Skip to main content
Glama

UK Due Diligence

by io.github.paulieb89

Get Companies House Filing Document

company_filing_document
Read-onlyIdempotent

Resolve a filing's document_metadata link to its authoritative source document.

Returns a resource_link (never embedded bytes, never base64) pointing at a company-document:// MCP resource — fetch it via resources/read to get the actual PDF. This tool only reads metadata (category, pages, available content types, byte size); it never downloads the document itself. Use company_filing_history first to find a filing's document_metadata URL.

Requires a resource-capable MCP client to retrieve the actual bytes — a tool-only client can see this result's metadata (company, category, page count, size) but cannot obtain the file through this tool call alone.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mime_typeNoWhich content representation to select, e.g. 'application/pdf'. Omit when the document has only one representation (the near-universal case) — it is auto-selected. Required if the document has more than one; omitting it in that case returns a validation error listing the choices.
document_metadata_urlYesThe document_metadata URL from a filing's links.document_metadata (returned by company_filing_history) — pass it through verbatim, not a document_id. Must be an exact https://document-api.company-information.service.gov.uk/document/{id} URL.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description explicitly discloses what never happens: no embedded bytes, no base64, no download of the PDF, and no direct retrieval of file bytes. It also clarifies that the tool reads only document metadata, which aligns with and enriches the annotation-provided safety profile.

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 description is slightly verbose but every sentence carries useful information, including the result format, metadata scope, prerequisite, and client constraint. It is front-loaded with the core action and return type, and the structured formatting makes the tripartite behavior easy to process.

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?

Without an output schema, the description fully compensates by explaining the returned resource_link, the way to fetch the PDF via resources/read, the metadata contents, and the prerequisite call to company_filing_history. It also covers environment constraints, making the tool call meaningfully complete for an AI agent.

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?

The input schema already documents both parameters thoroughly, including the exact URL format, pass-through requirement, and mime_type auto-selection behavior. The description adds little semantic information beyond repeating these instructions, so baseline 3 is appropriate given the 100% 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 names the specific verb 'Resolve' and the exact resource (a filing's document_metadata link), and states precisely what is returned: a resource_link to a company-document:// MCP resource. It also frames the tool's scope against company_filing_history, making the tool distinct from its siblings.

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?

It explicitly says 'Use company_filing_history first to find a filing's document_metadata URL', giving a clear prerequisite and sequencing instruction. It also explains the client requirement and notes the limitation for tool-only clients, helping an agent decide whether this tool is suitable for the current environment.

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

All UK Due Diligence toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation4/5

The domain-specific tools are clearly distinct (search vs profile for each register), and the generic search/fetch tools are designed to route across them. Potential overlap between company_officers and company_psc is resolved by clear descriptions of officers vs beneficial ownership. Slight ambiguity exists between generic fetch/search and the domain-specific counterparts, but the routing logic is well-documented.

Naming Consistency4/5

Most tools follow a consistent resource_action pattern with clear prefixes (charity_, company_, disqualified_, gazette_). Exceptions like company_officers, company_psc, sanctions_screen, and vat_validate deviate from the verb-first convention, and generic tools (fetch, search, get_prompt, list_prompts) do not follow the pattern. Overall, the naming is readable and predictable despite a few outliers.

Tool Count4/5

With 17 tools, the server sits slightly above the typical 3-15 well-scoped range, but the breadth of the domain (Companies House, Charity Commission, disqualifications, Gazette insolvency, sanctions, land registry, VAT) justifies the count. Each tool serves a distinct data source or action, and the two prompt-management tools are standard MCP utilities. The count feels appropriate rather than excessive.

Completeness4/5

The server covers the core due diligence workflow: searching and retrieving profiles for companies, charities, and disqualified directors, plus insolvency notices, sanctions screening, land transactions, and VAT validation. Minor gaps exist, such as no direct tool for company accounts or court judgments, but these are not core to the apparent purpose and can be worked around.

Resources