# Probative legal-marketing data (remote · probativegrowth.com)

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

- Trust score: 75/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `probativegrowth.com`: 75/100 (this document), [markdown](https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth.md), [page](https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth)

## Channel facts

- Endpoint: `https://probativegrowth.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.5.1`

## 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**: 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**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 22273 tokens (~107/item across 208 items; 24 tools + 184 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 49% 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 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 26 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).
  - Supports UI / widget rendering.

## Install

### How do I install the Probative legal-marketing data MCP server?

Probative legal-marketing data is a hosted endpoint at https://probativegrowth.com/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-probativegrowth-legal-marketing-data 'https://probativegrowth.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.com-probativegrowth-legal-marketing-data]
url = "https://probativegrowth.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-probativegrowth-legal-marketing-data": {
      "type": "remote",
      "url": "https://probativegrowth.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-probativegrowth-legal-marketing-data --url 'https://probativegrowth.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-probativegrowth-legal-marketing-data:
    url: "https://probativegrowth.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-probativegrowth-legal-marketing-data": {
      "Transport": "http",
      "Url": "https://probativegrowth.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-probativegrowth-legal-marketing-data -t streamable-http -u 'https://probativegrowth.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-probativegrowth-legal-marketing-data": {
      "type": "http",
      "url": "https://probativegrowth.com/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 75, +1)

- [security] Tool “get_state_market_brief” rewrote its description, which is the text the model reads

### 2026-11-03 (score 74, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-02 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] New resource “proof-ledger”
- [functional] New resource “legal-hiring-demand-changes”
- [functional] New resource “legal-hiring-demand-index”

### 2026-11-01 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “get_benchmark” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 19296 → 22173
- [functional] New resource “search-demand-changes”
- [functional] New resource “population-change-index”
- [functional] New resource “population-change-changes”
- [functional] New resource “osha-enforcement-index”
- [functional] New resource “osha-enforcement-changes”
- [functional] New resource “noncitizen-population-index”
- [functional] New resource “noncitizen-population-changes”
- [functional] New resource “union-membership-index”
- [functional] New resource “legal-profession-figures-index”
- [functional] New resource “marriage-divorce-index”
- [functional] New resource “mortgage-delinquency-changes”
- [functional] New resource “mortgage-delinquency-index”
- [functional] New resource “union-membership-changes”
- [functional] New resource “serp-landscape-index”
- [functional] New resource “serp-landscape-changes”
- [functional] New resource “search-demand-index”
- [functional] New resource “marriage-divorce-changes”
- [functional] New resource “ad-costs-changes”
- [functional] New resource “ad-costs-index”
- [functional] New resource “certified-specialists-changes”
- [functional] New resource “certified-specialists-index”
- [functional] New resource “demand-per-law-office-changes”
- [functional] New resource “demand-per-law-office-index”
- [functional] New resource “flood-claims-changes”
- [functional] New resource “flood-claims-index”
- [functional] New resource “law-firm-websites-changes”
- [functional] New resource “law-firm-websites-index”
- [functional] New resource “legal-profession-figures-changes”
- [cosmetic] “get_benchmark” added an optional parameter “public_table”
- [cosmetic] “get_benchmark” added an optional parameter “v5_table”
- [cosmetic] “cite” reworded the description of “dataset”
- [cosmetic] “data_compare” reworded the description of “dataset”
- [cosmetic] “data_search” reworded the description of “datasets”
- [cosmetic] “whats_new” reworded the description of “datasets”

