About Ayiru
Ayiru is an MCP server published by ruth411 in the Agents category: verified, machine-readable safety verdicts for AI agents running shell commands. Append-only audit log, six verification levels, deterministic risk engine. MIT.
The repository has 2 stars and 0 forks, with the last commit 2 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
git clone https://github.com/ruth411/ayiruThis 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 (7)
get_capabilitiesTyped `CapabilityRecord` rows — invocations, configs, constraints, effects
Parameters not published.
get_constraintsTyped constraint records — auth scopes, env preconditions, deprecation
Parameters not published.
get_effectsTyped effect profile — destructive / mutates_remote_state / reversible booleans
Parameters not published.
get_subject_specFull `SubjectSpec` for a known `subject_id`
Parameters not published.
get_workflow_planGoal-matched workflow plans, safest-first
Parameters not published.
resolve_actionEnd-to-end grounding — top capability + constraints + effects + risk verdict
Parameters not published.
resolve_subjectTyped `SubjectSummary` records from a fuzzy hint. **Call this first.**
Parameters not published.
Ask AI
Ask AI about Ayiru
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.