Rubric Protocol MCP Server

attested_inference

Generates GPT-4o-mini completions with cryptographic attestation of prompt hash, response hash, model version, and timestamp, creating verifiable evidence for compliance audits.

Instructions

PAID ($0.01 USDC): gpt-4o-mini completion plus attestation binding prompt hash, response hash, exact model version, timestamp - evidence of which model said what, when.

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": {
      "prompt": "<prompt>"
    },
    "name": "attested_inference"
  }
}

Input Schema

Name	Required	Description	Default
`prompt`	Yes
`max_tokens`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.2.4Nov 9, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose key traits: the call is paid ($0.01 USDC), the model is fixed to gpt-4o-mini, and the response carries specific attestation fields. It omits payment mechanics (wallet/auth flow), whether prompts are persisted, and any rate limits or failure behavior, which keeps it below a 5.

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?

A single sentence that front-loads the price and then the payload. No filler; every clause (price, model, attestation fields) adds decision-relevant information.

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

Completeness3/5

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

For a paid, no-annotation tool with no output schema, the description adequately explains what comes back (hashes, version, timestamp) but leaves out payment/auth requirements, max_tokens semantics, and response shape beyond the attestation fields. Enough to decide to call it, not enough to call it confidently.

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

Parameters2/5

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

Schema description coverage is 0% for both parameters. The description hints that 'prompt' is the input (via 'prompt hash') but says nothing about 'max_tokens' — its default, range, or effect on cost/output. With zero schema coverage, the description should compensate and largely does not.

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 concrete verb and resource: a gpt-4o-mini completion bundled with an attestation covering prompt hash, response hash, model version and timestamp. The model and the paid nature are named up front, which separates it from siblings like 'attest' (attest existing content) and 'verify' (check an attestation).

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?

The phrase 'evidence of which model said what, when' implies the use case (auditable provenance of a model response), but there is no explicit when-to-use/when-not guidance and no mention of when to prefer 'attest' or 'verify' instead. The agent must infer routing from the sibling names.

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

Deploy Server