Skip to main content
Glama
FractalAI MCP Server

FractalAI MCP Server

by johnInarti

Seal an AI agent decision (VAID-1)

attest_decision

Seals an AI agent's declared decision—input hash, output, model, timestamp—in an append-only on-chain record, returning a verifiable receipt and offline signature for EU AI Act Art.12 audits.

Instructions

Pay $0.05 USDC (x402) to seal an AI agent's declared decision: its input hash, output, model and timestamp are chained in an append-only Black Box and anchored on-chain (VAID-1, this server's node-bound Dilithium-2 key). You also get back a self-contained ML-DSA-65 / Dilithium-3 signature over the same canonical decision bytes for independent offline verification. Returns a re-verifiable receipt. Built for EU AI Act Art.12 record-keeping. It notarizes the decision as declared; it does not judge whether the decision was correct. Without payment_tx_hash you get the payment challenge.

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": {
      "agent_id": "<agent_id>",
      "input": "<input>",
      "output": "<output>"
    },
    "name": "attest_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYesThe decision input (or its hash).
modelNoModel/agent version that produced the decision.
payerNoOptional payer address hint.
outputYesThe decision output the agent produced.
agent_idYesStable identifier of the agent whose decision is sealed.
payment_tx_hashNoA confirmed USDC-on-Base transaction hash paying the required amount to the treasury. If omitted, the tool returns the x402 payment challenge (accepts[]) instead of a result — pay first, then call again with this set. One txHash buys exactly one call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations present, the description carries the full behavioral burden and does so well: it discloses the exact price and payment rail (x402, USDC-on-Base), the one-transaction-per-call rule, the challenge-then-result flow, what is recorded (input hash, output, model, timestamp, append-only, on-chain anchored under this server's node-bound Dilithium-2 key), and what is returned (a re-verifiable receipt plus a self-contained signature). It also explicitly disclaims correctness judgment, which prevents a common misuse.

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?

The definition is dense and front-loaded: cost and action come first, then the cryptographic and compliance framing, then the payment-fallback behavior as the final actionable sentence. No sentence is filler, though the cryptography/privacy framing sentence runs long and could be split for scanability.

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?

For a 6-parameter mutation-style tool with no annotations and no output schema, the description covers price, payment flow, what gets stored and anchored, and what is returned, which is what an agent needs to invoke it correctly. Gaps are minor: no mention of error conditions (e.g., invalid agent_id, replayed tx hash) or idempotency behavior.

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%, so the schema already defines all six parameters including the payment_tx_hash challenge semantics. The description reinforces the payment flow and names the identity/crypto fields conceptually, but adds no syntax, format, or constraint detail beyond what the schema supplies. Baseline 3 applies when the schema does the heavy lifting.

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

Purpose4/5

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

The description states a concrete verb and resource: seal an agent's declared decision by paying $0.05 USDC, with the decision chained in an append-only log and anchored on-chain plus an offline-verifiable ML-DSA-65 signature returned. That is far more specific than the name alone. It stops short of explicitly distinguishing itself from siblings such as pqc_sign (which presumably signs without sealing) or seal_provenance, leaving that inference to the agent.

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

Usage Guidelines3/5

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

It gives a clear motivating context ('Built for EU AI Act Art.12 record-keeping') and a concrete two-step workflow: call without payment_tx_hash to receive the x402 challenge, then call again with the hash. It also scopes the tool negatively ('it does not judge whether the decision was correct'). However, it never says when to prefer this over pqc_sign, seal_provenance, or verify_proof, so alternative selection is left implicit.

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