# NL Ledger (remote · nlledger.ca)

NL provincial and federal spending records, each with its source. Addresses do not locate work.

- Trust score: 86/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `nlledger.ca`: 86/100 (this document), [markdown](https://verifymcp.io/servers/ca-nlledger-nl-ledger/nlledger.md), [page](https://verifymcp.io/servers/ca-nlledger-nl-ledger/nlledger)

## Channel facts

- Endpoint: `https://nlledger.ca/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.0`

## 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. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2083 tokens (~138/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 65% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_pay" implies "pay" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the NL Ledger MCP server?

NL Ledger is a hosted endpoint at https://nlledger.ca/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 ca-nlledger-nl-ledger 'https://nlledger.ca/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ca-nlledger-nl-ledger": {
      "url": "https://nlledger.ca/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ca-nlledger-nl-ledger": {
      "type": "http",
      "url": "https://nlledger.ca/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ca-nlledger-nl-ledger]
url = "https://nlledger.ca/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ca-nlledger-nl-ledger --url 'https://nlledger.ca/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ca-nlledger-nl-ledger:
    url: "https://nlledger.ca/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ca-nlledger-nl-ledger": {
      "Transport": "http",
      "Url": "https://nlledger.ca/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ca-nlledger-nl-ledger -t streamable-http -u 'https://nlledger.ca/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ca-nlledger-nl-ledger": {
      "type": "http",
      "url": "https://nlledger.ca/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 86, 0)

- [security] Stability: 0.97 → pass

### 2026-11-04 (score 86, 0)

- [functional] Stability: pass → 0.97

### 2026-10-31 (score 86, 0)

- [security] Stability: 0.97 → pass

### 2026-10-29 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (15)

### `get_pay` (~69 tokens)

Pay by employer

Published pay above $100,000 by employer and calendar year, people, common titles, overtime and severance. Missing lists are not zero; this is not total payroll. Omit employer to list employers. Individuals use search_records.

Input parameters:

- `employer` (string)
- `year` (string)

### `get_body` (~53 tokens)

Public body records

A public body's reported values by year and source, and largest suppliers, matching its page. Award values are not payments; overlapping and federal sources stay labelled. Omit name to list bodies.

Input parameters:

- `name` (string)

### `tax_receipt` (~50 tokens)

Employment income tax receipt

Estimate provincial income tax on annual employment income and illustrate department spending shares, using the receipt page's assumptions. Not a personal tax assessment or a trace of your tax payments.

Input parameters:

- `income` (number, required)

### `get_totals` (~142 tokens)

Totals and rankings

Full-record totals or rankings filtered by supplier, named buyer, year or source. Groups by supplier, buyer/department, year or source, separately by source and currency with overlap exclusions. Awards are not payments; use get_department for program spending. No paginated-search sums.

Input parameters:

- `body` (string)
- `body_id` (string)
- `department` (string)
- `group_by` (string)
- `limit` (integer)
- `source` (string)
- `supplier` (string)
- `supplier_id` (string)
- `year` (string): Original record calendar year or published fiscal period; not annual spending.

### `search_records` (~302 tokens)

Search spending records

Search every line item: contract awards, federal contracts and grants, minister and MHA expense lines, and pay over $100,000. records holds exact matches: every word matches (by prefix), largest amount first, up to 25 per page (use page for more). A misspelled word is corrected when nothing matches exactly (see corrected). On page 1, related_by_meaning adds up to 20 records about the same thing that do not contain every word, closest first. Give a query, a filter, or both. Each record has its source citation. Sources: ppa = Provincial contract award; fed_contract = Federal contract; fed_grant = Federal grant or contribution; canadabuys = Federal award notice; pa_pss = Federal professional services payment; pa_tp = Federal transfer payment; sunshine = Public sector pay over $100,000; minister = Minister's expense claim; mha = MHA expense.

Input parameters:

- `page` (integer): Page number. Default 1.
- `pattern` (string): Flag id from list_flags, e.g. no-competition.
- `query` (string): Words to find, e.g. 'ferry repair', a company name, a town or a job title.
- `source` (string): Limit to one source.
- `supplier_id` (string): Supplier id from get_supplier.
- `year` (string): Calendar year of the record date, e.g. 2024.

### `get_record` (~78 tokens)

Get one record

Get one line item by its 12-character id. Returns retained source fields, evidence, inclusion rule, reported address/conflicts, separately supported location, native currency, amount kind and period, and citations. Federal amounts have no automatic provincial scaling.

Input parameters:

- `id` (string, required): Record id, e.g. 2ebb7ad3bd29.

### `get_supplier` (~107 tokens)

Get a supplier or recipient

Get included reported record values, all years, for a supplier or recipient, with explicit overlap/exclusion policy and breakdowns by source, amount kind, period, native currency and location evidence. These are not everything received, unique spending or spending in NL. Give a name or supplier_id; unmatched names return close matches.

Input parameters:

- `name` (string): Company or recipient name, e.g. 'Pennecon'.
- `supplier_id` (string): 10-character id from an earlier result.

