HandoffOS
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingest_eventC | Ingest an enterprise event and recalculate the workflow state. |
| detect_blockersC | Detect deterministic workflow blockers with evidence and risk breakdowns. |
| simulate_resolutionA | Simulate a workflow resolution without changing live workflow state. |
| plan_next_actionsC | Plan evidence-backed actions that require approval before execution. |
| execute_actionB | Execute an approved planned action and recalculate the live workflow. |
| escalate_blockerC | Prepare an evidence-backed escalation for the workflow root blocker. |
| predict_completionB | Forecast deterministic completion timing and identify critical-path delay drivers. |
| compare_workflowsB | Compare health, root blockers, and completion forecasts across active workflows. |
| rollback_actionC | Restore the snapshot before the last approved state-changing action. |
| what_if_multiB | Simulate resolving multiple workflow nodes without changing the live workflow. |
| export_audit_reportC | Export a structured JSON and Markdown audit report for a workflow. |
| verify_audit_integrityB | Verify the tamper-evident SHA-256 audit chain for a workflow. |
| reset_demoB | Reset the in-memory demo workflows and subscriptions to their deterministic seed state. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| explain_blocker | Explain a blocker using only findings and evidence supplied by HandoffOS resources. |
| manager_summary | Create a concise evidence-grounded manager summary for a workflow. |
| escalation_email | Draft an escalation email using only the escalation tool output and workflow evidence. |
| executive_digest | Create a one-paragraph leadership digest from deterministic workflow comparisons. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| HandoffOS Workflow Catalog | All active workflow IDs with deterministic health and completion summaries. |
| Priya Onboarding Workflow State | Current workflow state for Priya Nair onboarding. |
| Priya Onboarding Events | Enterprise events used to reconstruct Priya Nair onboarding. |
| Priya Onboarding Findings | Deterministic blocker findings and evidence references. |
| Priya Onboarding Audit Log | Tamper-evident audit records for Priya onboarding. |
| Vendor Onboarding Workflow State | Current workflow state for Acme vendor onboarding. |
| Vendor Onboarding Events | Source events for the vendor workflow. |
| Vendor Onboarding Findings | Deterministic findings for vendor onboarding. |
| Vendor Onboarding Audit Log | Tamper-evident audit records for vendor onboarding. |
| HandoffOS Rules | Deterministic workflow rules used to create findings. |
| Health Checks | Current health status of all registered health checks |
| Handoff Dashboard | UI component for Handoff Dashboard |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
TDQS
Scored across 13 tools
Most tools are distinct, but what_if_multi and simulate_resolution both simulate without changing live workflow state, differing mainly in scope (multi-node vs. single resolution), which could confuse an agent. Other tools are clearly separated by action and resource.
The naming convention is overwhelmingly verb_noun (ingest_event, detect_blockers, execute_action), but 'what_if_multi' breaks the pattern by not starting with a verb. No camelCase or mixed conventions exist, so the inconsistency is minor.
Thirteen tools is well within the optimal 3-15 range and each tool addresses a distinct aspect of workflow management, from simulation and execution to audit and comparison, so the count feels appropriately scoped.
The set covers core workflow operations like simulation, execution, rollback, prediction, and audit, but lacks an explicit approval tool even though plan_next_actions references approvals. Additionally, workflow retrieval is only implicit through compare_workflows, leaving a moderate gap in the lifecycle.