Google Search Console integration for Model Context Protocol (MCP)
Nothing to run from here
Probative legal-marketing data is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
23
tools declared
remote
at its publisher
—
calls last 7d
What it does
Open US legal-marketing datasets with sources and DOIs, one server per dataset. CC BY 4.0.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http probative-legal-marketing-data-mcp https://probativegrowth.com/mcp
# 2 — ask your agent for something these tools do
# list_datasets, cite, whats_new and 20 more
Probative legal-marketing data costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PRAll 2 servers
probativegrowth2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http probative-legal-marketing-data-mcp https://probativegrowth.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
23 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
The citation sentence, credit line, DOI and URL to cite: for a whole dataset, for one state, or for one rule cell (dataset "rules" with state and topic), or for one record id in another dataset. CC BY 4.0 asks for credit and a link.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset | string | no | Dataset id (list_datasets shows them) |
| state | string | no | rules only: two-letter code, or DC |
| topic | string | no | rules only: topic key, e.g. filing |
| id | string | no | Other datasets: the record id |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Confirmed changes across the datasets, newest first, each with its date, what changed and its source. Optional since (YYYY-MM-DD) and datasets filter.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | — |
| datasets | array | no | — |
| limit | integer | no | — |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Every lawyer advertising rule we track for one US state or DC (ad filing, required content, waiting periods, claims and testimonials, referral and lead rules, other languages, call recording, texting law, privacy law), each with its plain-English text, status (P primary source, S secondary, D ABA model default, U open question), sources with the days they were read, and the state page URL to cite.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | string | yes | Two-letter code (TX), or DC. Full names (Texas) also work. |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
One state's rule on one topic: the plain-English text, status (P/S/D/U), note, sources with dates, the cell URL and a one-sentence citation. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | string | yes | Two-letter code (TX), or DC. Full names (Texas) also work. |
| topic | string | yes | filing: Ad filing or review; requiredContent: What each ad must include; waitingPeriod: Waiting period for targeted injury contact; claims: Results, testimonials and “specialist” claims; referral: Ref |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
One rule topic side by side across several states (or all 50 states and DC when states is left out), each with its status, sources and cell URL. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | yes | filing: Ad filing or review; requiredContent: What each ad must include; waitingPeriod: Waiting period for targeted injury contact; claims: Results, testimonials and “specialist” claims; referral: Ref |
| states | array | no | Two-letter codes. Leave out for every jurisdiction. |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Keyword search over every rule cell. States (names, or capitalized codes like TX) and topics (filing, disclaimer, waiting period, testimonials, referral, Spanish, recording, texting, privacy) named in the query narrow the results. Deterministic keyword matching, no AI. Returns the best-matching cells with sources. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | For example "Florida filing fee" or "testimonials in New York" |
| limit | integer | no | — |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Confirmed changes to the lawyer advertising rules dataset, newest first, each with its date, state, the cells it touched and its primary source. Optional since (YYYY-MM-DD).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | Only changes on or after this day |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
For one US state or DC and the elements an ad contains (testimonials, results, specialist or expert claims, "no fee unless you win", dramatizations, Spanish or another language, a paid spokesperson, an AI-generated person or voice, comparative claims, a referral or lead service), returns each element's rule text from that state, its status (P/S/D/U), date checked, source and the page section to ci
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | string | yes | Two-letter code (TX) or DC; full names also work |
| elements | array | no | What the ad contains. Leave out to rely on ad_text only. |
| ad_text | string | no | Optional ad copy, script or landing-page text, scanned for elements. Never stored. |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Whether a state's bar requires lawyers to file or submit ads for review, which ads, when (before or after first use), the standard, expedited and late fees in US dollars, the portal or method, how long to keep copies, and the rule cited. One record per state or DC, read from the state's rules of professional conduct and bar pages, each with its sources and the day they were read. Results summarize
| Parameter | Type | Required | Notes |
|---|---|---|---|
