Skip to main content
Glama

gdex_connect

Connects a GDEX trading account without exposing secrets by using a local key file, creating a new wallet, or refreshing an accountRef; returns an accountRef for use with trading tools.

Instructions

Connect a GDEX trading account without putting any secret in the conversation. Signs in from a control-wallet key file on this machine (keyFile), or creates a new local wallet (create: true), or refreshes an existing accountRef. Returns an accountRef plus public addresses; pass accountRef to any trading tool instead of sessionPrivateKey/privateKey. Never ask the user to paste a private key or seed phrase.

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": "gdex_connect"
  }
}

Input Schema

NameRequiredDescriptionDefault
createNoCreate and store a new local control wallet (it starts unfunded)
keyFileNoPath to a local JSON key file ({ privateKey } or { control: { privateKey } })
accountRefNoRefresh the session of an already connected account
inviteCodeNoOnly with create: true, and only when the user explicitly chose to use someone's GDEX invite. Counts only for a brand-new account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv5.4.1
    • addedInput schema / properties / inviteCode
      Added value: +{
      +  "description": "Only with create: true, and only when the user explicitly chose to use someone's GDEX invite. Counts only for a brand-new account.",
      +  "pattern": "^[1-9A-HJ-NP-Za-km-z]{8,32}$",
      +  "type": "string"
      +}
  2. Addedv4.12.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true; the description goes further by disclosing the security model (secrets never enter the conversation, keys read from a local key file on this machine) and by naming the hard behavioral constraint "Never ask the user to paste a private key or seed phrase." It stops short of saying whether credentials persist to disk between calls or what failures look like when a key file is missing or malformed.

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, each carrying distinct load: what it does and its safety property, the mode enumeration, and the follow-up contract for accountRef. The most important constraint (no secrets in the conversation) is front-loaded in the first clause, and there is no redundant restatement of the title.

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 no output schema, the description correctly takes on the return contract ("Returns an accountRef plus public addresses") and explains the downstream handoff to trading tools. For a credential-minting tool with openWorldHint and no readOnly protection, it could additionally state whether reconnecting overwrites an existing local wallet or how accountRef expiry is handled.

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 100%, so the baseline is 3; the description earns above that by framing the parameters as mutually exclusive modes (keyFile vs create: true vs accountRef refresh) rather than a flat bag of optional fields, which is semantic information the schema does not encode. It still leaves the inviteCode/literal-path-permission relationship only to the schema text.

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?

Names a specific verb and resource ("Connect a GDEX trading account") and immediately enumerates the three distinct modes: sign-in via local keyFile, create a new local wallet, or refresh an existing accountRef. An agent can distinguish this credential-establishment tool from data/query siblings like gdex_accounts or gdex_status without opening the schema.

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?

Strong mode-selection guidance: it states that inviteCode applies only with create: true and only when the user explicitly opted into someone's invite, and that accountRef should be passed to any trading tool instead of raw private keys. What it does not do is disambiguate against nearby credential siblings such as auth_login, managed_sign_in, or generate_session_keypair, which an agent must choose between.

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