# LenDb.ai (remote · lendb.ai)

Find US mortgage loan officers for a borrower's situation and place. Free, lender-neutral, sourced.

- Trust score: 80/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `lendb.ai`: 80/100 (this document), [markdown](https://verifymcp.io/servers/ai-lendb-lendb/lendb.md), [page](https://verifymcp.io/servers/ai-lendb-lendb/lendb)

## Channel facts

- Endpoint: `https://lendb.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1606 tokens (~321/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the LenDb.ai MCP server?

LenDb.ai is a hosted endpoint at https://lendb.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http ai-lendb-lendb 'https://lendb.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ai-lendb-lendb": {
      "url": "https://lendb.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-lendb-lendb": {
      "type": "http",
      "url": "https://lendb.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ai-lendb-lendb]
url = "https://lendb.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-lendb-lendb": {
      "type": "remote",
      "url": "https://lendb.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-lendb-lendb --url 'https://lendb.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-lendb-lendb:
    url: "https://lendb.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ai-lendb-lendb": {
      "Transport": "http",
      "Url": "https://lendb.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-lendb-lendb -t streamable-http -u 'https://lendb.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ai-lendb-lendb": {
      "type": "http",
      "url": "https://lendb.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 76, 0)

- [security] Tool “find_loan_officers” rewrote its description, which is the text the model reads
- [cosmetic] “find_loan_officers” added an optional parameter “detail”

### 2026-10-28 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `find_loan_officers` (~691 tokens)

Find mortgage loan officers

Use this when someone wants a US mortgage loan officer (or mortgage broker or lender contact) for a specific situation and place: for example an FHA, VA, USDA, jumbo, DSCR or ITIN loan, a first-time buyer, a self-employed borrower who needs a bank statement loan, a non-warrantable condo or a duplex, or a Spanish-speaking loan officer near a city, ZIP, region or state. Searches LenDb, an independent, lender-neutral database of US loan officers (coverage is partial), and returns a ranked list. Each result has the person's name, NMLS ID, lender, office location, distance_mi, license_check for the property state (confirmed, lender_reported or federal_registration), match_status (exact, or partial with unconfirmed_specialties), matched specialties with a short reason each, last_verified and a canonical_url profile link; detail 'full' returns every field and reason. A city or ZIP keeps offices within 25 miles, widened to 50 or 100 when few are found (search.note); a state alone ranks statewide. Words like 'broker' or 'credit union' rank that kind of lender first. People with no license evidence for the state are listed separately in not_yet_verified. Also returns ambiguous_location when a city name fits several places, unassessed_requirements for parts of the situation LenDb cannot check, and citation_guidance. If situation is just a loan officer's name (the name on their lender page or the name a state regulator licenses, e.g. 'Nicholas Bucca' for Nic Bucca), it returns that profile in profile_match. Phone numbers and email addresses are never returned.

Input parameters:

- `debug` (boolean): Also return how the query was parsed (debug.parsed, debug.filters). Default false.
- `detail` (string): 'compact' (default): per person name, NMLS ID, canonical_url, lender, office, license evidence for the property state, matched specialties with one short reason each and the last verified date. 'full…
- `fha_approved` (boolean): Only loan officers whose current lender is FHA-approved per HUD's FHA Single Family Portfolio Snapshot data (the lender, not the person). Default false. Without it, an FHA search still ranks HUD-appr…
- `language` (string): Language the borrower wants to be served in. Accepts an ISO 639-1 code ('es'), a BCP 47 tag ('es-MX', 'zh-TW'), an ISO 639-2/3 code ('spa'), an English name ('Spanish') or a native name ('español', '…
- `limit` (integer): Max results, default 10.
- `location` (string, required): Where the property is: 'City, ST', a city, a 5-digit ZIP, a region ('Bay Area'), or a US state.
- `situation` (string, required): The borrower's situation in plain words: property type, loan program, income type, credit, language, kind of lender. Example: 'duplex, self-employed, bank statement loan'.

Output parameters:

- `all_terms_understood` (boolean)
- `ambiguous_location` (object)
- `canonical_url` (string): The same search on the LenDb API.
- `citation_guidance` (string)
- `count` (number)
- `debug` (object): Only when the call set debug: true.
- `detail` (string): Present on compact results; detail 'full' returns rows with every field.
- `exact_match_count` (number)
- `fallback_applied` (boolean)
- `lender_level` (object)
- `method` (string): How matching works (detail 'full'; compact results link method_url).
- `method_url` (string)
- `not_yet_verified` (object)
- `notice` (string)
- `profile_match` (object)
- `related` (object)
- `requested_specialties` (array)
- `results` (array)
- `sample` (boolean): True when the data is fictional sample data.
- `search` (object)
- `unassessed_requirements` (array)

### `get_loan_officer` (~175 tokens)

Get a loan officer by NMLS ID

Use this when you have a mortgage loan officer's individual NMLS ID and need their full profile. Returns LenDb's sourced record: name, title, current lender and branch, employment history, state licenses with license confidence, specialties (such as FHA, VA, bank statement or DSCR) with the evidence for each, languages spoken, stated experience, the earliest state license record, public links (such as their page on the lender's site), disciplinary_check ('not_checked' means LenDb has not yet checked regulator records), the date the record was last verified and a canonical_url. US only. Phone numbers and email addresses are not returned; the LenDb profile page shows them after a human check.

