Skip to main content
Glama
0xddneto

AI Proof of Us MCP Server

by 0xddneto
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

begin_ai_task

Start a privacy-preserving AI task session by sending provider, model, client, and a task hash. Returns a signed authorization and nonce to complete later, keeping raw prompts off-chain.

Instructions

Use once before meaningful AI work to create a task session. Provide the provider, model, client, and a 32-byte hash of the task description; returns a unique nonce and EIP-712 authorization signed by the dedicated farming wallet. This writes a pending local task session but does not publish, mint, or submit an on-chain transaction. Pass the returned nonce to complete_ai_task; do not reuse it for another task.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelYesProvider model identifier used for this task, from 1 through 128 characters.
clientYesHost client or agent identifier that starts this task session, from 1 through 64 characters.
providerYesAI provider name for this task session, from 1 through 64 characters.
taskHashYes32-byte hash of the task description; never send the raw prompt or task text.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.3
    • addedInput schema / properties / client / description
      Added value: +"Host client or agent identifier that starts this task session, from 1 through 64 characters."
    • addedInput schema / properties / model / description
      Added value: +"Provider model identifier used for this task, from 1 through 128 characters."
    • addedInput schema / properties / provider / description
      Added value: +"AI provider name for this task session, from 1 through 64 characters."
    • addedInput schema / properties / taskHash / description
      Added value: +"32-byte hash of the task description; never send the raw prompt or task text."
  2. Addedv0.1.1

TDQS

A4.2/5.0
Behavior4/5

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

The description discloses that the tool writes a pending local task session and explicitly states it does not publish, mint, or submit an on-chain transaction. It also reveals that a unique nonce and EIP-712 authorization are produced, providing meaningful behavior beyond the sparse annotations.

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?

Three sentences with no filler: purpose is front-loaded, required inputs and return values are summarized, and side-effect/sequencing guidance is included. Every sentence earns its place.

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 tool with no output schema, the description adequately states the returned artifacts (nonce and signed EIP-712 authorization), the local-only side effect, and the next step. It could mention response structure in more detail, but what an agent needs to call it correctly and chain it with complete_ai_task is present.

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 each parameter is already documented in the input schema. The description reinforces that taskHash is a 32-byte hash and warns not to send raw task text, but it does not substantially add meaning beyond the schema.

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 states a specific action and resource: 'create a task session' before AI work, and clarifies the local non-publishing nature. It also names the companion tool complete_ai_task, helping distinguish begin from complete in the same workflow.

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?

The description gives clear contextual timing ('Use once before meaningful AI work') and explicit sequencing ('Pass the returned nonce to complete_ai_task; do not reuse it'). It does not explicitly enumerate when not to use the tool versus other siblings, but the workflow guidance is strong enough for an agent to route correctly.

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

Deploy Server

Other Tools