Skip to main content
Glama

Create a proof (unsigned)

create_proof

Use to timestamp an output, file, or claim so it can't be disputed later: for example a report you generated, a dataset hash, a prediction, or a statement your operator wants on record. $1 + network fee (publication, deed and artwork $1), no API key. Creates a one-of-one proof token on Bitcoin for a claim, file, or SHA-256, paid and signed by your own wallet. Stores the public claim record and returns an UNSIGNED PSBT (base64 and hex) that issues the token (quantity 1, indivisible, locked) and already includes the service fee output. Nothing is broadcast and no money moves until you sign and call broadcast.

Types: proof ($1, needs claim), publication ($1, Proof of Publication: needs metadata.name plus a file, sha256 or metadata.description; the file is hashed and never stored), deed ($1, Ownership Token for a personal item, not legal title: needs metadata.name and a photo as file), artwork ($1, Certificate of Provenance: needs metadata.name, metadata.creator and a photo as file).

Files: pass a small file as base64 (or data: URL), an https file_url (up to 6 MB), or just its sha256 so the file never leaves your machine. Then sign every input with the key for address (SIGHASH_ALL), do not change any output, finalize, and call broadcast within 30 minutes. Rate limit: 20 new proofs per hour per IP.

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": {
      "address": "<address>"
    },
    "name": "create_proof"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoSmall file as base64 or a data: URL (keep under ~3 MB). For larger files use file_url or sha256.
typeNoDefault proof.
claimNoThe public claim, e.g. "I wrote this song on 2026-11-17". Required for type proof; generated from metadata for other types.
sha256NoSHA-256 (hex) of a file, if you do not want to send the file itself.
addressYesThe agent's own Bitcoin address. It pays, signs, and receives the token. Native SegWit bc1q… recommended.
detailsNoOptional longer details for the claim.
networkNoDefault mainnet.
fee_rateNoNetwork fee rate in sat/vB. Minimum 5; default is the current standard rate.
file_urlNohttps URL of the file (up to 6 MB); the server downloads and hashes it.
metadataNoOptional structured details. Shown as separate rows on the certificate and on Tokenscan.
file_nameNo
file_typeNoMIME type, e.g. image/png. Deed and artwork need an image.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior3/5

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

With readOnlyHint=false, openWorldHint=true and idempotentHint=false already declared, the description meaningfully adds cost ($1 plus network fee), no API key requirement, the unsigned-PSBT return format, the embedded fee output, the SIGHASH_ALL signing requirement, the 30-minute expiry window, and that files are hashed and never stored. That is substantial context beyond the annotations, though it omits details like what the returned proof identifier looks like and how partial failures are surfaced.

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 purpose, then cost and return value, then the type matrix and file conventions, then the signing procedure – a logical order with no filler. The Types and Files paragraphs are dense run-ons, but each sentence carries required information.

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

Completeness5/5

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

For a 12-parameter, nested-object mutation tool with no output schema, the description covers what is created, what is returned (base64 and hex PSBT), what the agent must do before broadcast, cost, timing, and rate limits. Nothing essential to calling it correctly is missing.

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 already 92%, so the schema carries most parameter documentation. The description still contributes real meaning the schema cannot express: the conditional requirements per type (proof needs claim; publication needs metadata.name plus file/sha256/metadata.description; deed and artwork need metadata.name and a photo), plus the three interchangeable ways to supply file content (base64, file_url, sha256).

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?

First sentence states a specific verb and outcome ('timestamp an output, file, or claim') and the second states the concrete artifact ('one-of-one proof token on Bitcoin'). It also distinguishes itself from the sibling broadcast by saying it only returns an unsigned PSBT and 'nothing is broadcast' until you sign and call broadcast.

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

Usage Guidelines5/5

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

Gives explicit use cases (generated report, dataset hash, prediction, operator statement), enumerates the four type variants with their required inputs, and names the follow-up step ('sign... and call broadcast within 30 minutes'). It also states an operational limit (20 proofs/hour per IP) that constrains when an agent should call it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.