### `get_department` (~119 tokens)

Get a provincial department's spending

Get a provincial department's gross spending by program: actual against amended and original estimates, for a fiscal year from 2019-20 to 2024-25, or the 2025-26 and 2026-27 estimates. Leave out name to list the departments and years.

Input parameters:

- `name` (string): Department name or part of it, e.g. 'Health'.
- `year` (string): Fiscal year, e.g. 2024-25 or 2026-27. Default: the latest year with actual spending.

### `get_budget` (~198 tokens)

Budget against actual, the deficit and net debt

Get what the province budgeted and what it spent in a fiscal year, the difference, the annual surplus or deficit, net debt, and every department's budget against its spending, largest difference first. Years from 2019-20; the newest budgets have no published results yet. Two bases that must not be added together: departments_spending is modified cash (the Estimates given to the House against the Report on the Program Expenditures and Revenues); whole_government is the audited Public Accounts (accrual, all government bodies), the only source for the surplus or deficit and net debt. Every figure has its source link. Leave out year for the latest year with published results.

Input parameters:

- `department` (string): Part of a department name, to return only matching departments, e.g. 'Health'.
- `year` (string): Fiscal year, e.g. 2024-25. Default: the latest year with published results.

### `get_members` (~137 tokens)

Compare MHA and minister expenses

Rank Members of the House of Assembly by allowance spending for a fiscal year, overall or for one category (for example travel), with the average. Give a name to get one member's spending by year and category. Set group to ministers for ministers' expense claim totals.

Input parameters:

- `category` (string): Words in the category name, e.g. 'travel', 'office', 'constituency'.
- `group` (string): Default mha.
- `name` (string): Part of a member's name.
- `year` (string): MHA fiscal year, e.g. 2024-25. Default: the latest full year.

### `list_flags` (~47 tokens)

List spending patterns

List the patterns people read as waste or perks (for example sole-source awards, contracts that grew, purchases just under a limit), with counts. Each pattern is a question, not a finding.

### `get_flag` (~57 tokens)

Get one spending pattern

Get one pattern by id (from list_flags): why people look at it, exactly how it is computed, what it cannot tell you, and its largest results.

Input parameters:

- `id` (string, required): Pattern id, e.g. no-competition.

### `human_scale` (~71 tokens)

Put an amount in human terms

Hypothetically divide a supported CAD amount by the NL population, households and reference median wage. Result states the denominator assumption and carries no geographic allocation, resident liability or local wage/employment claim. Includes Statistics Canada sources.

Input parameters:

- `amount` (number, required): Amount in Canadian dollars, e.g. 50000000.

### `search` (~56 tokens)

Search (for ChatGPT deep research)

Search the records and return a short list of results, each with id, title and url. Use fetch with an id to get the full record. Prefer search_records when you can pass filters.

Input parameters:

- `query` (string, required): Words to find.

### `fetch` (~30 tokens)

Fetch one record (for ChatGPT deep research)

Fetch the full text of one result from search, by id.

Input parameters:

- `id` (string, required): Id from search.

## Diagnostics

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

## Score history

- 2026-11-05: 86
- 2026-11-04: 86
- 2026-11-03: 86
- 2026-11-02: 86
- 2026-11-01: 86
- 2026-10-31: 86
- 2026-10-30: 86
- 2026-10-29: 86
- 2026-10-28: 85
- 2026-10-27: 85
- 2026-10-26: 84
- 2026-10-25: 84
- 2026-10-24: 83
- 2026-10-23: 83
- 2026-10-22: 82
- 2026-10-21: 82
- 2026-10-20: 81
- 2026-10-19: 81
- 2026-10-18: 80
- 2026-10-17: 80
- 2026-10-16: 79
- 2026-10-15: 79
- 2026-10-14: 79
- 2026-10-13: 78
- 2026-10-12: 78
- 2026-10-10: 77
- 2026-10-07: 75
- 2026-10-04: 74
- 2026-10-03: 73
- 2026-10-02: 73

## Common questions

### What is the NL Ledger MCP server?

NL Ledger is an MCP server listed in the public MCP registry as ca.nlledger/nl-ledger. NL provincial and federal spending records, each with its source. Addresses do not locate work. This page covers its hosted endpoint (https://nlledger.ca/mcp).

### Is the NL Ledger MCP server safe to use?

NL Ledger scores 86 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 NL Ledger MCP server expose?

NL Ledger exposes 15 tools: get_pay, get_body, tax_receipt, get_totals, search_records, and 10 more. Their descriptions and schemas cost roughly 1,516 tokens of context every time the server is loaded.

### Does the NL Ledger MCP server require authentication?

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

### Is the NL Ledger MCP server still maintained?

NL Ledger 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.

### What did VerifyMCP test on the NL Ledger MCP server?

VerifyMCP ran 13 checks on NL Ledger, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://nlledger.ca/mcp
- Website: https://nlledger.ca/data/
- Changelog RSS feed: https://verifymcp.io/servers/ca-nlledger-nl-ledger/nlledger.xml
- Changelog JSON feed: https://verifymcp.io/servers/ca-nlledger-nl-ledger/nlledger/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ca-nlledger-nl-ledger/nlledger.json
- HTML version of this page: https://verifymcp.io/servers/ca-nlledger-nl-ledger/nlledger