# Workers' Rights

> Read-only employment-law research: 140K+ rulings, employer track records, rights & EEOC guides.

- name: com.workers-rights/employment-law
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 76/100 flags: no-repository
- quality: 66/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.workers-rights%2Femployment-law
- tools: https://api.protogrid.dev/v1/servers/com.workers-rights%2Femployment-law/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "employment-law": {
      "type": "http",
      "url": "https://www.workers-rights.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-91d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 66/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 9 of 9 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_eeoc_process (idempotentHint); get_evidence_preservation_checklist (idempotentHint); find_similar_cases (idempotentHint); …
- pass `tools.token_cost`: about 3,639 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 9, about 3,639 tokens to load them all
- tool set hash: 66942ee7a664c3e9f38c1aa9bdc63084
- tools last changed: 2026-10-09T22:33:20.475Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.workers-rights/employment-law.svg)](https://protogrid.dev/servers/com.workers-rights/employment-law)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-09 `search_rulings` changed (description)
  - before: Search published employment-law rulings from our research corpus by keyword, law, court, federal circuit, state, outcome, and date. Returns published opinions with citations, outcomes, procedural stage, employers, claim types, damages, and links to the full opinion. Use this to ground any claim about how employment cases have been decided. Results are quality-filtered (low-confidence and junk rows excluded).
  - after: Search published employment-law rulings from our research corpus by keyword, law, court, federal circuit, state, outcome, and date. Returns published opinions with citations, outcomes, procedural stage, employers, claim types, recorded monetary amounts, and links to the full opinion. Use this to ground any claim about how employment cases have been decided. Results are quality-filtered (low-confidence and junk rows excluded).
- 2026-10-06 `find_similar_cases` changed (description)
  - before: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the topics courts discussed most in opinions employees won vs. lost, and a few representative example cases. Counts are returned at three levels (nationwide, the federal courts of the state's region, and the state) with a detailed breakdown for one level: who won, award amounts, what happened at each stage, and topics. Relay which level a figure describes. A level with few opinions returns counts without a win rate. Each example says what happened and why it matched. Topic rows record what opinions discussed, not what courts found. Educational statistics from published opinions: never present a historical percentage as this person’s probability of winning. Not a prediction or legal advice.
  - after: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the topics courts discussed most in opinions employees won vs. lost, and a few representative example cases. Counts are returned at three levels (nationwide, the federal courts of the state's region, and the state) with a detailed breakdown for one level: who won, award amounts, what happened at each stage, and topics. Relay which level a figure describes. A level with few opinions returns counts without a win rate. Each example says what happened and why it matched. Topic rows record what opinions discussed, not what courts found. Educational statistics from published opinions: never present a historical percentage as this person’s probability of winning. Not a prediction or legal advice. In structured stages: won and wonPct count opinions the worker won in whole or in part (wonPct leaves rulings sent back out of its base), and sentBack counts rulings sent back to a lower court. wentForward and wentForwardPct include rulings sent back to a lower court and are kept for compatibility.
- 2026-10-05 `find_similar_cases` changed (description, inputSchema)
  - before: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the topics courts discussed most in opinions employees won vs. lost, and a few representative example cases. The result states exactly which comparison set was used: the stated state, that state plus its federal circuit, or nationwide, and whether it was limited to opinions that mention a stated federal law. Relay that scope with any figure. When too few opinions match, counts are returned without a win rate. Each example says why it matched. Topic rows record what opinions discussed, not what courts found. Educational statistics from published opinions: never present a historical percentage as this person’s probability of winning. Not a prediction or legal advice.
  - after: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the topics courts discussed most in opinions employees won vs. lost, and a few representative example cases. Counts are returned at three levels (nationwide, the federal courts of the state's region, and the state) with a detailed breakdown for one level: who won, award amounts, what happened at each stage, and topics. Relay which level a figure describes. A level with few opinions returns counts without a win rate. Each example says what happened and why it matched. Topic rows record what opinions discussed, not what courts found. Educational statistics from published opinions: never present a historical percentage as this person’s probability of winning. Not a prediction or legal advice.
- 2026-10-05 `get_evidence_preservation_checklist` changed (description)
  - before: Concrete checklist for a worker who senses termination coming or is in a deteriorating work situation: what to save (emails, chat DMs, performance reviews, HR records, pay records), in what order, and how to do it without crossing lines — preserving your own employment record is legal; taking company IP is not. Use this whenever someone says they think they are about to be fired, fears retaliation is escalating, mentions a PIP or sudden access changes, or asks what to do before reporting discrimination. Sections: 'today' (highest-leverage, minutes matter), 'this-week', 'quiet' (low-priority prep). Time-sensitive — employers often revoke system access during the termination call itself.
  - after: Concrete checklist for a worker who senses termination coming or is in a deteriorating work situation: what to write down, which records are already theirs to gather (pay records, documents they were given), and how to list everything else so an attorney can ask the employer to preserve it. It does not advise copying or forwarding material from an employer’s systems. Use this whenever someone says they think they are about to be fired, fears retaliation is escalating, mentions a PIP or sudden access changes, or asks what to do before reporting discrimination. Sections: 'today' (highest-leverage, minutes matter), 'this-week', 'quiet' (low-priority prep). Time-sensitive — employers often revoke system access during the termination call itself.
- 2026-10-05 `find_similar_cases` changed (description) **meaning changed**
  - before: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the factors that most helped employees win vs. lose, and a few representative example cases. This is the highest-value grounding tool for 'what are my chances / what matters' questions. Educational statistics, not a prediction or legal advice.
  - after: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the topics courts discussed most in opinions employees won vs. lost, and a few representative example cases. The result states exactly which comparison set was used: the stated state, that state plus its federal circuit, or nationwide, and whether it was limited to opinions that mention a stated federal law. Relay that scope with any figure. When too few opinions match, counts are returned without a win rate. Each example says why it matched. Topic rows record what opinions discussed, not what courts found. Educational statistics from published opinions: never present a historical percentage as this person’s probability of winning. Not a prediction or legal advice.
- 2026-10-04 `get_corpus_stats` changed (description)
  - before: Return live statistics about the Workers' Rights corpus: total number of court rulings in the research corpus, number of public attorney listings, number of monitored legal data sources, the date the corpus was last updated, and the distribution of case outcomes across the analyzed rulings. Use this to establish scale/credibility or to answer 'how much data do you have / how current is it'.
  - after: Return live statistics about the Workers' Rights corpus: total number of collected court records in the research corpus, number of public attorney listings, number of monitored legal data sources, the date the corpus was last updated, and the distribution of reportable outcomes before the employment browse filter. Use this to establish scale/credibility or to answer 'how much data do you have / how current is it'.

