# Probative legal-marketing data

> Open US legal-marketing datasets with sources and DOIs, one server per dataset. CC BY 4.0.

- name: com.probativegrowth/legal-marketing-data
- version: 1.5.1
- connection class: R0 (autonomous)
- trust: 95/100
- quality: 87/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.probativegrowth%2Flegal-marketing-data
- tools: https://api.protogrid.dev/v1/servers/com.probativegrowth%2Flegal-marketing-data/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "legal-marketing-data": {
      "type": "http",
      "url": "https://probativegrowth.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% +updated-15d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 87/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### 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: 94 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 42 of 42 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- warn `tools.token_cost`: about 10,621 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 50 (weight 15)

- warn `stability.changes`: 120 tool changes in 30 days
- fail `stability.rug_pull`: 21 tools kept their name but changed most of their description in 30 days; review before trusting them
- pass `stability.new_links`: no tool change named a new site

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

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

- tools: 42, about 10,621 tokens to load them all
- tool set hash: fca8614f28ec5eca4c049be621ffe09b
- tools last changed: 2026-11-13T18:17:48.232Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.probativegrowth/legal-marketing-data.svg)](https://protogrid.dev/servers/com.probativegrowth/legal-marketing-data)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-13 `data_lookup` changed (inputSchema)
- 2026-11-10 `get_benchmark` changed (description)
  - before: Anonymized law-firm marketing benchmarks (ad costs, call outcomes, speed to sign), as bands, tiers and rounded values with the methods page to cite.
  - after: Law-firm marketing benchmarks (ad costs, call outcomes, speed to sign), as bands, tiers and rounded values with the methods page to cite.
- 2026-11-09 `calculate_fee_cap` changed (description)
  - before: The most a lawyer may charge, in dollars, on one award, settlement or past-due benefit under a legal fee cap.
  - after: The most a lawyer may charge, in dollars, on one award, settlement or past-due benefit, where a legal fee limit gives one figure.
- 2026-11-09 `data_lookup` changed (inputSchema)
- 2026-11-07 `get_state_market_brief` changed (description)
  - before: Every public number about marketing a law firm in one state or DC, joined from seven open datasets. Each figure carries its source and check date. Not a forecast. Results are not legal advice.
  - after: Every public number about marketing a law firm in one state or DC, joined from nine open datasets. Each figure carries its source and check date. Not a forecast. Results are not legal advice.
- 2026-11-07 `data_lookup` changed (inputSchema)
- 2026-11-05 `get_state_market_brief` changed (description)
  - before: Every public number about marketing a law firm in one state or DC, joined from seven open datasets. Results are not legal advice.
  - after: Every public number about marketing a law firm in one state or DC, joined from seven open datasets. Each figure carries its source and check date. Not a forecast. Results are not legal advice.
- 2026-11-02 `data_lookup` changed (inputSchema)
- 2026-11-01 `data_compare` changed (inputSchema)
- 2026-11-01 `whats_new` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/com.probativegrowth%2Flegal-marketing-data/changes

## Remotes

- https://probativegrowth.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.97333336)

