Firmaradar

Find Shared Connections

firmaradar_find_shared_connections

Read-onlyIdempotent

Analyse hidden connections across 2–10 Norwegian companies at once: shared board members/signatories, shared registered address, shared owners or ultimate parent, circular ownership, shared auditor, and companies founded close together in time — returned with weighted risk indicators, an overall risk level (lav/middels/hoy) and a node/edge graph. Use for due-diligence cluster analysis, shell-company / straw-man detection and fraud-pattern research. Requires the customer's koblingsanalyse extension; the company count is capped by their tier. Look up orgnrs via search_companies first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "orgnrs": "<orgnrs>"
    },
    "name": "firmaradar_find_shared_connections"
  }
}

Input Schema

Name	Required	Description	Default
`orgnrs`	Yes	2–10 Norwegian organisation numbers (9 digits each) to analyse together.

Output Schema

Name	Required	Description	Default
`graf`	No	{noder, kanter} for graph rendering.
`meta`	No
`summary`	No
`selskaper`	No	Companies analysed ({orgnr, navn}).
`risiko_niva`	No		ukjent
`felles_eiere`	No
`risiko_score`	No
`stiftet_tett`	No
`felles_adresser`	No
`felles_personer`	No
`felles_morselskap`	No
`risiko_indikatorer`	No
`sirkulaer_eierskap`	No
`felles_revisor_selskap`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedJun 22, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With annotations already declaring readOnlyHint and idempotentHint, the description adds valuable context: the extension requirement, company count cap, and the output structure (weighted risk indicators, overall risk level, node/edge graph). This goes beyond what annotations provide, informing the agent about business constraints and result format.

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?

The description is three sentences, each serving a distinct purpose: functionality/output, use cases, and constraints. It is front-loaded with the main action and results, and avoids redundancy with the schema.

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?

The tool has an output schema and one well-documented parameter. The description covers the analysis scope, output elements, prerequisites, and business constraints, making it complete for the task. The extension requirement and tier cap are crucial for successful invocation and are explicitly stated.

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 coverage is 100% as the orgnrs parameter is fully described with min/max items and format. The description reinforces this by mentioning '2–10 Norwegian companies' and that they are analysed 'together', but does not add new parameter-level details beyond the schema. The baseline of 3 applies due to high schema coverage.

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 uses a specific verb 'Analyse' with a clear resource 'hidden connections across 2–10 Norwegian companies' and lists specific connection types (shared board members, address, owners, auditor). This distinguishes it from sibling tools like get_company_ownership or find_related_companies, which focus on single companies or simpler relations.

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?

The description explicitly states 'Use for due-diligence cluster analysis, shell-company / straw-man detection and fraud-pattern research' and provides a prerequisite ('Look up orgnrs via search_companies first'). It also notes the extension requirement and tier cap, giving clear context for when this tool is appropriate. However, it does not explicitly state when not to use it or name alternatives.

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

All Firmaradar 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.