SecureLend Underwriting

ai.securelendPublished by securelend.aiOfficial publisherv1.0.0Updated Oct 29, 2026

Open a credit file, chase gaps, screen sanctions, draft a cited memo. Person decides.

VerifiedStreamable HTTPWeb executableFinanceSecurity & MonitoringBusiness & Commerce

Overview

AI-generated overview

Remote SecureLend MCP for lender underwriting: open a credit file, walk documents, screen sanctions and draft a cited credit memo for a human decision.

What you can do
  • Resolve and read listed companies, fetching annual filings with citations
  • Open and read credit cases, including status, facts, evidence, gaps and pending jobs
  • Index and walk a credit file, extracting facts and spreading financials
  • Score case facts against the active underwriting pack and list missing documents, drafting a chase email
  • Screen names against OpenSanctions and draft a cited credit memo from the file
  • Create and read underwriting packages, and register, check or release financed invoices on a blind anti-fraud registry
When to use it
For lending and credit teams that want an assistant to assemble a deal file, track missing documents and produce a cited draft memo inside an existing SecureLend workspace, while a person keeps the credit decision.
Requirements
A remote Streamable HTTP endpoint; nothing runs locally. Listing and initialization need no token, but tool calls require an OAuth bearer token with scope lender (authorization_code with PKCE S256). Sanctions screening needs a configured key. A SecureLend tenant workspace is implied.
Before you install
Tools write to your tenant: they open cases, start background jobs, create packages and register or delete invoice entries on a shared anti-fraud registry. Chase emails are drafted but not sent. Screening without a key writes nothing and does not pass the file. No tool approves a loan or moves money, and a person must make the decision.

Installation

In SourceWeft

  1. Open SecureLend Underwriting in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.securelend%2Flender/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "securelend-underwriting": {
      "type": "http",
      "url": "https://mcp.securelend.ai/v1/lender/mcp"
    }
  }
}

README

SecureLend Underwriting (MCP)

Public listing wrapper for SecureLend's remote underwriting MCP.

This repository does not run the server. The hosted Streamable HTTP endpoint is:

https://mcp.securelend.ai/v1/lender/mcp

What it does

Open a credit file, chase missing documents, screen sanctions when configured, and draft a cited credit memo. A person makes the credit decision. No tool approves a loan or moves money.

Connect

initialize, notifications/initialized, ping, and tools/list work without a token. tools/call requires OAuth (authorization_code + PKCE S256, scope lender).

Tools (11)

resolve_listed_company, read_listed_company, open_case, read_case, walk_credit_file, score_case_against_pack, chase_missing_documents, screen_sanctions, draft_memo_from_file, start_underwriting_package, read_package

Official registry metadata

See server.json (namespace ai.securelend/lender after domain verification).

Not this product

License

MIT

Source: README.md at commit 1a7749e

Tools

14

resolve_listed_company

Resolve listed company

Resolve a ticker, legal name, or CIK. Writes nothing. Returns one chosen company or the candidates.

ParametersasOfrequiredqueryrequired

read_listed_company

Read listed company filing

Fetches the annual filing and attaches a citation to the open case when the company resolves uniquely. Ambiguous names write nothing.

ParameterscikasOfrequiredquerycaseId

open_case

Open case

Open a case on the caller's tenant. Same record as New file. Ignores any tenant id in the arguments.

ParametersidemailsourcelegalName

read_case

Read case

Read one case: status, facts, evidence ids, gaps, recommendation, document file names and types, pending jobs, and memo id plus status. No storage keys.

ParameterscaseIdrequired

walk_credit_file

Walk credit file (extract + spread)

Index documents on the open case, extract facts from the package (including image PDFs where supported), and spread financials into the case. Starts or returns the walk job already running. Does not draft the credit memo and does not approve a loan.

ParameterscaseIdrequired

score_case_against_pack

Score case against underwriting pack

Score facts already on the open case against the active underwriting pack/rubric. Does not accept new facts in the arguments. Returns walk_pending while a file walk is still running. Does not approve a loan.

ParameterseventcaseIdrequired

chase_missing_documents

Chase missing documents

Name every missing pack document and missing required number. Drafts a chase email when the file has a borrower email, and does not send it. Returns the existing draft when the same items are still missing.

ParameterscaseIdrequired

screen_sanctions

Screen sanctions

Screen a name on the case with OpenSanctions. Same as Screen OpenSanctions. SANCTIONS or PEP. A missing key writes nothing and does not pass the file.

ParametersnamecaseIdrequiredcheckType

draft_memo_from_file

Draft memo from file

Draft a credit memo from the case file. Same CaseSchema.id as Draft from file. Uses the tenant model when one is saved, otherwise the file template.

ParameterscaseIdrequired

start_underwriting_package

Start underwriting package

Create a new underwriting package for a borrower and return deskUrl, dashboardUrl (hosted package page), and exportUrl (zip). Background checks may start automatically. Requires borrower, amount, currency, and security; a secured loan also needs a complete guarantee. Does not approve the loan. Human review remains required.

ParametersamountrequiredpricingpurposeborrowerrequiredcurrencyrequiredsecurityrequiredguaranteestenorMonthsamortisation

read_package

Read underwriting package

Read an underwriting package. Does not re-run the checks. POST requires an OAuth bearer token with scope lender. Pass packageId or caseId for the caller's workspace.

ParameterscaseIdpackageId

register_financed_invoice

Register financed invoice

Register a financed invoice on the blind anti-fraud registry. Stores only a keyed HMAC token and registrar hash, never supplier, debtor, invoice number, or amount. Returns conflict when another lender already registered it.

ParametersamountcaseIddebtorcurrencysupplierpurchaseIdinvoiceNumber

check_invoice_financed

Check invoice financed status

Check whether an invoice has already been financed on the blind registry. Pass supplier, debtor, invoiceNumber, amount, and currency, or a token. Returns only financed (true or false), matchKind, ownRegistration, and token. Never returns lender identity or invoice details.

ParameterstokenamountdebtorcurrencysupplierinvoiceNumber

release_financed_invoice

Release financed invoice

Delete a financed invoice registration from the blind anti-fraud registry when the invoice is paid off or withdrawn. Only the registering workspace can delete its token.

ParameterstokenamountcaseIddebtorcurrencysupplierpurchaseIdinvoiceNumber

Version history

1
  1. v1.0.0LatestOct 29, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts