Free, no-registration Model Context Protocol server that generates professional debt-collection demand letters: a print-ready PDF (formal letter + matching envelope), localized and legally formatted for 100+ jurisdictions and 33 languages (including Arabic/RTL, CJK, Indic, Thai, Cyrillic, and Greek).
Website: https://finalnotice.io
Hosted MCP endpoint: https://finalnotice.io/mcp (Streamable HTTP, JSON-RPC 2.0)
No auth, no API key, free.
The rendering engine (fonts, layout, jurisdiction rules) runs on the hosted service. This package is a thin stdio MCP server that forwards the three tools to the free public API, so you can run it locally or point any MCP client at the hosted endpoint.
claude mcp add --transport http final-notice https://finalnotice.io/mcp{
"mcpServers": {
"final-notice": { "type": "http", "url": "https://finalnotice.io/mcp" }
}
}{
"mcpServers": {
"final-notice": { "command": "npx", "args": ["-y", "finalnotice-mcp"] }
}
}docker build -t finalnotice-mcp .
docker run -i --rm finalnotice-mcpThe stdio server calls https://finalnotice.io by default; override with the
FINALNOTICE_API_BASE environment variable.
Related MCP server: mcp-europe-business
Tool | Description |
| Supported countries, currencies, languages, and tones. Call first to pick a valid jurisdiction + language. |
| Render the letter's text (title, subject, body, amount, legal reference, closing) as structured JSON — no PDF — to review wording. |
| Generate the finished PDF (letter + envelope) and return it as a base64 resource. |
generate_demand_letter arguments){
"jurisdiction": "GB",
"language": "en",
"tone": "final",
"senderName": "Acme Ltd",
"senderType": "business",
"attested": true,
"senderAddress": "1 High St\nLondon",
"debtorName": "J. Smith",
"debtorAddress": "2 Park Rd\nLeeds",
"debtorType": "individual",
"amount": 2450,
"currency": "GBP",
"invoiceNumber": "INV-1042",
"deadlineDays": 14
}Required fields: senderName, senderAddress, debtorName, debtorAddress, amount (> 0).
Business/firm senders must set attested: true. Set debtorType: "individual" to apply
consumer-protection rules where they exist (e.g. the UK Pre-Action Protocol for Debt
Claims 30-day period, or the Dutch WIK fourteen-day wording).
A REST API mirrors the MCP tools: GET /api/meta, POST /api/preview, POST /api/generate.
This is not legal advice; letters are factual, non-threatening templates.
The service is free; an optional donation link is at https://finalnotice.io/donate.
MIT — see LICENSE.
Generate the finished demand-letter PDF (formal letter + matching envelope), localized and legally formatted for the jurisdiction. Returns the PDF as a base64 resource. Free, no registration.
| Name | Required | Description | Default |
|---|---|---|---|
| bank | No | Payment/bank details keyed by field (e.g. {bankName, iban, accountNumber}). Optional. | |
| tone | No | Escalation level. Default: final. | |
| amount | Yes | Amount owed, as a number (no separators). Required, > 0. | |
| attested | No | Confirms authorization to send under the sender name. Required when senderType is business/firm. | |
| currency | No | ISO 4217 currency (optional; defaults to the jurisdiction's). | |
| language | No | Letter language code (e.g. en, es, fr, de, pt, ar, zh, ja). Must be offered for the jurisdiction; defaults to en. | |
| senderRef | No | Creditor's own reference number (optional). | |
| debtorName | Yes | Debtor name. Required. | |
| debtorType | No | Whether the debtor is a private individual (consumer) or a business. 'individual' activates jurisdiction consumer rules (e.g. GB Pre-Action Protocol 30-day floor, NL WIK wording). Default: business. | |
| enclosures | No | Enclosed documents, printed as 'Encl.: …' under the signature (e.g. 'Copy of invoice INV-123'). Optional. | |
| senderName | Yes | Creditor name (person or business). Required. | |
| senderType | No | Creditor type. Business/firm requires attested=true. | |
| signerName | No | Name of the person signing (optional; defaults to senderName). | |
| description | No | What the debt is for (optional). | |
| senderTitle | No | Signer's job title (optional). | |
| deadlineDays | No | Days from issue to pay (optional; default 14). | |
| jurisdiction | No | ISO 3166-1 alpha-2 country code of the debtor (e.g. US, GB, DE, BR, AE). Use list_jurisdictions for the full set; XX = generic/international. | |
| originalDate | No | ISO date the debt was incurred/invoiced (optional). | |
| debtorAddress | Yes | Debtor postal address, multi-line. Required. | |
| invoiceNumber | No | Invoice/account number (optional). | |
| senderAddress | Yes | Creditor postal address, multi-line (\n separated). Required. | |
| senderContact | No | Creditor email/phone (optional). | |
| deliveryMethod | No | How the letter is sent; printed as a notation above the recipient (e.g. 'By registered post and email'). Optional. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides basic behavior: generates PDF, returns base64. It mentions localization and legal formatting but omits details on processing time, size limits, authentication, or data storage. Adequate for a generation tool but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences: first states core function and output, second adds 'Free, no registration.' Front-loaded with essential information, no redundant words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 23 parameters, nested objects, and no output schema, the description covers core functionality but does not mention prerequisites like jurisdiction requirement or input validation. Sibling tools are not referenced, missing guidance on tool interactions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents each parameter. The description adds no parameter-level meaning beyond summarizing the tool's purpose. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it generates a finished demand-letter PDF, including formal letter and envelope, localized and legally formatted. It explicitly mentions the output as a base64 resource, distinguishing it from siblings like list_jurisdictions and preview_demand_letter.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for generating final documents but does not explicitly state when to use this tool versus preview_demand_letter or list_jurisdictions. It lacks direct guidance on when not to use it or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every supported country/jurisdiction (code, name, currency, default language) plus the available languages and tones. Call this first to pick a valid jurisdiction + language.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It implies a read-only operation but doesn't explicitly state safety, side effects, or data freshness. However, for a simple list tool, this is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the main action. Every word serves a purpose: describes contents and suggests usage. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and no annotations, the description is nearly complete. It explains what the tool returns and when to use it. Could specify output structure (e.g., array) but sufficient for a simple list.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in schema (100% coverage), so description's job is to explain output. It lists what the tool returns, providing useful context beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists supported countries with specific fields (code, name, currency, default language) plus languages and tones. It distinguishes from siblings (generate/preview letters) by being a discovery tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Call this first to pick a valid jurisdiction + language,' guiding the agent to use it before other tools. No exclusions or alternatives mentioned, but the context implies it's for initial setup.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Render the demand letter's text content (title, subject, body paragraphs, amount line, legal reference, closing) as structured JSON, without producing a PDF. Use to review or refine wording before generating.
