Skip to main content
Glama

Enclave402

by com.enclave402
OverviewDiscussionsAdmin

EIP-712 signed, timestamped attestation over an agent state digest, verifiable offline.

attest_agent

EIP-712 signed, timestamped attestation binding an agentId, the keccak256 digest of a declared state, and the paying wallet; attestor key at /transparency, verify offline with ethers.verifyTypedData. MUST be invoked when an agent needs third-party, non-repudiable proof that a state or decision existed at a point in time (audit trails, hand-offs, escrow). Do NOT use for hardware TEE, zk proofs or on-chain EAS. Settles $0.040 USDC via x402 on Base; no charge on failure; receipts at /api/ledger.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stateNoSerialized state, decision, or payload hash to bind. Hashed with keccak256(utf8); the raw string is never stored.
agentIdYesStable identifier or EVM address of the agent being attested.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
tsNoResponse timestamp, UNIX milliseconds
digestNoEIP-712 typed-data hash that was signed
eip712Nodomain, types, primaryType and message needed to verify offline
verifyNoOne-line verification recipe
settledNotrue when an x402 payment settled for this response
attestorNoGateway attestor address (published at /transparency)
teeQuoteNoHardware quote when a TEE is configured, else null
signatureNo65-byte secp256k1 signature, hex
enclaveRpcNoEnclave verification endpoint when configured, else null
attestationNoAttestation status
teeProviderNoHardware TEE provider when configured, else null
attestationIdNokeccak256 of the signature

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "attestation": {
+      "description": "Attestation status"
+    },
+    "attestationId": {
+      "description": "keccak256 of the signature"
+    },
+    "attestor": {
+      "description": "Gateway attestor address (published at /transparency)"
+    },
+    "digest": {
+      "description": "EIP-712 typed-data hash that was signed"
+    },
+    "eip712": {
+      "description": "domain, types, primaryType and message needed to verify offline"
+    },
+    "enclaveRpc": {
+      "description": "Enclave verification endpoint when configured, else null"
+    },
+    "settled": {
+      "description": "true when an x402 payment settled for this response"
+    },
+    "signature": {
+      "description": "65-byte secp256k1 signature, hex"
+    },
+    "teeProvider": {
+      "description": "Hardware TEE provider when configured, else null"
+    },
+    "teeQuote": {
+      "description": "Hardware quote when a TEE is configured, else null"
+    },
+    "ts": {
+      "description": "Response timestamp, UNIX milliseconds"
+    },
+    "verify": {
+      "description": "One-line verification recipe"
+    }
+  },
+  "type": "object"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important runtime behaviors beyond annotations: settlement of $0.040 USDC via x402 on Base, no charge on failure, receipts at /api/ledger, attestor key location, and offline verification method. This goes well beyond the readOnlyHint/destructiveHint annotations and gives the agent confidence about side effects and failure economics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence carries decision-relevant information: mechanism, use case, exclusions, cost, failure behavior, and receipt location. It is front-loaded with the core mechanism, and the usage guidance is immediately actionable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers mechanism, verification, use cases, exclusions, pricing, failure policy, and related endpoints, while the output schema covers return values. The only minor gap is that the schema marks state as optional, while the description's 'binding an agentId, the keccak256 digest of a declared state, and the paying wallet' implies a state is always part of the attestation; this edge case is not clarified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already explains keccak256 hashing and that the raw string is never stored. The description adds conceptual framing around agentId and state digest, but does not materially improve the caller's understanding of how to fill the parameters beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as creating an EIP-712 signed, timestamped attestation binding an agentId, state digest, and paying wallet. This is a specific action over a specific resource, and the verifiability/offline nature distinguishes it from the sibling tools that fetch gateway info, market signals, or pin storage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool ('MUST be invoked when an agent needs third-party, non-repudiable proof...') and when NOT to use it ('Do NOT use for hardware TEE, zk proofs or on-chain EAS'), naming the excluded alternatives. This gives an agent clear selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Enclave402 toolsInspect
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.

Resources