Widget-storage residue verdict
Server Details
Per-widget x per-host browser-storage residue verdict, hash-only census, verified-clear receipt.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
The tools operate at different granularities: census for per-server/per-origin residue inventory, matrix for one widget across five hosts, and probe for a single widget-host write attempt. Census and matrix both produce aggregate storage verdicts, so there is slight potential for misselection, but the descriptions make the intended scope reasonably clear.
All three tools use a consistent storage_ prefix followed by a clear noun (census, matrix, probe). The pattern is predictable and readable.
Three tools is well-scoped for a narrow storage-residue verdict service. Each tool corresponds to a distinct assessment tier without unnecessary bloat.
The surface covers single widget-host probing, one-widget-across-five-hosts matrixing, and broader census/receipt functionality. Minor gaps remain, such as arbitrary multi-widget probing or explicit enumeration of available servers/hosts, but core verdict workflows are covered.
Available Tools
3 toolsstorage_censusCInspect
Residue census + verified-clear receipt ($4.99): hash-only census per server x host origin; clear:true adds the re-read-verified signed receipt
Inputs: host (required), server_id (required), clear.
storage_matrixDInspect
Full storage matrix ($3.99; watch allowance applies): 1 widget x 5 hosts with per-host verdicts
Inputs: widget (required), server_id (required).
storage_probeCInspect
Single widget x host storage probe ($0.99; one free trial per operator ever): PERSISTS-KEYED / EPHEMERAL / FORBIDDEN-THROWS graded from profile state after a real write attempt
Inputs: host (required), widget (required), server_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event.
Per-principal census of MCP subscriptions and durable tasks, with verified-stop receipts.
Per-dataset granularity verdicts keyed to the dataset's own manifest hash, before you pay.
The record of what the agent relied on: a signed, chained receipt per cleared read. Verify by id.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to capture and hash-register browser evidence, enforce cite-or-fail claim checks against registered bytes, and export Merkle-rooted evidence bundles that other agents can re-verify fully offline.26 npm-
- AlicenseNot gradedqualityCmaintenanceEnables MCP hosts to batch known repository reads, literal searches and Git inspections, summarize noisy command output into compact diagnostics, and recover captured stdout/stderr bytes through bounded, expiring evidence receipts. Optional guarded TypeSafe decisions select among validated candidate actions or escalate to the current host, while deterministic local reads run without a key and never send repository contents externally.MIT
- AlicenseBqualityBmaintenanceSigned receipts for agent actions and a read-only-allowlist decision gate, as an MCP server. Ed25519, plus ML-DSA-65 when the post-quantum backend is available. gate_decision returns ALLOW, DENY or ESCALATE from action names and does not observe or block anything. verify_receipt takes expected_kid to pin which key signed. Seven tools.1650 PyPIApache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables agent-neutral MCP clients to inspect native T3 inventory and results, persist signed events, perform explicit bounded delegation, and retain durable auditable receipts.AGPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.