Skip to main content
Glama
FractalAI MCP Server

FractalAI MCP Server

by johnInarti

Buy a PQC + drand provenance seal

seal_provenance

Seals content with a post-quantum provenance record via a $0.05 USDC x402 payment: drand timestamp, ML-DSA-65 signature, and on-chain anchor for EU AI Act provenance.

Instructions

Pay $0.05 USDC (x402) for a post-quantum provenance seal over content: a drand round (League of Entropy, not backdateable) + a self-contained ML-DSA-65 / Dilithium-3 signature over the seal + an on-chain anchor attempt (this server's node-bound Dilithium-2 key) over the content hash. Useful for EU AI Act (Art. 10/50/53) provenance. It is a provenance record, not a content audit. Without payment_tx_hash you get the payment challenge.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "seal_provenance"
  }
}

Input Schema

NameRequiredDescriptionDefault
payerNoOptional payer address hint.
contentNoUTF-8 content; sha256(content) is sealed.
content_hashNoSha256 hex you already computed. Provide content OR content_hash.
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

A4.3/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses the exact price and rail (x402, USDC), that the drand round is not backdateable, which key type signs what, and that the on-chain anchor is only an 'attempt' — honestly flagging a fallible side effect. This is behavior an agent cannot learn from the schema or any annotation.

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 price and the deliverable, then closes with the two most decision-relevant caveats in short sentences. The opening sentence is a long, jargon-dense run-on ('self-contained ML-DSA-65 / Dilithium-3 signature over the seal + an on-chain anchor attempt ... over the content hash') that takes effort to parse, but no sentence is filler.

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 payment-gated tool with no annotations and no output schema, it covers price, asset, signer keys, payment sequencing, and the challenge-vs-result branching. The remaining gap is the shape of a successful response (fields/verification data), which an agent must discover on first paid call.

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 spells out the payment_tx_hash challenge flow and the content/content_hash choice, so the description mostly restates structured data. It adds only the marginal framing that the sealed object is sha256(content), matching the baseline 3 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.

Purpose5/5

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

States a specific verb and price ('Pay $0.05 USDC ... for a post-quantum provenance seal over content') and enumerates exactly what the artifact contains (drand round, ML-DSA-65 signature, on-chain anchor). The line 'It is a provenance record, not a content audit' actively distinguishes it from audit/attestation-style siblings.

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?

Gives clear usage context ('Useful for EU AI Act (Art. 10/50/53) provenance') and an explicit negative exclusion ('not a content audit'), plus the key operating flow that omitting payment_tx_hash yields a payment challenge. It stops short of naming when to pick this over pqc_sign or attest_decision, so sibling routing is implicit rather than explicit.

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