Cyan Eclipse Grantseal
OfficialCyan Eclipse Grantseal is an MCP witness server for sealing grant scopes and minting recomputable scope-use/renewal verdicts.
Seal connect-time grants with granted scopes, connector/agent identity, and Class F/G integration class (
grantseal_seal_grant, metered).Capture exercised scopes from the principal’s runtime for Class F and mint
WITHIN-GRANTorOUT-OF-SCOPE-USEverdicts (grantseal_capture_use; UNVERIFIABLE captures do not meter).Seal renewals, diff them against the original seal, and flag
EXPANDED-AT-RENEWALor no-change (grantseal_seal_renewal, unmetered).Retrieve full verdict records with use facet, named scopes, taxonomy version, and receipt refs (
grantseal_get_verdict).Get a counterparty view with verdict class and named out-of-scope/added scopes only (
grantseal_check).Recompute verdicts offline from exported captures plus taxonomy version (
grantseal_recompute).Export sealed captures and receipt-chain head for independent recomputation (
grantseal_export_captures).Witness only: it does not block, revoke, or enforce; it refuses credential-shaped inputs and does not store credentials.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cyan Eclipse Grantseal seal the scopes my agent was granted at connect"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cyan Eclipse Grantseal
Powered by Cyan Eclipse Technologies — https://cetech.ai
Icon: branding/icon.svg — v3, owner-elected 2026-11-12 (Tap 45). Icongate PASS: legible at 48 px and 32 px (cap 4.94 px @48 · 3.29 px @32).
Grantseal seals the exact permissions an agent or app was granted at connect time, and the permissions it actually exercised as captured in your own agent runtime. If it used a scope it was never granted — or a renewal quietly added scopes — the sealed record names them, and anyone can recompute the verdict from the record itself.
Cyan Eclipse Grantseal is a Model Context Protocol (MCP) server. It witnesses scope grants from the principal's side of the seam: the buyer instruments their own connect flow and their own agent runtime — no connector cooperation is required. At connect, the connect flow presents the grant as accepted: the granted scope set, the connector identity, the agent identity. Grantseal seals that bundle and stamps the record with its integration class.
Two classes, kept honest by construction:
Class F (full) — grant seal + exercised-scope capture from the principal's own agent runtime. Mints diff verdicts: WITHIN-GRANT, or OUT-OF-SCOPE-USE naming the exercised scopes outside the sealed grant.
Class G (grant only) — grant seal alone, where no runtime capture exists for that connector class. Mints GRANT-SEALED and provably cannot mint a use verdict.
Renewals are witnessed at the moment they are presented: a
renewal grant is diffed against the original seal, and added
scopes verdict EXPANDED-AT-RENEWAL naming them, whether or
not they are ever exercised. A capture that cannot be resolved
under the published scope-taxonomy grammar (TAXONOMY.md)
verdicts UNVERIFIABLE — a state of the evidence, never a
party's fault. Use evidence arrives only from the principal-side
runtime capture; records computed from a provider's own logs are
not witnessing, and captures of that provenance are rejected.
Grantseal is a witness, not an enforcement point: it never blocks a call, revokes a token, or polices a scope. Its records may inform a decision the principal takes elsewhere.
Tools
Tool | What it does |
| Seal the scope granted at connect, as presented by the principal-side connect flow. Metered: one op per grant seal (PC-8 pattern). |
| Present an exercised-scope capture from the principal's own agent runtime (Class F only) and mint the diff verdict. Metered: one op per use-window diff; UNVERIFIABLE captures do not meter. |
| Seal a renewal grant and diff it against the original seal at presentation. Unmetered. |
| The full verdict record: verdict, use-verdict facet, named out-of-scope and added scopes, taxonomy version, receipt refs. Unmetered. |
| Counterparty view: verdict class and the names of out-of-scope or added scopes only. Unmetered. |
| Recompute a verdict from exported captures + the taxonomy version, with no service state. Unmetered. |
| Export the sealed captures with the receipt-chain head for independent recomputation. Unmetered. |
No tool accepts a token, key, or credential as an input in any form; a credential-shaped input is refused and the refusal is receipted.
Related MCP server: action-ledger
Custody
The store carries only the sealed scope field set: granted and exercised scope identifiers under the taxonomy, connector and agent identities as presented, timestamps, seals, and the verdict with its named grammar basis. No access tokens, refresh tokens, API keys, or credentials are captured, held, or sealed in any form — not even as digests. No resource contents, no call payloads, no data the scopes were exercised on. Records serve the principal whose side sealed them; there is no cross-principal aggregation surface. Every grant seal, use capture, renewal record, and verdict appends one record to a hash-chained receipt journal, verified at load; a store that fails verification fails closed.
Status
v0.1.0 · built · bench-pending (independent bench requested; builder tests are not a bench verdict) · name "Cyan Eclipse Grantseal" is provisional pending trademark screen · not listed, not offered for sale — review-first standing posture.
