKAGE_DIR

Directory where sealed receipt packages are written. Defaults to a temporary directory.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
5
Alternatives in Other