Full history: https://api.protogrid.dev/v1/servers/com.workers-rights%2Femployment-law/changes

## Remotes

- https://www.workers-rights.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (9)

- `explain_my_rights`: Explain which federal (and state, if a state is given) employment laws may protect a worker based on the type of issue (e.g. discrimination, harassment, retaliation, wrongful termination) and/or the protected class involved (e.g. race, sex, age, disability, pregnancy). Returns the relevant statutes with citations, who they cover (employer-size thresholds), filing deadlines and agencies, and available remedies. Use this to ground an answer about a worker’s legal protections. Deadline guidance covers private-sector and state/local government workers; federal employees follow a separate process with a much shorter deadline (45 days to contact their agency's EEO counselor). Educational information, not legal advice.
- `find_employment_attorney`: Find public-source employment-law attorney listings near a US location. Returns source-attributed identity, firm, location, and contact data sorted by proximity. Person-specific filters and fields apply only where the underlying directory supports them; Google Places metrics are labeled as firm/office listing data, never individual ratings. Listings are not state-bar verification or an endorsement.
- `find_similar_cases`: Given the facts of an employment situation — claim types, protected class, employer, state — analyze how similar real cases in the corpus were decided. Returns the aggregate plaintiff (employee) win rate, settlement rate, typical damages range, the topics courts discussed most in opinions employees won vs. lost, and a few representative example cases. Counts are returned at three levels (nationwide, the federal courts of the state's region, and the state) with a detailed breakdown for one level: who won, award amounts, what happened at each stage, and topics. Relay which level a figure describes. A level with few opinions returns counts without a win rate. Each example says what happened and why it matched. Topic rows record what opinions discussed, not what courts found. Educational statistics from published opinions: never present a historical percentage as this person’s probability of winning. Not a prediction or legal advice. In structured stages: won and wonPct count opinions the worker won in whole or in part (wonPct leaves rulings sent back out of its base), and sentBack counts rulings sent back to a lower court. wentForward and wentForwardPct include rulings sent back to a lower court and are kept for compatibility.
- `get_attorney_track_record`: Given an employment attorney name (or profile slug), return the federal employment-law cases on file in which that attorney appeared — case caption, court, year, nature-of-suit, and the side they appeared for when on record. Use this when a user names an attorney and wants their public litigation history. Facts only, sourced from federal court dockets. Attorney identities are algorithmically matched; ambiguous and lower-confidence matches are excluded. One case is one normalized court+docket number, so duplicate source rows do not inflate the count.
- `get_corpus_stats`: Return live statistics about the Workers' Rights corpus: total number of collected court records in the research corpus, number of public attorney listings, number of monitored legal data sources, the date the corpus was last updated, and the distribution of reportable outcomes before the employment browse filter. Use this to establish scale/credibility or to answer 'how much data do you have / how current is it'.
- `get_eeoc_process`: Plain-English guide to the 9 stages of an EEOC discrimination/retaliation charge, from pre-filing through resolution. Call with no arguments for an overview of all stages with typical durations; call with a stage number (1-9) for a deep-dive on that stage: what to expect, how long it takes, the key tip, and do/don't guidance. Use this whenever someone asks what happens after filing with the EEOC, how long the process takes, what a position statement or rebuttal is, or what to do at the stage they are currently in. Covers private-sector and state/local government workers; federal employees follow a separate EEO process with a much shorter deadline (45 days to contact their agency's EEO counselor).
- `get_employer_track_record`: Given an employer/company name, return distinct federal cases and trusted published opinions that involve that employer, the breakdown of outcomes (employee wins, employer wins, settlements, dismissals), the most notable recent opinions, AND the count of federal docket records on file (cases that may not have a written opinion). Use this when a user names their employer and wants that company's litigation history + footprint.
- `get_evidence_preservation_checklist`: Concrete checklist for a worker who senses termination coming or is in a deteriorating work situation: what to write down, which records are already theirs to gather (pay records, documents they were given), and how to list everything else so an attorney can ask the employer to preserve it. It does not advise copying or forwarding material from an employer’s systems. Use this whenever someone says they think they are about to be fired, fears retaliation is escalating, mentions a PIP or sudden access changes, or asks what to do before reporting discrimination. Sections: 'today' (highest-leverage, minutes matter), 'this-week', 'quiet' (low-priority prep). Time-sensitive — employers often revoke system access during the termination call itself.
- `search_rulings`: Search published employment-law rulings from our research corpus by keyword, law, court, federal circuit, state, outcome, and date. Returns published opinions with citations, outcomes, procedural stage, employers, claim types, recorded monetary amounts, and links to the full opinion. Use this to ground any claim about how employment cases have been decided. Results are quality-filtered (low-confidence and junk rows excluded).