# FedSalary: official pay data (remote · fedsalary.com)

Official pay statistics for any job and place, offer checks and two-offer comparisons.

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `fedsalary.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp.md), [page](https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp)

## Channel facts

- Endpoint: `https://fedsalary.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-21.

- **Endpoint Security**: 74/100
  - 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.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 61/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1775 tokens (~295/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 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.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 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 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the FedSalary: official pay data MCP server?

FedSalary: official pay data is a hosted endpoint at https://fedsalary.com/api/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 com-fedsalary-official-pay 'https://fedsalary.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-fedsalary-official-pay": {
      "url": "https://fedsalary.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-fedsalary-official-pay": {
      "type": "http",
      "url": "https://fedsalary.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-fedsalary-official-pay]
url = "https://fedsalary.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-fedsalary-official-pay": {
      "type": "remote",
      "url": "https://fedsalary.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-fedsalary-official-pay --url 'https://fedsalary.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-fedsalary-official-pay:
    url: "https://fedsalary.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-fedsalary-official-pay": {
      "Transport": "http",
      "Url": "https://fedsalary.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-fedsalary-official-pay -t streamable-http -u 'https://fedsalary.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-fedsalary-official-pay": {
      "type": "http",
      "url": "https://fedsalary.com/api/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.

### 2026-11-21 (score 71, 0)

- [cosmetic] “find_jobs” added an optional parameter “pay_basis”
- [cosmetic] “match_jobs” reworded the description of “min_pay”

### 2026-11-20 (score 71, +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.

### 2026-11-19 (score 70, +1)

- [security regression] HSTS header: unverified → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.33

### 2026-11-17 (score 69, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] Stability: 0.23 → unverified
- [security regression] HSTS header: fail → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-16 (score 69, +1)

- [security regression] HSTS header: unverified → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [functional regression] MCP protocol: unverified → fail
- [functional improvement] Endpoint reachability: unreachable → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.23

### 2026-11-15 (score 68, 0)

- [security regression] Endpoint reachability: reachable → unreachable
- [security regression] HSTS header: fail → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.17 → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-14 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 67, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1344 → 1739
- [functional] New tool “match_jobs”
- [cosmetic] “find_jobs” added an optional parameter “remote_only”

## MCP tools (6)

### `get_pay` (~220 tokens)

Official pay for a job

Official pay statistics for one job in one place: median, 10th to 90th percentiles, employment, the publisher and reference period, take-home pay where the site shows it, and for US states and metro areas the U.S. Department of Labor's four wage levels (entry to fully competent). Covers the US (national, every state, the 50 largest metro areas), Canada (national, provinces) and the UK (national; regions are a table on the national answer). Returns the page's Markdown copy with a citation line.

Input parameters:

- `job` (string, required): Job title as people say it (registered nurse, software engineer), a FedSalary page slug (registered-nurses) or an occupation code (SOC 29-1141, NOC 31301).
- `place` (string): us, ca or uk for a whole country (default us); a US state (texas or TX); a large US metro area (austin, seattle); a Canadian province (ontario); a UK region (london).

### `check_pay` (~172 tokens)

Check a pay offer or range

Where a job offer's pay, or a posted pay range, sits on the official pay distribution for the same job and place: the percentile span, the median, US take-home pay at the midpoint after federal and state tax, and for US metro areas which Department of Labor wage level (entry to fully competent) the pay meets. Same places as get_pay.

Input parameters:

- `job` (string, required): Job title, FedSalary slug or occupation code.
- `max` (number): High end of the range (optional).
- `min` (number, required): Low end of the range, or the only figure.
- `place` (string, required): us, ca, uk, a US state or large metro area, a Canadian province or a UK region.
- `unit` (string): year or hour. UK places take year only.

### `compare_offers` (~212 tokens)

Compare two US job offers

Two US job offers, each a pay figure in a state or one of the 50 largest metro areas, compared after federal income tax, Social Security, Medicare and state income tax, then after local prices (BEA regional price parities, rent included). Returns take-home pay, take-home at national prices, which offer is worth more and by how much, and the salary each place would need to match the other. With a job, also where each offer sits on the official pay distribution. City and county income taxes are not included.

Input parameters:

- `a_pay` (number, required): Offer A's pay.
- `a_place` (string, required): Offer A's place: a US state or large metro area.
- `b_pay` (number, required): Offer B's pay.
- `b_place` (string, required): Offer B's place.
- `job` (string): Optional job title or slug, to place each offer on the official distribution.
- `unit` (string): year or hour, for both offers (default year).

### `find_jobs` (~455 tokens)

Find current job openings with their pay

Current job openings in the US and Canada from employers' own job boards and US federal announcements from USAJOBS (read through their documented APIs, refreshed weekly), matching keywords and a place. Each result: title and employer as posted, places, posting date, the pay range when the employer published one, and when it did not, the official BLS median for the occupation in the US state named (national for US remote jobs); for published US ranges, where the range sits on the official distribution; and the link to apply on the employer's own site. Results are newest first or by published pay. Coverage is strongest for technology, finance, startups and remote work; many hospitals, retailers and state and local governments are not included yet, so few or no results does not mean no such jobs exist. No job descriptions; FedSalary takes no applications.

