A
licenseNot graded
qualityC
maintenanceEnables durable agent session transfer between machines by serializing state, provisioning sandboxes, and metering costs via MCP tools over a Postgres-backed state machine.
2 npm
MIT
Hibernation capsule for rarely-run agents
Server Details
Hibernation capsule for rarely-run agents. $9/wake.
Ownership verified
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- ChatGPT
- –
- Claude
- –
TDQS
B3.4/5.0
Scored across 11 tools
Disambiguation4/5
Most tools target clearly distinct resources or actions, and the detailed descriptions make boundaries largely inferable. The main ambiguity is among hib_run_wake, hib_execute_wake, and hib_run_deferred, which all concern wake execution and could be misselected without careful reading.
Naming Consistency5/5
All tools use a consistent hib_ prefix followed by a predictable verb_noun pattern such as get_capsule, list_wakes, resolve_wake, and run_deferred. The naming is uniform and readable throughout.
Tool Count5/5
With 11 tools, the surface is well within the appropriate range for a capsule-and-wake lifecycle service. Each tool appears to serve a distinct operational purpose, with no obvious redundant filler tools.
Completeness4/5
The tool set covers capsule creation, retrieval, listing, wake execution, deferred execution, review queue handling, resolution, and usage metering. Minor lifecycle gaps exist, such as no explicit capsule deletion/revocation or wake cancellation, but these may be intentionally unsupported and do not block core workflows.
Available Tools
11 toolshib_capture_capsuleBInspect
Capture + seal an expectations capsule at sleep time (same operation as POST /capsules): tool contracts, credential references + expiry (raw secrets are refused), model pin, behaviour payload, attestation-only assumptions. Returns the sealed capsule and its capsule_id.
Inputs: tools (required), summary (required), model_pin (required), slept_day (required), +4 more.
hib_execute_wakeBInspect
Probationary-gate execution on one wake: blocked (error result) until the tool's dependent checks PASS/ACCEPTED; executes exactly once per idempotency_key
Inputs: tool (required), wake_id (required), idempotency_key (required), arguments.
hib_get_capsuleCInspect
Get one of your capsules by capsule_id
Inputs: capsule_id (required).
hib_get_review_queueCInspect
Your operator review queue: open deltas across your wakes
Inputs: no named parameters.
hib_get_usageBInspect
Your usage: capsule count, storage metering, Fleet wakes used, trial state
Inputs: no named parameters.
hib_get_wakeBInspect
Get one of your wakes: status, briefing and its execution log
Inputs: wake_id (required).
hib_list_capsulesBInspect
List your own capsules (other operators' capsules are never included)
Inputs: no named parameters.
hib_list_wakesBInspect
List your own wakes
Inputs: no named parameters.
hib_resolve_wakeAInspect
Review queue resolution for one wake: action accept (accept a DRIFT / RETIRED / BEHAVIOUR-DRIFT / ATTESTATION-REQUIRED delta) or renew (record a credential renewal with new_ref + new_expires_day; the renewed credential must be attested under new_ref in the wake's world descriptor and the service judges that attested descriptor; REVOKED-DEAD is terminal and refused)
Inputs: action (required), wake_id (required), check_id (required), new_ref, +2 more.
hib_run_deferredCInspect
Run the deferred tier of one of your wakes and return the updated briefing
Inputs: wake_id (required).
hib_run_wakeBInspect
Run the wake gauntlet for a capsule against a presented world descriptor (same operation as POST /wakes): the seal is verified before billing and before any world evaluation; billing is trial (first capsule's first wake) then Fleet inclusion then x402 - for a paid wake send the x402 payment in the X-PAYMENT header of the MCP HTTP request; with no cover and no payment the full 402 challenge is returned as an error result. Returns the wake briefing with the verdict-distribution receipt.
Inputs: world (required), wake_day (required), capsule, capsule_id, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Wake-ups, webhook inboxes, TTL memory, watches and human approval for agents. Paid per call.
Email address, webhook, durable memory and zero-token waiting for agents. Paid in USDC via x402.
Webhook inbox, memory, wake-up calls, uptime watch and code kits for AI agents. Prepaid balance.
Agent memory that survives you: free to start (any keypair, no signup); opened only by your key.
Related MCP Servers
- AlicenseAqualityDmaintenanceEphemeral MicroVM-isolated code execution for AI agents. Run Python, Node, or bash — fresh hardware-isolated VM per call, hard-purged after. No state persists between calls.1849 npmMIT
- AlicenseNot gradedqualityCmaintenanceAutonomous Cloud GPU Spot Bursts (rent_gpu_burst_arbitrage): Scans wholesale spot orderbooks (RTX 3090, RTX 4090, A100, H100) and provisions on-demand 3-minute compute bursts ($0.0500 USDC) with an automated 180-second idle deadman destruction switch and warm-pool multi-agent reuse.MIT
- AlicenseBqualityBmaintenanceDurable execution for AI agents — worker death triggers supervisor orphaning and standby resume from the last checkpoint, zero rework.181MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.