## Packages

_none_

## Tools (42)

- `calculate_fee_cap`: The most a lawyer may charge, in dollars, on one award, settlement or past-due benefit, where a legal fee limit gives one figure.
- `check_ad_elements`: Which of one state's lawyer ad rules an ad touches, from what it contains (testimonials, past results, expert claims, actors, Spanish, AI) or its text. Results are not legal advice.
- `cite`: How to cite a dataset, a state or one record: the citation sentence, credit line, DOI and URL to cite. CC BY 4.0 asks for credit and a link.
- `compare_states`: Which states do what: one ad-rule topic (e.g. the waiting period before contacting accident victims, texting, filing) side by side across states, or all 50 and DC. Results are not legal advice.
- `data_compare`: Compare up to 10 states, counties or other keys of one dataset side by side, e.g. lawyer pay or bar pass rates in two states. Results are not legal advice.
- `data_lookup`: Figures for one state, county or other key from one open dataset, e.g. limitation periods, lawyers per resident, bankruptcy filings, law firms, court backlogs. Results are not legal advice.
- `data_search`: Find records by words across the open datasets when you do not know the key, e.g. "nursing home abuse" or "legal services price index". Results are not legal advice.
- `fees_compare`: Fee limits side by side for up to 10 jurisdictions (two-letter codes, DC, or US for federal programs), each with its cited source. Dataset: Attorney fee caps and contingency-fee rules, by state and federal program. Not legal advice.
- `fees_lookup`: The fee limits recorded for one US state, DC or US (federal programs): workers' comp, and where read, medical malpractice and contingency rules, each with its cap, what it applies to, who approves the fee, and the cited source. Dataset: Attorney fee caps and contingency-fee rules, by state and federal program. Not legal advice.
- `fees_search`: Fee-cap records whose text matches the words given, such as "workers comp 20%", "FTCA", "medical malpractice sliding scale" or a state name. Dataset: Attorney fee caps and contingency-fee rules, by state and federal program. Not legal advice.
- `fetch`: The full text of one record found with search (ids like rules:TX:filing, opinions:ny-nysba-1306 or benchmarks:speed-to-sign). Not legal advice.
- `filing_compare`: Ad filing duties and fees side by side for up to 10 states (two-letter codes, or DC). Dataset: What US state bars charge, and require, to file or review lawyer advertising. Not legal advice.
- `filing_lookup`: What one state or DC asks a lawyer to file before or after an ad runs: the filing duty, timing, standard, late and advisory fees, the portal, record-keeping, and the quoted primary sources. Dataset: What US state bars charge, and require, to file or review lawyer advertising. Not legal advice.
- `filing_search`: Ad filing records whose text matches the words given, such as "filing fee", "before first use" or a state name. Dataset: What US state bars charge, and require, to file or review lawyer advertising. Not legal advice.
- `get_ad_filing_requirements`: Whether a state's bar requires lawyers to file or submit ads for review, which ads, when. Results are not legal advice.
- `get_ad_platform_policies`: What Google Ads, Local Services Ads, Microsoft, Meta, LinkedIn, YouTube and ChatGPT ads allow for law-firm ads: eligibility, verification, targeting, creative. Results are not legal advice.
- `get_attorney_fee_caps`: The fee-cap rules (percent and dollar limits on attorney fees) for one state or federal program: workers' comp, med-mal, contingency, SSDI, FTCA, VA. Results are not legal advice.
- `get_benchmark`: Law-firm marketing benchmarks (ad costs, call outcomes, speed to sign), as bands, tiers and rounded values with the methods page to cite.
- `get_ca_court_filings`: California only: cases filed in one county's superior court (or CA for the whole state) in fiscal year 2024-25, by case type, with the prior year. Results are not legal advice.
- `get_rule`: One state's lawyer advertising rule on one topic, e.g. can a firm text leads, record intake calls, pay referral fees, what disclaimer every ad must include. Results are not legal advice.
- `get_spanish_demand_supply`: Spanish speakers with limited English per Spanish-speaking lawyer in one US state, DC, the US or a metro area (Census ACS). Results are not legal advice.
- `get_state_market_brief`: Every public number about marketing a law firm in one state or DC, joined from nine open datasets. Each figure carries its source and check date. Not a forecast. Results are not legal advice.