Input parameters:

- `federal_only` (boolean): true = only US federal job announcements (from USAJOBS; apply on USAJOBS).
- `keywords` (string): Words matched against the job title and employer, all of which must match (data analyst, product manager, Stripe).
- `min_pay` (number): Minimum yearly pay in USD: the top of the published range must reach it (Canadian ranges converted). Jobs without published pay are left out when this is set.
- `pay_basis` (string): With min_pay, require the published annual minimum (year) or hourly minimum (hour, compared to min_pay / 2,080). Omit for the top of the annualized range.
- `place` (string): A US state (texas or TX), a US metro area or large city (austin), remote (US remote jobs), canada, a Canadian province (ontario) or a large Canadian city (toronto). Leave out for everywhere.
- `published_pay_only` (boolean): true = only jobs that publish a pay range.
- `remote_only` (boolean): true = only jobs the employer marks remote, on top of any place (remote jobs open to Texas: place texas, remote_only true). For remote jobs anywhere in the US, set place to remote instead.
- `sort` (string): new (default) or pay.

### `match_jobs` (~317 tokens)

Jobs that fit a person's experience

Current US and Canadian openings ranked by how closely they fit a person's work history: the job titles they have held, years of experience, skills, place and minimum pay. Each title is read as the occupation that most employers' current postings with that title fall under; openings are then ranked by title match, same or neighbouring occupation, skills named in the posting's title and seniority fit (intern and junior roles drop for experienced people, senior roles for people starting out). Each result says why it is listed, with the pay range the employer published or the official median when it published none, and the link to apply on the employer's site. No job descriptions are read, so a skill counts only when the employer put it in the job title. Nothing about the person is stored. Same coverage limits as find_jobs.

Input parameters:

- `include_remote` (boolean): With a place: also include remote jobs (default true).
- `min_pay` (number): Minimum of the employer’s posted yearly salary in USD. Hourly estimates and jobs without published salaries are excluded.
- `place` (string): A US state (texas or TX), a large US metro area (austin), canada or a Canadian province. Leave out for everywhere.
- `skills` (array): Skills or specialties, twelve at most (ICU, pediatrics, Python).
- `titles` (array): Job titles the person has held, most recent first, three at most (registered nurse, charge nurse).
- `years_experience` (number): Years of work experience.

### `take_home` (~213 tokens)

US take-home pay after tax

Take-home pay on a US salary or hourly wage in a state or one of the 50 largest metro areas: federal income tax, Social Security, Medicare, the state's income tax and the state's employee payroll contributions where it has them (disability insurance, paid family leave, long-term care, employee unemployment insurance), using the state's newest published rules with the federal rules of the same year. Single filer, no dependents, standard deduction, wage income only; city and county income taxes are not included. Returns the yearly, monthly and per-paycheck amounts with each tax line and a link to the state's calculator page.

Input parameters:

- `pay` (number, required): Pay before tax: a yearly salary, or an hourly wage with unit hour.
- `place` (string, required): A US state (ohio or OH) or a large US metro area (austin, seattle). us gives federal taxes only.
- `unit` (string): year (default) or hour; hourly pay is annualized at 2,080 hours.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 71
- 2026-11-19: 70
- 2026-11-18: 69
- 2026-11-17: 69
- 2026-11-16: 69
- 2026-11-15: 68
- 2026-11-14: 68
- 2026-11-13: 67
- 2026-11-12: 67
- 2026-11-11: 67
- 2026-11-10: 66
- 2026-11-09: 66

## Common questions

### What is the FedSalary: official pay data MCP server?

FedSalary: official pay data is an MCP server listed in the public MCP registry as com.fedsalary/official-pay. Official pay statistics for any job and place, offer checks and two-offer comparisons. This page covers its hosted endpoint (https://fedsalary.com/api/mcp).

### Is the FedSalary: official pay data MCP server safe to use?

FedSalary: official pay data scores 71 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 FedSalary: official pay data MCP server expose?

FedSalary: official pay data exposes 6 tools: get_pay, check_pay, compare_offers, find_jobs, match_jobs, take_home. Their descriptions and schemas cost roughly 1,589 tokens of context every time the server is loaded.

### Does the FedSalary: official pay data MCP server require authentication?

No. We connected to FedSalary: official pay data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the FedSalary: official pay data MCP server still maintained?

FedSalary: official pay data is still listed as active in the MCP registry. We last reached this channel on 21 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 FedSalary: official pay data MCP server?

VerifyMCP ran 13 checks on FedSalary: official pay data, 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://fedsalary.com/api/mcp
- Website: https://fedsalary.com/connect/
- Changelog RSS feed: https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-fedsalary-official-pay/api-mcp
