deusproof-mcp

certify_creation

Records an AI creation with authorship scoring, signing, RFC 3161 timestamping, and Bitcoin anchoring to provide public proof of what was made and when.

Instructions

Record when an AI creation existed: timestamp it and anchor it to Bitcoin.

Get a permanent, verifiable record of what THIS agent submitted, and WHEN. Scores authorship (AAS 0-100, a heuristic), signs a C2PA-style manifest under the agent's own key (tier "signed": the record shows that key signed it), timestamps it (RFC 3161) and anchors it to Bitcoin on a public, append-only ledger. Not a patent: it proves when, not who. Free. Use this whenever an agent makes something worth a dated public record.

Args: prompt: the task/instruction that produced the output. output: the creation itself (text). handle: public agent name shown on the certificate and Pantheon. model: AI model to credit (attested by the signature). tools: external tools the agent used, for the tool-diversity score.

Returns the certificate id, authorship score, tier, and a public verify URL.

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>",
      "output": "<output>"
    },
    "name": "certify_creation"
  }
}

Input Schema

Name	Required	Default
`model`	No
`tools`	No
`handle`	No	mcp-agent
`output`	Yes
`prompt`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.3Jul 15, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the heuristic authorship score, signing under the agent's own key, RFC 3161 timestamping, public append-only Bitcoin anchoring, and that the service is free. It also explains that the record proves timing rather than authorship. It does not explicitly cover auth/key requirements, privacy exposure of prompt/output, or idempotency, so it is not fully exhaustive.

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 description is front-loaded with the core purpose and then structured into behavior, usage, args, and returns. It is generally efficient, though the opening line and second paragraph repeat the timestamp-and-Bitcoin-anchor idea.

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 complex tool with no annotations, no output schema, and five undocumented schema parameters, the description is substantially complete: it explains the process, usage context, every parameter, and the return values. It still omits operational details such as key requirements, privacy implications, and duplicate-submission behavior.

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 0%, so the description must explain all five parameters, and it does: prompt, output, handle, model, and tools each receive meaningful context beyond their names. It does not specify required versus optional fields, defaults, or type constraints, which leaves some semantic gaps.

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 specific verb and resource: record when an AI creation existed, timestamp it, and anchor it to Bitcoin. It also enumerates the exact operations: authorship scoring, manifest signing, RFC 3161 timestamping, and Bitcoin anchoring. It does not explicitly differentiate itself from siblings like birth_certificate, claim_authorship, or notarize_hash, so it falls short of a 5.

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?

It gives clear usage context: "Use this whenever an agent makes something worth a dated public record." It also adds a boundary: "Not a patent: it proves when, not who." However, it does not name alternatives or state when another sibling tool should be used instead.

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

Deploy Server