Skip to main content
Glama

Get Persons with Significant Control

company_psc
Read-onlyIdempotent

Identify beneficial ownership risks by fetching Persons with Significant Control for a UK company. Returns PSC entries with natures of control, nationality, and country of residence, flagging overseas corporate PSC as a risk signal.

Instructions

Fetch Persons with Significant Control (beneficial ownership) for a company.

Returns PSC entries with natures of control, nationality, and country of residence. Flags overseas corporate PSC entries as a beneficial ownership risk signal. Returns an explanatory note for widely-held PLCs with no registrable PSC.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
company_numberYesCompanies House company number (8 digits, e.g. '03782379'). Returned by company_search.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
company_numberYesCompanies House company number.
totalYesTotal PSC entries returned for this company.
overseas_corporate_psc_flagNoNumber of corporate PSCs registered outside the UK. Non-zero values indicate an offshore beneficial ownership chain.
pscNoPersons with Significant Control records.
noteNoExplanatory note when total=0. Typical for widely-held listed PLCs where no single person or entity holds 25%+ of shares or voting rights.

Implementation Reference

  • The company_psc tool handler function. It is a FastMCP tool decorated with @mcp.tool(name='company_psc') that accepts a company number and returns a CompanyPSCResult. It normalizes the company number and delegates to _fetch_company_psc.
    async def company_psc(
        company_number: Annotated[str, Field(description="Companies House company number (8 digits, e.g. '03782379'). Returned by company_search.", min_length=1, max_length=10)],
    ) -> CompanyPSCResult:
        """Fetch Persons with Significant Control (beneficial ownership) for a company.
    
        Returns PSC entries with natures of control, nationality, and
        country of residence. Flags overseas corporate PSC entries as a
        beneficial ownership risk signal. Returns an explanatory note for
        widely-held PLCs with no registrable PSC.
        """
        return await _fetch_company_psc(_normalise_company_number(company_number))
  • The _fetch_company_psc helper function that calls the Companies House API endpoint /company/{number}/persons-with-significant-control, parses PSC entries, computes the overseas corporate PSC flag, and returns a CompanyPSCResult.
    async def _fetch_company_psc(company_number: str) -> CompanyPSCResult:
        async with companies_house_client() as client:
            resp = await _request_with_retry(
                client, "GET",
                f"/company/{company_number}/persons-with-significant-control",
            )
            data = resp.json()
    
        raw_items = data.get("items", []) or []
        total = int(data.get("total_results", len(raw_items)) or 0)
    
        psc_entries: list[CompanyPSCEntry] = []
        overseas_flag = 0
        for raw in raw_items:
            natures = _truncate_natures(list(raw.get("natures_of_control") or []), 300)
            entry = CompanyPSCEntry(
                kind=raw.get("kind"),
                name=raw.get("name"),
                notified_on=raw.get("notified_on"),
                ceased_on=raw.get("ceased_on"),
                nationality=raw.get("nationality"),
                country_of_residence=raw.get("country_of_residence"),
                natures_of_control=natures,
                identification=raw.get("identification") or {},
                address=raw.get("address") or {},
            )
            psc_entries.append(entry)
    
            if entry.kind in (
                "corporate-entity-person-with-significant-control",
                "legal-person-person-with-significant-control",
            ):
                place = (entry.identification.get("place_registered") or "").upper()
                if place not in UK_JURISDICTIONS:
                    overseas_flag += 1
    
        note = None
        if total == 0:
            note = (
                "No registrable PSC. Typical for widely-held listed PLCs where "
                "no single person or entity holds 25%+ of shares or voting rights."
            )
        return CompanyPSCResult(
            company_number=company_number,
            total=total,
            overseas_corporate_psc_flag=overseas_flag,
            psc=psc_entries,
            note=note,
        )
  • CompanyPSCEntry model - a single Person with Significant Control record (kind, name, notified_on, ceased_on, nationality, country_of_residence, natures_of_control, identification, address).
    class CompanyPSCEntry(BaseModel):
        """A single Person with Significant Control record."""
    