| Name | Required | Description | Default |
|---|---|---|---|
| bank | No | Payment/bank details keyed by field (e.g. {bankName, iban, accountNumber}). Optional. | |
| tone | No | Escalation level. Default: final. | |
| amount | Yes | Amount owed, as a number (no separators). Required, > 0. | |
| attested | No | Confirms authorization to send under the sender name. Required when senderType is business/firm. | |
| currency | No | ISO 4217 currency (optional; defaults to the jurisdiction's). | |
| language | No | Letter language code (e.g. en, es, fr, de, pt, ar, zh, ja). Must be offered for the jurisdiction; defaults to en. | |
| senderRef | No | Creditor's own reference number (optional). | |
| debtorName | Yes | Debtor name. Required. | |
| debtorType | No | Whether the debtor is a private individual (consumer) or a business. 'individual' activates jurisdiction consumer rules (e.g. GB Pre-Action Protocol 30-day floor, NL WIK wording). Default: business. | |
| enclosures | No | Enclosed documents, printed as 'Encl.: …' under the signature (e.g. 'Copy of invoice INV-123'). Optional. | |
| senderName | Yes | Creditor name (person or business). Required. | |
| senderType | No | Creditor type. Business/firm requires attested=true. | |
| signerName | No | Name of the person signing (optional; defaults to senderName). | |
| description | No | What the debt is for (optional). | |
| senderTitle | No | Signer's job title (optional). | |
| deadlineDays | No | Days from issue to pay (optional; default 14). | |
| jurisdiction | No | ISO 3166-1 alpha-2 country code of the debtor (e.g. US, GB, DE, BR, AE). Use list_jurisdictions for the full set; XX = generic/international. | |
| originalDate | No | ISO date the debt was incurred/invoiced (optional). | |
| debtorAddress | Yes | Debtor postal address, multi-line. Required. | |
| invoiceNumber | No | Invoice/account number (optional). | |
| senderAddress | Yes | Creditor postal address, multi-line (\n separated). Required. | |
| senderContact | No | Creditor email/phone (optional). | |
| deliveryMethod | No | How the letter is sent; printed as a notation above the recipient (e.g. 'By registered post and email'). Optional. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It states the tool renders text without producing a PDF, but does not explicitly declare it as read-only or free of side effects, nor mention authentication or rate limits. Basic transparency is present but incomplete.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description consists of two well-structured sentences: the first states the action and output type, the second states the use case. No wasted words; information is front-loaded and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
While the description covers purpose and basic behavior, it lacks details on the output structure (no output schema). With 23 parameters and nested objects, the agent might benefit from a clearer indication of how the JSON is structured. However, the description is sufficient for a preview tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so parameters are adequately documented. The tool description does not add additional meaning beyond what the schema already provides, meeting the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool renders demand letter text content as structured JSON without producing a PDF, and explicitly distinguishes it from the sibling generate_demand_letter by noting it is for review before generating.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use to review or refine wording before generating,' giving clear context for when to use. Alternatives are implied by sibling names (generate_demand_letter for final output), but no explicit when-not-to-use guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0generate_demand_letterlist_jurisdictionspreview_demand_letterScored across 3 tools
Each tool has a unique purpose: listing jurisdictions, previewing text, and generating the PDF. No overlap or ambiguity.
All tools follow the same snake_case verb_noun pattern (list_jurisdictions, preview_demand_letter, generate_demand_letter), providing a predictable naming convention.
Three tools is precisely the right number for this domain—covering listing, preview, and generation without bloat or insufficiency.
The tool set fully covers the demand letter workflow: jurisdiction selection, content preview, and final PDF generation. No obvious gaps.
Fill in 1,000+ legal PDF templates in many languages, get a signed PDF back. Free, no API key.
Generate invoice and receipt PDFs from JSON. Agent-callable document API with a free demo quota.
Generate attorney-drafted NDAs, MSAs, DPAs, and more as PDF, ODT, or Markdown. No account required.
Compliant legal documents from your AI assistant: 1,100+ templates, 15 countries, free preview.
