About signet-eval
signet-eval is an MCP server published by wandercom in the Communication category: deterministic policy enforcement and MCP management for AI agent tool calls.
The repository has 4 stars and 2 forks, with the last commit 11 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/wandercom/signet-evalThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (17)
signet_add_ruleAdd a new rule (appended after locked rules)
Parameters not published.
signet_condition_helpShow available condition functions
Parameters not published.
signet_delete_credentialDelete a credential
Parameters not published.
signet_edit_ruleModify rule properties (refuses on locked rules)
Parameters not published.
signet_list_credentialsList credential names
Parameters not published.
signet_list_rulesShow all rules with locked status
Parameters not published.
signet_recent_actionsShow recent action log
Parameters not published.
signet_remove_ruleRemove a rule (refuses on locked rules)
Parameters not published.
signet_reorder_ruleMove a rule (refuses on locked, prevents placing above locked)
Parameters not published.
signet_reset_sessionClear spending counters
Parameters not published.
Show all 17 tools
signet_set_limitSet a spending limit for a category
Parameters not published.
signet_sign_policyHMAC-sign the policy file
Parameters not published.
signet_statusVault status, spending totals, credential count
Parameters not published.
signet_store_credentialStore a Tier 3 credential
Parameters not published.
signet_testTest a tool call against the current policy
Parameters not published.
signet_use_credentialRequest a credential through capability constraints
Parameters not published.
signet_validateCheck policy for errors
Parameters not published.
Ask AI
Ask AI about signet-eval
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.