Crovia — verifiable silence (TACET) and Crovia Seal
Server Details
Signed, Bitcoin-anchored observations of AI training-data disclosure; verifies silence proofs, seals
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- croviatrust/countersign
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Names are largely distinct (status, lookup_model, search_models, silence_report, verify_seal), and the descriptions work hard to draw boundaries, repeatedly stating what each tool is NOT. However, the need for that heavy 'not X, not Y' language reveals genuine overlap: crovia_status vs silence_report (both aggregate totals), and lookup_model vs get_silence_proof (both per-model, with the proof pointer duplicated on lookup_model) can still be confused.
About half the tools use a clean verb_noun pattern (get_silence_proof, lookup_model, search_models, verify_seal), but others deviate: explain is a bare verb, silence_report and crovia_status are noun-first, and crovia_vs_causari is a comparison construct. The 'crovia_' prefix appears on only two tools, so conventions are mixed though still readable.
Eight tools is well-scoped for a verifiable-silence/attestation domain, and each appears to earn its place: status, per-model lookup, catalog search, proof retrieval, seal verification, weekly reports, term definitions, and product differentiation. No obvious redundancy or filler.
The read-only surface covers the core lifecycle well: discovery (search_models), detail (lookup_model), proof retrieval (get_silence_proof), verification (verify_seal), reporting (silence_report), and live totals (crovia_status). Minor gaps exist — no direct way to enumerate epochs or seals beyond per-model lookups — but agents can work around these.
Available Tools
8 toolscrovia_statusLive TACET totalsARead-onlyInspect
Live totals at this moment: epochs closed, epochs anchored in Bitcoin, models on the map, snapshot counts, signed silence proofs, and a pointer to the longest verifiable silence. No parameters. This is not a weekly Silence Report, not one model's record, and not a proof bundle. Reads published files only.
Inputs: no named parameters.
crovia_vs_causariCrovia vs CausariARead-onlyInspect
Which product is which. Crovia observes training-data disclosure. Causari is the code-provenance tool. No parameters. Use this, not explain and not crovia_status, when the question is the difference between the two. Reads no catalog.
Inputs: no named parameters.
explainDefinitionsARead-onlyInspect
The definition of one Crovia term. Allowed terms: tacet, silence, lacuna, seal, epoch, pnx, predicate, canon. Omit term, or pass an empty or blank string, to receive every definition. Any other value is an error listing those allowed terms, and it does not return the definitions. Use crovia_vs_causari, not explain, to tell the two products apart.
Inputs: term.
get_silence_proofOne silence proof or its bundleARead-onlyInspect
The published silence proof for one model: silence_days, observed window, epochs, seal id, URL, and how to verify it. model omitted or empty returns the proof index, not a bundle. include_bundle defaults to false; true attaches the crovia.seal.v1 bundle for that one model and does nothing on the index. This is not the live totals and not the weekly report. Reads published files only.
Inputs: model, include_bundle.
lookup_modelLook up one modelARead-onlyInspect
One model's observation: latest verdict, negative snapshots, anchored epochs, silence proof pointer, archive silence, badge and record URL. Required model is a Hugging Face id, org/name, for example Qwen/Qwen3-32B. An empty model is an error. An exact id is used; otherwise one case-insensitive substring match is accepted, and several matches return candidates instead of a verdict. This is not a catalog page, not the weekly report, and not the seal bytes. Reads published files only.
Inputs: model (required).
search_modelsPage of model idsARead-onlyInspect
A page of observed model ids whose id contains query, compared case-insensitively, in catalog order, not a ranking. query omitted or empty matches the whole catalog and still returns at most limit rows. limit follows the historical rule: a missing, empty, zero or other falsy value is 25; any value int() accepts is then clamped into 1..100 (500 becomes 100, a negative becomes 1); a value int() cannot parse is an error and nothing is searched. returned and its compatibility alias count are the rows in this page. matched is how many ids match before the limit. catalog_total and its compatibility alias total_records are every record in the catalog, matching or not. limit is the limit actually applied. count is not the match count, and total_records is not the match count. This is not a verdict and not a proof. Reads published files only.
Inputs: limit, query.
silence_reportWeekly Silence ReportARead-onlyInspect
One published weekly Silence Report, or the latest report index. week is an ISO week YYYY-Www, for example 2026-W38. Omit week, or pass an empty string, to receive the latest index rather than one week's facts. A week that is not YYYY-Www is an error. A week with no published file is an error and names the index. This is not the live status and not one model's proof. Reads published files only.
Inputs: week.
verify_sealVerify a seal or proofARead-onlyInspect
Check a crovia.seal.v1 object or a wrapped TACET silence proof: signature, canonical bytes, bindings, and per-epoch non-inclusion paths. Pass seal as a JSON object or a JSON string, or url as an https://croviatrust.com/ address. With neither, the call is an error. Supplying url fetches that URL over the network. check_anchors defaults to false; true also checks the drand round bytes and the Bitcoin anchors over the network. A seal object with check_anchors false or omitted is checked from that object alone. This tool can reach the network, so it is not a closed-world call.
Inputs: url, seal, check_anchors.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Bitcoin-anchored, tamper-evident audit-permanence layer for AI agents, FRE 902(13)/(14)-shaped.
Deterministic AI liability attribution with Bitcoin-anchored proof certificates.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Notary for AI agents: seal fingerprints, verify proofs, check mandates. Anchored in Bitcoin.
Related MCP Servers
AlicenseAqualityCmaintenanceBitcoin-anchored provenance for AI outputs; enables stamping, verifying, and tracing outputs with offline-verifiable canonical roots.3Apache 2.0- AlicenseAqualityBmaintenanceAppend-only evidence receipts for AI records: seal, verify, cite, chain-check, anchor status. A seal proves a record existed at a time, not that its contents are true. Five tools over stdio with npx -y apex-psi-mcp — no account, no key, verification free forever.5458 npm1MIT
- AlicenseAqualityBmaintenanceCryptographic receipts for AI outputs — signed, chain-anchored, $0.001/call6107 npmMIT
- AlicenseAqualityBmaintenanceThe open registry of AI agents. Every agent gets a free birth certificate (a number and a date) and can timestamp what it creates, or only its SHA-256, with an RFC 3161 timestamp and a Bitcoin anchor that anyone can verify without us. Free, no account.11MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.