ProofSnap

Certify a file by its SHA-256

certify_hash

Destructive

Seals the SHA-256 of a file (the file itself never leaves the user's device) as a ProofSnap certification with an OpenTimestamps (Bitcoin) proof, optionally an eIDAS qualified timestamp. The hash is the SHA-256 of the file's exact bytes (64 hexadecimal characters); a hash that does not come from the file certifies nothing. Uses one capture of the account's plan per hash.

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": "certify_hash"
  }
}

Input Schema

Name	Required	Description
`hash`	No	One SHA-256. Use hash or hashes.
`fresh`	No	Set true only when the user asks for a new one: every call with fresh true creates a new, billed item, also when it repeats an earlier call. Without it, the same request repeated within 10 minutes (sometimes up to 20) returns the earlier result.
`label`	No	A name for the certified file, for example its file name.
`hashes`	No	Up to 100 SHA-256 values. Use hash or hashes.
`language`	No	Language of the human-readable PDF report. Default en.
`confirm_cost`	No	The confirmation_token this tool returned with its cost, sent only after the user agreed to that cost.
`include_eidas`	No	Add an eIDAS qualified timestamp. Charged separately; needs an account with linked billing.
`case_reference`	No

Output Schema

Name	Required	Description	Default
`count`	No
`label`	No
`status`	No
`batch_id`	No
`combined`	No
`certify_id`	No
`file_count`	No
`timestamps`	No
`verify_url`	No
`certify_ids`	No
`hash_sha256`	No
`certified_at`	No
`download_url`	No
`failed_count`	No
`dashboard_url`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Adds real context beyond annotations: the file never leaves the device, each hash consumes one capture of the account's plan, and eIDAS is an optional separately charged add-on requiring linked billing. It does not describe the confirm_cost two-step confirmation flow, but the safety/billing profile is otherwise well disclosed and does not conflict with destructiveHint=true.

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?

Three sentences, front-loaded with the core action and proof mechanism, with no filler. Slightly dense (billing caveat and hash-provenance warning packed into the last two sentences) but every sentence carries information.

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?

With an output schema present and 88% schema coverage, the description needn't explain return values, and it covers the essentials: what gets sealed, cost model, optional eIDAS. The main omission is the confirm_cost confirmation handshake, which is only documented in the parameter schema.

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 88%, so baseline is 3; the description earns a bump by clarifying that the hash must be 64 hex characters derived from the file's exact bytes and by stating the per-hash plan consumption, which is the key semantic behind the hash/hashes pair. The confirm_cost, fresh, and language parameters are left entirely to 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?

States a specific verb and resource ('Seals the SHA-256 of a file ... as a ProofSnap certification with an OpenTimestamps (Bitcoin) proof') and names the produced artifact. Also distinguishes itself from the verify/list siblings by describing the act of creating a certification from a hash rather than checking an existing capture.

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?

Implies when to use it (you have a SHA-256 and want a timestamp proof) and warns that 'a hash that does not come from the file certifies nothing'. However it never names alternatives such as verify_capture, compare_captures, or capture_web_page, and gives no explicit when-not-to-use guidance.

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

All ProofSnap tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.