Skip to main content
Glama
@gblin-protocol/mcp-server

@gblin-protocol/mcp-server

seal_action_demo

Seals SHA-256 hashes of an AI action into GBLIN's public append-only transparency log and returns a portable Ed25519 receipt with Merkle inclusion proof, verifiable offline.

Instructions

Seals the hashes of an AI action into GBLIN's public append-only RFC 6962 transparency log (free demo, 5 per day per IP, receipt marked demo: true). Returns a portable receipt: Ed25519 signature, Merkle inclusion proof and operator-signed C2SP checkpoint, verifiable offline with the zero-dependency verify-receipt.mjs. Input and output go in as sha256 hashes only; the action label and metadata are published in the public log. Unlimited sealing is a separate paid x402 HTTP endpoint (0.0045 USDC per seal).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>",
      "input_hash": "<input_hash>"
    },
    "name": "seal_action_demo"
  }
}

Input Schema

NameRequiredDescriptionDefault
metaNoOptional public metadata (published).
toolNoOptional name of the tool/model that produced the action (published).
actionYesShort public label of the action, e.g. 'trade.executed' or 'report.generated'. Published in the log — never put secrets here.
agent_idNoOptional public identifier of the agent (published in the log).
input_hashYessha256 of the action input, as 64 lowercase hex chars. Hash locally; never send content.
output_hashNoOptional sha256 of the action output (64 lowercase hex chars).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.5

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond annotations, which only declare non-read-only, open-world, non-idempotent. The description adds the rate limit (5/day/IP), that receipts are marked demo:true, that the action label and metadata become public and permanent, and precisely what the receipt contains (Ed25519 signature, Merkle inclusion proof, C2SP checkpoint, offline verification via verify-receipt.mjs). That is exactly the context a caller needs before publishing.

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

Conciseness4/5

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

Front-loads the operation and its target log, then layers limits, return value, and the paid alternative in a compact block. Dense but every clause (demo quota, demo:true marking, public visibility, receipt components) carries decision-relevant information.

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

Completeness5/5

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

No output schema exists, yet the description fully describes the return value and its offline verification path. For a write tool that publishes to a public log, it covers quota, permanence, receipt shape, and the paid escalation path — nothing an agent needs to call it safely is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already carries the parameter definitions. The description still adds meaningful semantics beyond it: only sha256 hashes go in, content must be hashed locally, while action label and metadata are published. That reinforces the privacy contract of each parameter rather than restating it.

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?

States a specific verb ('Seals') and resource ('hashes of an AI action into GBLIN's public append-only RFC 6962 transparency log'), scoping exactly what is written and where. An agent can distinguish this from prepare_action or how_to_seal_paid without opening the schema.

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

Usage Guidelines4/5

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

Clear context for when to call: free demo limited to 5 per day per IP, with a pointer that unlimited sealing lives at the separate paid x402 endpoint. It also warns that label and metadata are published publicly, which steers callers away from this tool for sensitive content. It does not explicitly compare against the sibling how_to_seal_paid or prepare_action, so not a 5.

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