PriorSeal
Server Details
Verifiable execution records for AI agents: signed receipts, tamper-evident archives and portable evidence bundles, exposed via MCP and REST, with paid verify and anchor calls settled over x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- imokokok/PriorSeal
- GitHub Stars
- 6
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 12 tools
Most tools target a distinct lifecycle step, but the three evidence tools (get_evidence, get_evidence_bundle, get_fresh_evidence_check) are structurally identical 'free x402 handoff' wrappers differing only in which paid artifact they gate, which invites misselection. The prepare_authorization / prepare_controlled_execution / accept_authorization boundary is also subtle: the descriptions clarify it, but only after careful reading of the read-only vs state-changing distinction.
Every tool uses the same priorseal_ prefix followed by a consistent snake_case verb_noun pattern (get_, prepare_, accept_, observe_, verify_). The verb choice maps predictably to read vs write vs prepare semantics across the whole set.
Twelve tools is a well-scoped size for a prepare/sign/observe/verify workflow. The only mild bloat is the trio of near-identical evidence handoff tools, which could plausibly be one parameterized tool.
The core lifecycle (capabilities → prepare → accept → observe → receipt → verify → evidence) is covered end to end, but every read is by explicit identifier: there are no list/enumerate tools for authorizations, receipts, or observation jobs, and no revoke/cancel operation for an accepted authorization. Agents cannot discover existing records or undo a consumed authorization, which are meaningful dead ends.
Publisher details
- Operator
- PriorSeal — solo operator · Publisher source
- Operator website
- https://priorseal.xyz
- Vendor relationship
- First-party
- Documentation
- https://priorseal.xyz/docs · Publisher source
- Privacy policy
- https://priorseal.xyz/privacy · Publisher source
- Trust center
- Not available
- Restrictions
- Public evidence verification is free; anchor and premium verify calls are paid via x402 micropayments. · Publisher source
Available Tools
12 toolspriorseal_accept_authorizationAInspect
Verify and persist a principal-signed authorization. This can consume configured Agent credits and changes service state; send an idempotency key. It never signs, submits, or executes a transaction.
Inputs: input (required). Returns: data, risk, tool, schema, +4 more
priorseal_get_authorizationARead-onlyIdempotentInspect
Read an accepted authorization by its identifier.
Inputs: authorizationId (required). Returns: data, risk, tool, schema, +4 more
priorseal_get_capabilitiesARead-onlyIdempotentInspect
Read the live PriorSeal deployment capabilities before constructing a workflow.
Returns: data, risk, tool, schema, +4 more
priorseal_get_evidenceCRead-onlyIdempotentInspect
Get a free x402 purchase handoff for the chain-neutral Evidence API envelope. This MCP result never includes the paid envelope itself.
Inputs: receiptId (required). Returns: data, risk, tool, schema, +4 more
priorseal_get_evidence_bundleBRead-onlyIdempotentInspect
Get a free x402 purchase handoff for the portable receipt evidence bundle. This MCP result never includes the paid bundle itself.
Inputs: receiptId (required). Returns: data, risk, tool, schema, +4 more
priorseal_get_fresh_evidence_checkCRead-onlyIdempotentInspect
Get a free x402 purchase handoff for a newly signed, read-only chain re-observation of an authorization-bound receipt.
Inputs: receiptId (required). Returns: data, risk, tool, schema, +4 more
priorseal_get_observation_jobBRead-onlyIdempotentInspect
Read the durable status of an automatic finality-observation job.
Inputs: jobId (required). Returns: data, risk, tool, schema, +4 more
priorseal_get_receiptBRead-onlyIdempotentInspect
Read a signed execution receipt by its identifier.
Inputs: receiptId (required). Returns: data, risk, tool, schema, +4 more
priorseal_observe_executionAInspect
Persist an observation request for an already-submitted EVM or Solana transaction, then issue evidence when configured observation completes. A successful metered observation includes its first portable evidence bundle. This can consume configured Agent credits; send an idempotency key. It never broadcasts a transaction.
Inputs: input (required). Returns: data, risk, tool, schema, +4 more
priorseal_prepare_authorizationARead-onlyIdempotentInspect
Canonicalize a bounded authorization and return the exact EIP-712 typed data or Solana message for a human-controlled principal to sign. This is read-only and never signs, submits, or executes a transaction.
Inputs: input (required). Returns: data, risk, tool, schema, +4 more
priorseal_prepare_controlled_executionARead-onlyIdempotentInspect
Prepare the Seal stage of one Verified Action together with deployment capabilities and a safe handoff plan for Witness, Match, and Review. A human-controlled principal must still sign; this never accepts an authorization, signs, submits, or executes a transaction.
Inputs: input (required). Returns: data, risk, tool, schema, +4 more
priorseal_verify_receiptARead-onlyIdempotentInspect
Convenience-verify a PriorSeal receipt with the deployment key registry. Independent local verification remains required for trust decisions.
Inputs: receipt (required). Returns: data, risk, tool, schema, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
Agent-native MCP for governed commerce, x402 payments, paid capabilities, and verifiable receipts.
Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Policy-aware AI execution, verification, cost, and trajectory evidence for agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceCryptographically anchored, tamper-evident evidence receipts for AI agents — verified run receipts, existence-at-time proofs, and cited answers from an anchored public record. Remote MCP with proof-gated settlement; attests existence and integrity, never truth.-
- AlicenseAqualityBmaintenancealalanet-agent is the open local client of alalanet.com, the free service an AI agent asks before it installs, connects or pays. A stdio MCP server whose key stays on your machine: it signs agent passports, receipts, skill and package releases, mail and memory locally (16 tools) and checks files and agents against alalanet's public transparency log. Hosted checks: https://alalanet.com/mcp.216Apache 2.0
- AlicenseAqualityBmaintenanceCryptographic accountability for AI agents. Ed25519-signed receipts for every MCP tool call. Constraints, chains, AI judgment, invoicing, and local dashboard included.241MIT
- AlicenseNot gradedqualityBmaintenanceTamper-evident recorder for AI agent tool calls. Every MCP call is written to a hash-chained, signed log the agent cannot edit, delete or hide; anyone can verify the chain offline.Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.