### 2026-10-31 (score 73, +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.

### 2026-10-30 (score 72, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 15860 → 19296
- [functional] New resource “tx-nonsubscribers-changes”
- [functional] New resource “wc-benefits-index”
- [functional] New resource “wc-benefits-changes”
- [functional] New resource “fair-housing-index”
- [functional] New resource “hospital-safety-changes”
- [functional] New resource “hospital-safety-index”
- [functional] New resource “irs-databook-changes”
- [functional] New resource “irs-databook-index”
- [functional] New resource “legal-aid-orgs-changes”
- [functional] New resource “legal-aid-orgs-index”
- [functional] New resource “mine-accidents-changes”
- [functional] New resource “mine-accidents-index”
- [functional] New resource “mortgage-lending-changes”
- [functional] New resource “mortgage-lending-index”
- [functional] New resource “practice-official-changes”
- [functional] New resource “practice-official-index”
- [functional] New resource “tx-nonsubscribers-index”
- [functional] New resource “aviation-accidents-changes”
- [functional] New resource “aviation-accidents-index”
- [functional] New resource “boating-accidents-changes”
- [functional] New resource “boating-accidents-index”
- [functional] New resource “charge-deadlines-changes”
- [functional] New resource “charge-deadlines-index”
- [functional] New resource “court-fees-changes”
- [functional] New resource “court-fees-index”
- [functional] New resource “eviction-laws-changes”
- [functional] New resource “eviction-laws-index”
- [functional] New resource “fair-housing-changes”
- [functional] New resource “attorneys-changes”
- [functional] New resource “attorneys-index”
- [functional] New resource “crime-data-changes”
- [functional] New resource “crime-data-index”
- [functional] New resource “product-recalls-changes”
- [functional] New resource “product-recalls-index”
- [functional] Server version: 1.5.0 → 1.5.1
- [functional] Server version: 1.4.0 → 1.5.0
- [cosmetic] “whats_new” added an optional parameter “practice”
- [cosmetic] “whats_new” added an optional parameter “state”
- [cosmetic] “cite” reworded the description of “dataset”
- [cosmetic] “data_compare” reworded the description of “dataset”
- [cosmetic] “data_search” reworded the description of “datasets”
- [cosmetic] “whats_new” reworded the description of “datasets”

### 2026-10-29 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 11492 → 15860
- [functional improvement] Tool coverage: 47% → 52%
- [functional] New resource “state-civil-rights-changes”
- [functional] New resource “business-applications-changes”
- [functional] New resource “business-applications-index”
- [functional] New resource “county-income-changes”
- [functional] New resource “county-income-index”
- [functional] New resource “device-events-changes”
- [functional] New resource “device-events-index”
- [functional] New resource “drug-events-changes”
- [functional] New resource “drug-events-index”
- [functional] New resource “evictions-changes”
- [functional] New resource “evictions-index”
- [functional] New resource “federal-filings-county-changes”
- [functional] New resource “federal-filings-county-index”
- [functional] New resource “firm-web-census-changes”
- [functional] New resource “firm-web-census-index”
- [functional] New resource “green-cards-changes”
- [functional] New resource “green-cards-index”
- [functional] New resource “ny-attorneys-changes”
- [functional] New resource “ny-attorneys-index”
- [functional] New resource “ny-workers-comp-changes”
- [functional] New resource “ny-workers-comp-index”
- [functional] New resource “rail-casualties-changes”
- [functional] New resource “rail-casualties-index”
- [functional] New resource “state-civil-rights-index”
- [functional] New resource “state-wage-claims-changes”
- [functional] New resource “state-wage-claims-index”
- [functional] New resource “toxic-releases-changes”
- [functional] New resource “toxic-releases-index”
- [functional] New resource “unemployment-changes”
- [functional] New resource “unemployment-index”
- [functional] New resource “uscis-offices-changes”
- [functional] New resource “uscis-offices-index”
- [functional] New resource “va-spending-changes”
- [functional] New resource “va-spending-index”
- [functional] New resource “warn-layoffs-changes”
- [functional] New resource “warn-layoffs-index”
- [cosmetic] “cite” reworded the description of “dataset”
- [cosmetic] “data_compare” reworded the description of “dataset”
- [cosmetic] “data_search” reworded the description of “datasets”
- [cosmetic] “whats_new” reworded the description of “datasets”

### 2026-10-28 (score 71, −1)

We did not load change detail this far back for this component, so this day may have recorded more than is shown.