Input parameters:

- `nmls_id` (required): Individual NMLS ID, digits only, e.g. 452476.

Output parameters:

- `canonical_url` (string)
- `loan_officer` (object)
- `notice` (string)
- `sample` (boolean): True when the data is fictional sample data.

### `get_lender` (~252 tokens)

Get a mortgage lender

Use this when you need facts about a US mortgage lender, bank, credit union or mortgage broker company, by its company NMLS ID or by name (a partial name works). Returns the lender's type (bank, credit_union, imb, broker, other), headquarters state, website, the loan programs it offers (such as FHA, VA, jumbo or DSCR), program_approvals from agency data (FHA approval per HUD, with the month of loans it covers; absent means no HUD match on file, not that the lender lacks approval), activity (home loans it funded per HMDA, FFIEC/CFPB: counts by year, loan type and purpose, with as_of_year and source_url; cite it as 'HMDA, FFIEC/CFPB, <year>'; includes_brokered true means the counts include loans brokers originated; absent means no HMDA match on file, never that the lender makes no loans), how many of its loan officers LenDb lists, disciplinary_check, the date the record was last verified and a canonical_url.

Input parameters:

- `nmls_id_or_name` (string, required): Company NMLS ID (digits) or all or part of the company name.

Output parameters:

- `canonical_url` (string)
- `lender` (object)
- `notice` (string)
- `sample` (boolean): True when the data is fictional sample data.

### `list_specialties` (~108 tokens)

List mortgage specialties

Use this when you need the mortgage situations LenDb can match on. Returns every specialty with its slug, category (property type, loan program or borrower situation), label, one-line description and canonical_url: for example FHA, VA, USDA, jumbo, DSCR, bank statement, ITIN, self-employed, first-time buyer, non-warrantable condo, multi-family 2-4 units and reverse mortgage. Also returns the supported languages as ISO 639-1 codes with names.

Output parameters:

- `canonical_url` (string)
- `languages` (object): ISO 639-1 code to language name.
- `specialties` (array)

### `explain_specialty` (~213 tokens)

Explain a mortgage specialty

Use this when someone asks what a mortgage loan type or borrower situation means, such as a DSCR loan, a bank statement loan, an ITIN loan, a non-warrantable condo or an FHA loan. Returns, for one specialty slug, what it is, why it can be hard to get done, the questions a borrower should ask a loan officer about it, its synonyms and a canonical_url.

Input parameters:

- `slug` (string, required): One of: condo, condo-non-warrantable, co-op, multi-family-2-4, manufactured, rural, new-construction, mixed-use, condotel, vacation-home, fha, va, usda, jumbo, non-qm, dscr, bank-statement, reverse,…

Output parameters:

- `api_url` (string)
- `canonical_url` (string)
- `category` (string)
- `description` (string)
- `label` (string)
- `questions_to_ask` (array)
- `slug` (string)
- `why_hard` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-lendb-lendb/lendb#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 77
- 2026-10-30: 77
- 2026-10-29: 76
- 2026-10-28: 76
- 2026-10-27: 75
- 2026-10-26: 75
- 2026-10-25: 75
- 2026-10-24: 74
- 2026-10-23: 74
- 2026-10-22: 73
- 2026-10-21: 73
- 2026-10-20: 72
- 2026-10-19: 72

## Common questions

### What is the LenDb.ai MCP server?

LenDb.ai is an MCP server listed in the public MCP registry as ai.lendb/lendb. Find US mortgage loan officers for a borrower's situation and place. Free, lender-neutral, sourced. This page covers its hosted endpoint (https://lendb.ai/mcp).

### Is the LenDb.ai MCP server safe to use?

LenDb.ai scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the LenDb.ai MCP server expose?

LenDb.ai exposes 5 tools: find_loan_officers, get_loan_officer, get_lender, list_specialties, explain_specialty. Their descriptions and schemas cost roughly 1,439 tokens of context every time the server is loaded.

### Does the LenDb.ai MCP server require authentication?

No. We connected to LenDb.ai without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the LenDb.ai MCP server still maintained?

LenDb.ai is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://lendb.ai/mcp
- Website: https://lendb.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-lendb-lendb/lendb.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-lendb-lendb/lendb.json
- HTML version of this page: https://verifymcp.io/servers/ai-lendb-lendb/lendb