Skip to main content
Glama
@proof-holdings/mcp-server

@proof-holdings/mcp-server

Official

get_current_sub_account

Read-only

Retrieves a sub-account key's own profile or the account's primary sub-account, returning theme, custom links, and public proof settings; creates the primary on first use if none exists.

Instructions

Get the current sub-account record: with a sub-account key, that key's own sub-account; otherwise the account's primary sub-account. The first call creates a primary sub-account if the account has none (never for a sub-account key, which gets profile_not_found). Returns profile details, theme, custom links, and public proof display settings. Its write twin is update_public_page (the same record). In the dashboard, the Profile page (https://proof.holdings/profile) edits whichever sub-account is selected there.

ACCESS: needs a Proof account. Set PROOF_API_KEY and restart this server, then call this tool again. start_login does NOT open this tool.

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": "get_current_sub_account"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
idYesMongoDB ObjectId
bioNo
themeYesProfile theme customization
usernameNoAbsent until a username is claimed
is_publicYes
avatar_urlNoA URL or a data URI; null once cleared
created_atYes
is_primaryYes
profile_idYesThe public id used in profile URLs
updated_atYes
view_countYes
email_themeYesTheme of this sub-account's emails; null when unset (read as `dark`).
is_businessYes
name_reviewYesWhy a typed name is left out of the public reads: it reads as a protected brand's own, until a domain of that brand is checked. Null when nothing is held.
proof_orderYesWho decided the order of a profile's proofs. `default`: domain, social account, Telegram bot, email, phone, wallet, then each proof's `display_order`. `owner`: the owner's `display_order` alone — send it when the owner reorders. The first shown proof that is not hidden leads the profile's preview card, share tags and badge. Omitted on an update, the profile keeps its current setting.
custom_linksYes
display_nameNo
business_nameNo
name_headlineYesWhy a published name may not lead the page (it carries a protected brand word); it leads only when an OV/EV certificate names it. Null when not demoted.
public_proofsYesThe shown proofs, in the order the public profile shows them
support_emailYesSupport address shown in this sub-account's messages; null when unset.
show_delegationsYes
channels_completeYesThe owner's statement that the channels listed are all of theirs.
verification_levelYesAlways 'basic'; no levels are computed; removed in the next major.
show_proof_channelsYes
username_is_defaultNoThe username was given automatically (from the domain the profile shows, else its short id); the owner may replace it once with a name of their choice.
show_verification_datesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.10.0

TDQS

A4/5.0
Behavior1/5

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

The description discloses that the first call creates a primary sub-account when none exists, which is a state-modifying side effect, yet the annotations declare readOnlyHint=true. An agent reading the annotations will assume a pure read, so the two signals conflict at the exact point that matters for a zero-argument call. The disclosure itself is admirably honest, but it directly contradicts the supplied annotation.

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 dense, front-loaded sentences plus a separate ACCESS block, so a reader gets the core contract in the first line. The dashboard/Profile-page sentence is the weakest link but does earn some place by tying the record to a human-visible surface for verification.

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 zero-parameter tool with an output schema, everything an agent needs is present: record resolution, lazy-creation behavior, the error case, the paired write tool, and the exact auth prerequisite with restart instructions. The return payload is summarized even though the output schema already covers it.

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?

The tool takes no parameters, so per the baseline there is nothing for the description to compensate for. The description instead spends that space on implicit-input semantics: which identity (api key type) determines the returned record.

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?

Opens with a precise verb+resource ('Get the current sub-account record') and immediately disambiguates resolution rules: with a sub-account key it returns that key's own record, otherwise the primary sub-account. This is clearly distinguishable from get_sub_account, which the sibling name implies takes an explicit identifier.

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?

Explicitly states when each resolution branch applies, names the failure case ('profile_not_found' for sub-account keys), warns about the lazy-create side effect on first call, and routes to the write sibling update_public_page for mutation. It also states the prerequisite (PROOF_API_KEY) and preempts a wrong turn by noting start_login does not unlock this tool.

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