- `get_state_rules`: Every lawyer advertising rule for one US state or DC in one call: filing, disclaimers, waiting periods, claims, referrals, language, recording, texting, privacy. Results are not legal advice.
- `language_compare`: The same measures side by side for up to 10 areas (US, state codes or metro CBSA codes). Dataset: Spanish-speaking demand vs Spanish-speaking lawyer supply, by state and metro. Not legal advice.
- `language_lookup`: For one area (US, a two-letter state code, or a metro's 5-digit CBSA code such as 19100 for Dallas-Fort Worth): Spanish speakers, those with limited English, lawyers, Spanish-speaking lawyers and the ratios, each with its margin of error and reliability. Dataset: Spanish-speaking demand vs Spanish-speaking lawyer supply, by state and metro. Not legal advice.
- `language_search`: Records whose text matches the words given, such as a metro or state name ("Houston", "New Jersey") plus a measure ("limited English per Spanish-speaking lawyer"). Dataset: Spanish-speaking demand vs Spanish-speaking lawyer supply, by state and metro. Not legal advice.
- `list_datasets`: Every public dataset on this server: what it covers, its version, DOI, license (CC BY 4.0), credit line, last-checked date, the page to cite, its files and its tools.
- `list_mdl_dockets`: Federal multidistrict litigation (MDL) dockets from the Judicial Panel on Multidistrict Litigation's monthly pending-dockets reports, largest first. Results are not legal advice.
- `list_rule_changes`: Recent confirmed changes to state lawyer advertising rules only, newest first, with the date, state, rules touched and primary source of each.
- `mdl_compare`: Up to 10 MDL dockets (for example MDL-2738, MDL-3140) side by side: pending and total actions, the 12-month change and the monthly history. Dataset: Mass-tort docket tracker, federal MDL pending actions by month since 2019. Not legal advice.
- `mdl_lookup`: For one MDL docket (for example MDL-2738): the court's title, district, actions now pending and ever filed in the latest JPML report, the 12-month change, and the monthly pending count since 2019. Dataset: Mass-tort docket tracker, federal MDL pending actions by month since 2019. Not legal advice.
- `mdl_search`: Federal MDL dockets in the latest JPML report whose title matches the words given (a product, drug, device or company name), with pending actions. Dataset: Mass-tort docket tracker, federal MDL pending actions by month since 2019. Not legal advice.
- `opinions_compare`: The indexed marketing ethics opinions of up to 10 jurisdictions side by side. Dataset: Legal-marketing ethics opinions, 2015–2026. Not legal advice.
- `opinions_lookup`: The marketing ethics opinions indexed for one state, DC or the ABA: issuing body, number, date, topics, a one-sentence holding, whether it is still in force, the official link and a short quote. Dataset: Legal-marketing ethics opinions, 2015–2026. Not legal advice.
- `opinions_search`: Marketing ethics opinions whose holding or title matches the words given, such as "lead generator", "Google reviews", "trade name" or "chatbot". Dataset: Legal-marketing ethics opinions, 2015–2026. Not legal advice.
- `platforms_compare`: The tracked policies of up to 10 ad platforms side by side. Dataset: Legal ad-platform policy tracker. Not legal advice.
- `platforms_lookup`: Every tracked policy for one ad platform (google-ads, google-lsa, youtube, microsoft-ads, meta, linkedin-ads or chatgpt-ads): the rule in plain English, what to do, the practice areas it touches, its dates and the quoted policy page. Dataset: Legal ad-platform policy tracker. Not legal advice.
- `platforms_search`: Ad-platform policy records whose text matches the words given, such as "bail bonds", "debt services", "missed call" or "Spanish ads". Dataset: Legal ad-platform policy tracker. Not legal advice.
- `search`: Id search for deep-research clients: returns ids, titles and URLs to read with fetch; the named tools answer one question directly.
- `search_ethics_opinions`: Bar ethics opinions (ABA and state) on lawyer marketing, e.g. pay-per-lead, Google reviews, AI chatbots, referral fees, social media. Results are not legal advice.
- `search_rules`: Keyword search across all rule text, for a word or claim such as "expert" or "guaranteed results". Results are not legal advice.
- `whats_new`: What changed lately in any of the datasets (or only the `datasets` named), newest first, with the date and source of each. Optional `since` (YYYY-MM-DD).