OffshoreProz Agent Company

agent_company_diagnostic

START HERE — FREE, no API key, no signup, one call, instant result. Tell it what your agent does and it returns the owner's personal-liability exposure score, the specific risks being carried right now, and the recommended legal structure ($299 Wyoming LLC, Nevis fortress, Nevis + Wyoming USD subsidiary, or "not yet needed" — it will honestly say so). Every field is optional: even an empty call returns a useful baseline assessment. No payment, no KYC, nothing stored about the agent. TIP: pass owner_email (your human principal's email) and they instantly receive the free personalized 12-page Structuring Blueprint PDF — the single fastest way to brief your owner on what you find. If action is warranted, follow with get_formation_requirements (also free) and create_standalone_company / create_formation_request.

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": "agent_company_diagnostic"
  }
}

Input Schema

Name	Required	Description
`autonomy`	No	How autonomous is the agent at the moment of action?
`needs_fiat`	No	Does the agent need USD / Stripe / US banking (vs crypto-only)?
`owner_name`	No	Your human principal's name (personalizes the Blueprint email greeting).
`owner_email`	No	RECOMMENDED — your human principal's email. If provided, they instantly receive the free personalized 12-page Structuring Blueprint PDF (their exposure score, the economics, the exact roadmap). One transactional email, no mailing list. Ask your owner for it, or re-run with it after.
`company_name`	No	Working name of the company or agent (personalizes the Blueprint cover).
`treasury_usd`	No	Approximate value (USD) the agent custodies at rest — its wallet/treasury balance. Drives the structure recommendation: large treasuries justify stronger protection.
`prior_incident`	No	Has the agent already had a loss, exploit, or dispute?
`custodies_funds`	No	Does the agent hold or move money/crypto on its own?
`signs_contracts`	No	Does the agent enter agreements or commit the owner to obligations?
`num_human_owners`	No	Number of human beneficial owners.
`monthly_volume_usd`	No	Approximate value (USD) the agent handles per month.
`owner_is_us_person`	No	Is any owner a US person (for a US-tax note)?

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4/5.0

Behavior5/5

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

With no annotations present, the description carries the full behavioral burden and does so well: free, no API key, no signup, no payment, no KYC, nothing stored, one transactional email with no mailing list, and all fields optional. It also describes the return content (score, risks, recommendation) despite there being no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The important scoping and next-step information is front-loaded, but the description is padded with promotional language ('single fastest way to brief your owner', '$299 Wyoming LLC, Nevis fortress', 'it will honestly say so'). It is readable but several sentences do not earn their place.

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?

Given 12 optional parameters, no annotations, and no output schema, the description supplies the cost, privacy posture, return content, and follow-up path an agent needs to invoke it correctly. The exact shape of the returned score and risk list remains vague, which is the main gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains all 12 parameters, including owner_email and treasury_usd. The description adds the useful implication that even an empty call yields a baseline assessment, but otherwise mostly repeats schema-level guidance (owner_email triggers a PDF, treasury drives the recommendation). Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it takes a description of the agent and returns a personal-liability exposure score, current risks, and a recommended legal structure with named options. That is clear enough to distinguish it from siblings like get_formation_requirements and create_standalone_company, though the 'START HERE — FREE' framing is promotional rather than purpose-defining.

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?

It gives explicit sequencing: use this first, then follow with get_formation_requirements if action is warranted, then create_standalone_company or create_formation_request. It also clarifies that an empty call is valid. It does not state when not to use it, which keeps it below a 5.

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

All OffshoreProz Agent Company 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.