        model_config = BASE_CFG
    
        kind: str | None = Field(
            None,
            description=(
                "Upstream 'kind' (e.g. 'individual-person-with-significant-control', "
                "'corporate-entity-person-with-significant-control')."
            ),
        )
        name: str | None = Field(None, description="PSC name (individual or entity).")
        notified_on: str | None = Field(
            None, description="Date notified as a PSC (ISO YYYY-MM-DD)."
        )
        ceased_on: str | None = Field(
            None,
            description="Date PSC status ceased, if applicable.",
        )
        nationality: str | None = Field(
            None, description="Declared nationality for individual PSCs."
        )
        country_of_residence: str | None = Field(
            None,
            description="Declared country of residence for individual PSCs.",
        )
        natures_of_control: list[str] = Field(
            default_factory=list,
            description=(
                "List of 'nature of control' descriptors (e.g. "
                "'ownership-of-shares-75-to-100-percent'). Individual entries may "
                "be truncated to 300 characters each."
            ),
        )
        identification: dict[str, Any] = Field(
            default_factory=dict,
            description=(
                "Identification block for corporate PSCs: place_registered, "
                "registration_number, country_registered, legal_authority, etc."
            ),
        )
        address: dict[str, Any] = Field(
            default_factory=dict,
            description="PSC correspondence address.",
        )
  • CompanyPSCResult model - the return type for company_psc, containing company_number, total, overseas_corporate_psc_flag, psc list, and an optional note.
    class CompanyPSCResult(BaseModel):
        """List of Persons with Significant Control for a company."""
    
        model_config = BASE_CFG
    
        company_number: str = Field(..., description="Companies House company number.")
        total: int = Field(
            ..., description="Total PSC entries returned for this company."
        )
        overseas_corporate_psc_flag: int = Field(
            0,
            description=(
                "Number of corporate PSCs registered outside the UK. Non-zero "
                "values indicate an offshore beneficial ownership chain."
            ),
        )
        psc: list[CompanyPSCEntry] = Field(
            default_factory=list,
            description="Persons with Significant Control records.",
        )
        note: str | None = Field(
            None,
            description=(
                "Explanatory note when total=0. Typical for widely-held listed PLCs "
                "where no single person or entity holds 25%+ of shares or voting rights."
            ),
        )
  • Registration of the company_psc tool via @mcp.tool(name='company_psc', ...) decorator within the register_tools(mcp) function. Registration happens at runtime in server.py line 158: companies_house.register_tools(mcp).
    # ------------------------------------------------------------------ #
    # 4. company_psc
    # ------------------------------------------------------------------ #
    @mcp.tool(
        name="company_psc",
        annotations={
            "title": "Get Persons with Significant Control",
            "readOnlyHint": True,
            "destructiveHint": False,
            "idempotentHint": True,
            "openWorldHint": True,
        },
    )
    async def company_psc(
        company_number: Annotated[str, Field(description="Companies House company number (8 digits, e.g. '03782379'). Returned by company_search.", min_length=1, max_length=10)],
    ) -> CompanyPSCResult:
        """Fetch Persons with Significant Control (beneficial ownership) for a company.
    
        Returns PSC entries with natures of control, nationality, and
        country of residence. Flags overseas corporate PSC entries as a
        beneficial ownership risk signal. Returns an explanatory note for
        widely-held PLCs with no registrable PSC.
        """
        return await _fetch_company_psc(_normalise_company_number(company_number))
Behavior5/5

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

The description adds behavioral context beyond annotations: it specifies what details are returned (natures of control, nationality, etc.), flags overseas corporate PSC entries as a risk signal, and mentions the explanatory note for PLCs. Annotations already indicate safety (readOnlyHint, idempotentHint) and description complements them without contradiction.

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?

Two concise sentences front-load the key action and results, with no unnecessary words. Every sentence earns its place.

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 annotations covering safety and idempotency, and an output schema presumably detailing return fields, the description is complete enough. It covers the tool's purpose, return data, and a special case.

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% and the description does not add new meaning to the parameter beyond what the schema provides (company_number is well-described in the schema). Baseline for high coverage is 3.

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 clearly states it fetches Persons with Significant Control (beneficial ownership) for a company, specifying what details are returned. It distinguishes from sibling tools like company_officers and company_profile by focusing on beneficial ownership.

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 implies usage for retrieving PSC data and mentions a special case for widely-held PLCs. However, it does not explicitly state when not to use this tool or compare with alternatives, though the context provides some guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/paulieb89/uk-due-diligence-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server