Skip to main content
Glama

Sato Hub: Build Onchain & Crypto Agents

Check what an install can do with your keys and funds

onchain_agent_check_install
Read-onlyIdempotent

USE WHEN you are about to install a crypto package or MCP server and want to know what it can do with your keys and funds: before npm/pnpm/yarn/bun add, npx -y, pip install, uvx or claude mcp add, or before pasting an {"mcpServers": …} config. NOT FOR a token, repo, endpoint or agent you were handed (use onchain_agent_preflight instead), install steps for a stack pick (use onchain_agent_get_deploy_spec), or an agent skill's disclosure (use onchain_agent_search_skills).

REDACT BEFORE YOU CALL: send only what the check reads. For an MCP add, that is the transport word and the server's package (with its version) or URL (host and path words): write the server name as <redacted> and leave out env, headers and every other flag (claude mcp add <redacted> -- npx -y <package>). For a package install, the check reads the installer, package names (with versions, repo paths and refs) and flag names, never values: replace every secret-flag value, argument the program gets after its package, private key, seed phrase, and URL credential, path token or query value with <redacted>. In a JSON config, keep command, the package in args and the url; set every other value to "". In Claude Code with the Sato Hub plugin, its hook checks each install command before it runs: do not send a command the hook already checked.

RETURNS a Sato Check custody summary for every target in the command or config you pass, answering four questions: does it take your key, does your key leave, can it move funds on its own, what changed.

Each answer rests on evidence of one class — declared (the project says so), traced (our static read of the published artifact) or observed (a sandbox run with planted test keys). A stored profile answers first; an unstored target is read live within a bounded budget. Targets that could not be profiled are listed in unresolved with the reason. has_observed_key_egress is true only when a planted test key was seen leaving — the one fact to stop on.

RULE ENFORCED: a profile describes what was read and run, with dates. It is not a safety rating, an audit or an endorsement; "unknown" means we could not look, and "none found" is not "not there". Local signing is what a wallet does.

RETURNS (json): { schema: "sato.custody/v1", subjects: [{ subject, summary: { key_access, key_egress, fund_action_count, notable, version, as_of, check_url }, answers: { key_access, key_egress, fund_actions, changes }, solana_receipt }], unresolved: [{ input, reason }], has_observed_key_egress }. solana_receipt is where that version's reading is recorded on Solana ({ attestation_address, explorer_url, cluster, as_of, digest_hex }), or null when none is. install/cmd/package/text are read as command, mcp/mcpServers as config (labelled); {} checks nothing and answers needs_input. Read-only.

Example: { command: "npm i viem @goat-sdk/core" } · { config: "{"mcpServers":{"wallet":{"command":"npx","args":["-y","some-wallet-mcp"]}}}" }

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": "onchain_agent_check_install"
  }
}

Input Schema

NameRequiredDescriptionDefault
cmdNoRead as `command`.
mcpNoRead as `config` (an MCP config block, as text or an object).
textNoRead as `config` when it is a JSON block, else as `command`.
configNoAn MCP config block as text, e.g. {"mcpServers": {...}}. A JSON object is read as its text. Up to 16 KB is checked.
commandNoAn install command, e.g. "npm i @solana/web3.js viem" or "claude mcp add wallet -- npx -y some-wallet-mcp".
installNoRead as `command`.
packageNoRead as `command` (an install command or package names).
mcpServersNoRead as `config`: { mcpServers: <this> }.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / cmd
      Added value: +{
      +  "description": "Read as `command`.",
      +  "maxLength": 16384,
      +  "type": "string"
      +}
    • changedInput schema / properties / config / description
      Previous value: -"An MCP config block as text, e.g. {\"mcpServers\": {...}}."New value: +"An MCP config block as text, e.g. {\"mcpServers\": {...}}. A JSON object is read as its text. Up to 16 KB is checked."
    • changedInput schema / properties / config / maxLength
      Previous value: -16384New value: +262144
    • addedInput schema / properties / install
      Added value: +{
      +  "description": "Read as `command`.",
      +  "maxLength": 16384,
      +  "type": "string"
      +}
    • addedInput schema / properties / mcp
      Added value: +{
      +  "description": "Read as `config` (an MCP config block, as text or an object).",
      +  "maxLength": 262144,
      +  "type": "string"
      +}
    • addedInput schema / properties / mcpServers
      Added value: +{
      +  "additionalProperties": {},
      +  "description": "Read as `config`: { mcpServers: <this> }.",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / package
      Added value: +{
      +  "description": "Read as `command` (an install command or package names).",
      +  "maxLength": 16384,
      +  "type": "string"
      +}
    • addedInput schema / properties / text
      Added value: +{
      +  "description": "Read as `config` when it is a JSON block, else as `command`.",
      +  "maxLength": 16384,
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: the three evidence classes (declared, traced, observed), the stored-profile-first then bounded live-read behavior, the `unresolved` bucket, and the meaning of `has_observed_key_egress` as the single stop signal. It also carries a rare and valuable epistemic disclaimer ('not a safety rating... "none found" is not "not there"') and a mandated redaction procedure before calling.

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 definition is long but deliberately structured with USE WHEN / NOT FOR / REDACT / RETURNS headers, and the trigger conditions are front-loaded ahead of the procedural detail. It loses a point for redundancy: a prose RETURNS paragraph is followed by a second 'RETURNS (json)' block that restates the same field names, and the redaction paragraph is dense enough to slow scanning.

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?

With 8 optional parameters, nested config objects, and no output schema, the description carries the full burden and does so: it inlines the complete response shape (schema, subjects, answers, solana_receipt, unresolved, has_observed_key_egress), supplies two worked call examples, and covers input-size expectations. Nothing an agent needs in order to call it correctly appears to be 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 100%, so the baseline is 3, and the description goes beyond it by mapping aliases to canonical slots (install/cmd/package/text → `command`, mcp/mcpServers → `config`), specifying the empty-object behavior (`{}` checks nothing and answers needs_input), and giving per-parameter redaction rules for what to send. It does not add per-field format constraints beyond the examples, which is why it stops short of 5.

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?

The description states a specific verb and resource ('Check what an install can do with your keys and funds') and immediately scopes it to install commands and MCP configs. It explicitly names the three sibling tools it is not (onchain_agent_preflight, onchain_agent_get_deploy_spec, onchain_agent_search_skills), so an agent can route without opening any schema.

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?

The 'USE WHEN' block enumerates concrete trigger points (npm/pnpm/yarn/bun add, npx -y, pip install, uvx, `claude mcp add`, pasting an mcpServers config), and the 'NOT FOR' block names each alternative and the condition that selects it. This is about as explicit as when-to-use guidance gets.

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.