Run
python3 server.py # MCP over stdioEnvironment: ECLIPSE_GRANTSEAL_STATE (record store path),
ECLIPSE_GRANTSEAL_RUNTIME_KEYS (principal-side runtime channel
keys, JSON — principal-held in production; the keys in keys/
are test fixtures only).
License
MIT — see LICENSE.
Available Tools
7 toolsgrantseal_capture_useB
Present an exercised-scope capture from the principal's own agent runtime (Class F records only) and mint the diff verdict against the original sealed grant. Captures from any other provenance are rejected. One metered op per use-window diff; UNVERIFIABLE captures do not meter.
Inputs: source (required), runtime_id (required), window_end (required), window_start (required), +4 more.
grantseal_checkC
Counterparty view: the verdict class and the names of out-of-scope or added scopes only. Unmetered.
Inputs: grant_seal_id (required).
grantseal_export_capturesB
Export the sealed captures for a grant (grant capture, latest use capture, renewal records) with the receipt chain head and taxonomy version, for independent recomputation. Unmetered.
Inputs: grant_seal_id (required).
grantseal_get_verdictC
The full verdict record for a grant seal: verdict, use verdict facet, named out-of-scope and added scopes, taxonomy version, receipt refs. Class G records return GRANT-SEALED. Unmetered.
Inputs: grant_seal_id (required).
grantseal_recomputeB
Recompute a verdict from the exported captures plus the taxonomy version, with no service state. Unmetered.
Inputs: grant_capture (required), taxonomy_version (required), use_capture.
grantseal_seal_grantB
Seal the exact scope granted at connect time, as presented by the principal-side connect flow: granted scope set, connector identity, agent identity, and the integration class (F = grant seal + runtime use capture; G = grant seal only). One metered op per grant seal. Grantseal seals the exact permissions an agent or app was granted at connect time, and the permissions it actually exercised as captured in your own agent runtime. If it used a scope it was never granted — or a renewal quietly added scopes — the sealed record names them, and anyone can recompute the verdict from the record itself.
Inputs: agent_id (required), connector_id (required), granted_scopes (required), integration_class (required), +1 more.
grantseal_seal_renewalA
Seal a renewal or re-connect grant and diff it against the original seal at presentation: added scopes verdict EXPANDED-AT-RENEWAL naming them; a renewal that changes nothing records a no-change marker. Renewals do not meter.
Inputs: grant_seal_id (required), renewed_scopes (required), renewal_timestamp.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
The core lifecycle tools (seal_grant, seal_renewal, capture_use, export_captures) each target a clearly distinct operation. However, get_verdict, check, and recompute all return verdict-like data, distinguished only by scope of disclosure and statefulness; an agent could plausibly misselect between get_verdict and check when it just wants 'the verdict'.
All tools share a uniform grantseal_ prefix followed by a verb_noun pattern (seal_grant, capture_use, export_captures), which is highly predictable. The two bare-verb exceptions, grantseal_check and grantseal_recompute, are minor deviations that remain readable.
Seven tools is well within the ideal range and each maps to a distinct step in the seal/capture/verdict/recompute workflow. No tool appears redundant filler, and the surface is neither thin nor bloated.
The surface covers the full lifecycle: seal initial grant, capture exercised use, seal renewal, retrieve verdict, counterparty check, stateless recompute, and export for independent verification. The main gap is discovery/listing — there is no way to enumerate seals by agent or connector identity, so callers must already hold an identifier.
Maintenance
Related MCP Connectors
Scoped agent execution. Server-side credentials, policy, budgets and verifiable receipts.
Bounded authorization and independently verifiable execution evidence for agents.
Live behavioral security verifier, schema auditor, and trust oracle for A2A, MCP & x402 agents.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Related MCP Servers
- AlicenseAqualityBmaintenanceFree seven-tool proof loop for MCP agents: scoped sessions, bounded authorization, typed outcomes, evidence-bound claims, and tamper-evident local closure. Upgrade to Complete Local for durable memory, recovery, signed traces, release verification, and multi-agent workflows.7Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables recording agent proposals, executions, redactions and annotations into an append-only, hash-linked evidence chain, then exporting a self-contained range and verifying offline from the export's own bytes alone so a third party can check history without trusting the agent runtime or its storage.MIT
- AlicenseCqualityCmaintenanceEnables an AI agent to preflight concrete tool calls by recording principal, destination, scope, authority evidence, and relations, allowing only formed actions to execute and producing inspectable evidence receipts.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to govern the memory store they already run by gating what gets written, filtering recall by caller identity and memory validity, executing verifiable forgetting, and recording refusals and deletions in a hash-chained audit trail. It exposes these admission, authorization, and evidence controls over MCP so that credentials and personal data never persist and every deletion can be proven.1MIT