- [security] Tool “cite” rewrote its description, which is the text the model reads
- [security] Tool “compare_states” rewrote its description, which is the text the model reads
- [security] Tool “get_state_rules” rewrote its description, which is the text the model reads
- [security] Tool “fetch” rewrote its description, which is the text the model reads
- [security] Tool “get_ad_filing_requirements” rewrote its description, which is the text the model reads
- [security] Tool “get_ad_platform_policies” rewrote its description, which is the text the model reads
- [security] Tool “get_attorney_fee_caps” rewrote its description, which is the text the model reads
- [security] Tool “get_benchmark” rewrote its description, which is the text the model reads
- [security] Tool “get_ca_court_filings” rewrote its description, which is the text the model reads
- [security] Tool “get_rule” rewrote its description, which is the text the model reads
- [security] Tool “get_spanish_demand_supply” rewrote its description, which is the text the model reads
- [security] Tool “calculate_fee_cap” rewrote its description, which is the text the model reads
- [security] Tool “check_ad_elements” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 79% → 47%
- [functional regression] Schema quality: 4092 → 11492
- [functional] First check of Capabilities: pass
- [functional] New tool “get_state_market_brief”
- [cosmetic] “data_search” added an optional parameter “response_format”
- [cosmetic] “check_ad_elements” added an optional parameter “response_format”
- [cosmetic] “cite” added an optional parameter “response_format”
- [cosmetic] “compare_states” added an optional parameter “response_format”
- [cosmetic] “data_compare” added an optional parameter “response_format”
- [cosmetic] “data_lookup” added an optional parameter “response_format”
- [cosmetic] “get_ad_filing_requirements” added an optional parameter “response_format”
- [cosmetic] “get_ad_platform_policies” added an optional parameter “response_format”
- [cosmetic] “get_attorney_fee_caps” added an optional parameter “response_format”
- [cosmetic] “get_benchmark” added an optional parameter “response_format”
- [cosmetic] “get_ca_court_filings” added an optional parameter “response_format”
- [cosmetic] “get_rule” added an optional parameter “response_format”
- [cosmetic] “get_spanish_demand_supply” added an optional parameter “response_format”
- [cosmetic] “calculate_fee_cap” added an optional parameter “response_format”
- [cosmetic] “cite” reworded the description of “dataset”
- [cosmetic] “compare_states” reworded the description of “topic”
- [cosmetic] “data_compare” reworded the description of “dataset”
- [cosmetic] “data_lookup” reworded the description of “dataset”
- [cosmetic] “get_ad_platform_policies” reworded the description of “area”
- [cosmetic] “get_ad_platform_policies” reworded the description of “cursor”
- [cosmetic] “get_ad_platform_policies” reworded the description of “platform”
- [cosmetic] “get_attorney_fee_caps” reworded the description of “jurisdiction”
- [cosmetic] “get_attorney_fee_caps” reworded the description of “program”
- [cosmetic] “get_benchmark” reworded the description of “query”
- [cosmetic] “get_benchmark” reworded the description of “table”
- [cosmetic] “get_ca_court_filings” reworded the description of “county”
- [cosmetic] “get_ca_court_filings” reworded the description of “group”
- [cosmetic] “get_rule” reworded the description of “topic”
- [cosmetic] “get_spanish_demand_supply” reworded the description of “area”
- [cosmetic] “calculate_fee_cap” reworded the description of “award_usd”
- [cosmetic] “calculate_fee_cap” reworded the description of “jurisdiction”
- [cosmetic] “calculate_fee_cap” reworded the description of “program”
- [cosmetic] “calculate_fee_cap” reworded the description of “stage”
- [cosmetic] “check_ad_elements” reworded the description of “ad_text”
- [cosmetic] “get_benchmark” dropped the optional parameter “detail”
- [cosmetic] “check_ad_elements” dropped the optional parameter “detail”
- [cosmetic] “cite” dropped the optional parameter “detail”
- [cosmetic] “compare_states” dropped the optional parameter “detail”
- [cosmetic] “data_compare” dropped the optional parameter “detail”
- [cosmetic] “data_lookup” dropped the optional parameter “detail”
- [cosmetic] “get_ad_filing_requirements” dropped the optional parameter “detail”
- [cosmetic] “get_ad_platform_policies” dropped the optional parameter “detail”
- [cosmetic] “get_attorney_fee_caps” dropped the optional parameter “detail”
- [cosmetic] “get_state_rules” dropped the optional parameter “detail”
- [cosmetic] “data_search” dropped the optional parameter “detail”
- [cosmetic] “get_ca_court_filings” dropped the optional parameter “detail”
- [cosmetic] “get_rule” dropped the optional parameter “detail”
- [cosmetic] “get_spanish_demand_supply” dropped the optional parameter “detail”
- [cosmetic] “calculate_fee_cap” dropped the optional parameter “detail”

## MCP tools (24)

### `list_datasets` (~61 tokens)

List the 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.

Input parameters:

- `response_format` (string)

### `cite` (~134 tokens)

How to 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.

Input parameters:

- `dataset` (string): A dataset id, e.g. rules, ad-costs, attorneys, aviation-accidents, bankruptcy. list_datasets lists every id.
- `id` (string): Other datasets: the record id
- `response_format` (string)
- `state` (string): rules only: two-letter code, or DC
- `topic` (string): rules only: topic key, e.g. filing

### `data_lookup` (~91 tokens)

Look up one key in a dataset

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.

Input parameters:

- `dataset` (string, required)
- `key` (string, required): The key, e.g. TX, google-ads, 19100, MDL-2738
- `response_format` (string)

### `get_benchmark` (~96 tokens)

Law-firm marketing benchmarks

Anonymized law-firm marketing benchmarks (ad costs, call outcomes, speed to sign), as bands, tiers and rounded values with the methods page to cite.

Input parameters:

- `public_table` (string)
- `query` (string): Optional words to keep only matching rows, e.g. "hour" or…
- `response_format` (string)
- `table` (string)
- `v5_table` (string)

### `data_search` (~104 tokens)

Search the datasets

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.

Input parameters:

- `datasets` (array): Dataset ids, e.g. ad-costs, attorneys, aviation-accidents, bankruptcy, bar-pipeline. list_datasets lists every id.
- `limit` (integer)
- `query` (string, required)
- `response_format` (string)

### `get_state_rules` (~80 tokens)

Lawyer advertising rules for one state

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.

Input parameters:

- `response_format` (string)
- `state` (string, required): Two-letter code (TX), or DC. Full names (Texas) also work.

### `whats_new` (~115 tokens)

What changed

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).

Input parameters:

- `datasets` (array): Dataset ids, e.g. rules, ad-costs, attorneys, aviation-accidents, bankruptcy. list_datasets lists every id.
- `limit` (integer)
- `practice` (string)
- `response_format` (string)
- `since` (string)
- `state` (string)

### `list_mdl_dockets` (~138 tokens)

Federal MDL dockets by actions pending

Federal multidistrict litigation (MDL) dockets from the Judicial Panel on Multidistrict Litigation's monthly pending-dockets reports, largest first. Results are not legal advice.

Input parameters:

- `cursor` (string): The nextCursor from the previous page; leave out for the first…
- `docket` (string): One docket, e.g. MDL-2738 or 2738; returns its monthly history
- `limit` (integer): Records per page (1 to 25)
- `query` (string): Words in the docket title or court, e.g. "hernia mesh"
- `response_format` (string)

### `get_rule` (~85 tokens)

One lawyer advertising rule in one state

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.

Input parameters:

- `response_format` (string)
- `state` (string, required): Two-letter code (TX), or DC. Full names (Texas) also work.
- `topic` (string, required)

### `search` (~55 tokens)

Search the legal-marketing records

Id search for deep-research clients: returns ids, titles and URLs to read with fetch; the named tools answer one question directly.

Input parameters:

- `query` (string, required): For example "Texas ad filing" or "pay per lead ethics opinion"

### `get_spanish_demand_supply` (~80 tokens)

Spanish-language legal demand and lawyer supply in one area

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.

Input parameters:

- `area` (string, required): A state code (TX), DC, US, a metro code (26420), or a metro…
- `response_format` (string)

### `check_ad_elements` (~118 tokens)

Which state ad rules an ad touches

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.

Input parameters:

- `ad_text` (string): Optional ad copy, script or landing-page text, scanned for…
- `elements` (array): What the ad contains. Leave out to rely on ad_text only.
- `response_format` (string)
- `state` (string, required): Two-letter code (TX) or DC; full names also work

### `get_ad_filing_requirements` (~68 tokens)

Bar ad filing requirements and fees for one state

Whether a state's bar requires lawyers to file or submit ads for review, which ads, when. Results are not legal advice.

Input parameters:

- `response_format` (string)
- `state` (string, required): Two-letter code (TX) or DC; full names (Texas) also work

### `search_ethics_opinions` (~179 tokens)

Bar ethics opinions on lawyer marketing

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.

Input parameters:

- `cursor` (string): The nextCursor from the previous page; leave out for the first…
- `in_force_only` (boolean): Leave out opinions marked withdrawn or superseded
- `limit` (integer): Records per page (1 to 25)
- `query` (string): Words to match, e.g. "Google reviews" or "pay per lead"
- `response_format` (string)
- `state` (string): Two-letter code, DC, or ABA for the American Bar Association
- `topic` (string): One of 27 values, e.g. advertising-general, fee-sharing, trade-names

### `calculate_fee_cap` (~118 tokens)

Calculate the legal limit on an attorney fee

The most a lawyer may charge, in dollars, on one award, settlement or past-due benefit under a legal fee cap.

Input parameters:

- `award_usd` (number, required): The award, settlement or past-due benefits in US dollars (the…
- `jurisdiction` (string, required): Two-letter state code, DC, or US for federal programs (Social…
- `program` (string, required)
- `response_format` (string)
- `stage` (string): Optional: the stage, e.g. "administrative" or "litigation"…

### `compare_states` (~83 tokens)

Compare one rule across 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.

Input parameters:

- `response_format` (string)
- `states` (array): Two-letter codes. Leave out for every jurisdiction.
- `topic` (string, required)

### `list_rule_changes` (~58 tokens)

Confirmed changes to the rules

Recent confirmed changes to state lawyer advertising rules only, newest first, with the date, state, rules touched and primary source of each.

Input parameters:

- `response_format` (string)
- `since` (string): Only changes on or after this day

### `get_ad_platform_policies` (~132 tokens)

Ad-platform policies for law-firm ads

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.

Input parameters:

- `area` (string)
- `cursor` (string): The nextCursor from the previous page; leave out for the first…
- `limit` (integer): Records per page (1 to 25)
- `platform` (string)
- `query` (string): Words to match, e.g. "bail bonds" or "verification"
- `response_format` (string)

### `get_attorney_fee_caps` (~90 tokens)

Legal limits on attorney fees in one jurisdiction

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.

Input parameters:

- `jurisdiction` (string, required): Two-letter state code, DC, or US for federal programs; full…
- `program` (string)
- `response_format` (string)

### `search_rules` (~70 tokens)

Search the lawyer advertising rules

Keyword search across all rule text, for a word or claim such as "expert" or "guaranteed results". Results are not legal advice.

Input parameters:

- `limit` (integer)
- `query` (string, required): For example "Florida filing fee" or "expert"
- `response_format` (string)

### `get_ca_court_filings` (~92 tokens)

California court filings in one county

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.

Input parameters:

- `county` (string, required): County name ("Los Angeles", "san-diego") or CA for the…
- `group` (string)
- `response_format` (string)

### `data_compare` (~97 tokens)

Compare keys in a dataset

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.

Input parameters:

- `dataset` (string, required): A dataset id, e.g. ad-costs, attorneys, aviation-accidents, bankruptcy, bar-pipeline. list_datasets lists every id.
- `keys` (array, required)
- `response_format` (string)

### `fetch` (~57 tokens)

Fetch one legal-marketing record

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.

Input parameters:

- `id` (string, required): An id from search

### `get_state_market_brief` (~81 tokens)

Law-firm market brief for one state

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.

Input parameters:

- `response_format` (string)
- `state` (string, required): Two-letter code (TX) or DC; full names (Texas) also work

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth#diagnostics

## Score history

- 2026-11-05: 75
- 2026-11-04: 74
- 2026-11-03: 74
- 2026-11-02: 73
- 2026-11-01: 73
- 2026-10-31: 73
- 2026-10-30: 72
- 2026-10-29: 72
- 2026-10-28: 71
- 2026-10-27: 72
- 2026-10-26: 72

## Common questions

### What is the Probative legal-marketing data MCP server?

Probative legal-marketing data is an MCP server listed in the public MCP registry as com.probativegrowth/legal-marketing-data. Open US legal-marketing datasets with sources and DOIs, one server per dataset. CC BY 4.0. This page covers its hosted endpoint (https://probativegrowth.com/mcp).

### Is the Probative legal-marketing data MCP server safe to use?

Probative legal-marketing data scores 75 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 Probative legal-marketing data MCP server expose?

Probative legal-marketing data exposes 24 tools: list_datasets, cite, data_lookup, get_benchmark, data_search, and 19 more. Their descriptions and schemas cost roughly 2,282 tokens of context every time the server is loaded.

### Does the Probative legal-marketing data MCP server require authentication?

No. We connected to Probative legal-marketing data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Probative legal-marketing data MCP server still maintained?

Probative legal-marketing data 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 Probative legal-marketing data MCP server?

VerifyMCP ran 14 checks on Probative legal-marketing data, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 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://probativegrowth.com/mcp
- Repository: https://github.com/ops864/legal-marketing-data
- Website: https://probativegrowth.com/data/
- Changelog RSS feed: https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth.json
- HTML version of this page: https://verifymcp.io/servers/com-probativegrowth-legal-marketing-data/probativegrowth