| state | string | yes | Two-letter code (TX) or DC; full names (Texas) also work |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Statutory and agency limits on what a lawyer may charge: workers' compensation in every state and DC; Social Security (SSDI and SSI), the Federal Tort Claims Act, VA, Longshore and other federal programs (jurisdiction US); medical-malpractice and general contingency-fee rules where read. Each record gives the cap type, percent, dollar cap or sliding scale, what it applies to, who approves the fee,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | Two-letter state code, DC, or US for federal programs; full state names also work |
| program | string | no | Optional: only this program |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Federal multidistrict litigation (MDL) dockets from the Judicial Panel on Multidistrict Litigation's monthly pending-dockets reports, largest first: the docket number, title, court district, actions pending on the report date, total actions, and the change over the past year. Filter by words in the title (for example "hair relaxer" or "talcum") or ask for one docket (MDL-2738) to get its monthly h
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Words in the docket title or court, e.g. "hernia mesh" |
| docket | string | no | One docket, e.g. MDL-2738 or 2738; returns its monthly history |
| limit | integer | no | Records per page (1 to 25) |
| cursor | string | no | The nextCursor from the previous page; leave out for the first page |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Ethics opinions from the ABA and state bars on lawyer marketing: lead generators and pay-per-lead, fee sharing, online reviews, lawyer platforms, trade names, solicitation, social media, testimonials, AI tools and more. Each record gives the issuing body, opinion number, date issued, whether it is still in force, its holding in plain words, the rules it applies, what to do, and a link to the opini
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Words to match, e.g. "Google reviews" or "pay per lead" |
| state | string | no | Two-letter code, DC, or ABA for the American Bar Association |
| topic | string | no | — |
| in_force_only | boolean | no | Leave out opinions marked withdrawn or superseded |
| limit | integer | no | Records per page (1 to 25) |
| cursor | string | no | The nextCursor from the previous page; leave out for the first page |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
The published advertising policies that apply to law-firm ads on Google Ads, Google Local Services Ads, Microsoft Advertising, Meta (Facebook and Instagram), LinkedIn, YouTube and ChatGPT ads: who may advertise, restricted categories (bail bonds, debt relief, legal services verification), creative, targeting, measurement and billing rules, each quoted from the platform's own policy page with the d
| Parameter | Type | Required | Notes |
|---|---|---|---|
| platform | string | no | Optional: one platform key |
| area | string | no | Optional: one policy area |
| query | string | no | Words to match, e.g. "bail bonds" or "verification" |
| limit | integer | no | Records per page (1 to 25) |
| cursor | string | no | The nextCursor from the previous page; leave out for the first page |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
For one US state, DC, the US, or a metro area: people aged 5 and over, Spanish speakers, Spanish speakers who speak English less than very well, employed lawyers, Spanish-speaking lawyers, and how many Spanish speakers with limited English there are per Spanish-speaking lawyer. U.S. Census Bureau American Community Survey 5-year estimates, each with its margin of error, table and reliability flag.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| area | string | yes | A state code (TX), DC, US, a metro code (26420), or a metro name ("Houston") |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Cases filed in one California county's superior court (or CA for the whole state) in fiscal year 2024-25, by case type: civil (including motor-vehicle injury and other injury and wrongful death), criminal, family, juvenile, probate, mental health and appeals, each with the prior year and the Judicial Council of California Court Statistics Report table it came from. Counts are cases, not people or
| Parameter | Type | Required | Notes |
|---|---|---|---|
| county | string | yes | County name ("Los Angeles", "san-diego") or CA for the statewide row |
| group | string | no | Optional: one group of case types |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
The most a lawyer may charge on one award under a statutory or agency fee limit: Social Security (the lesser of 25% and the current dollar cap), the Federal Tort Claims Act (20% administrative, 25% after suit), VA, workers' compensation sliding scales and medical-malpractice or contingency scales where the dataset has them. Returns the dollar limit, the formula, who approves the fee, the statute o
| Parameter | Type | Required | Notes |
|---|---|---|---|
| jurisdiction | string | yes | Two-letter state code, DC, or US for federal programs (Social Security, FTCA, VA) |
| program | string | yes | workers-comp, med-mal, contingency-general, ssdi-ssi, ftca, va, longshore or other |
| award_usd | number | yes | The award, settlement or past-due benefits in US dollars (the base the rule names) |
| stage | string | no | Optional: the stage, e.g. "administrative" or "litigation" (FTCA), "agency" or "court" (Social Security), "before answer" (Florida) |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Published benchmark tables on law-firm intake and marketing, as bands, tiers and rounded values with the methods page to cite: speed-to-sign (how quickly inquiries become signed clients); calls-and-hours (phone calls and signed-client likelihood); organic-ai (ai answers and organic search clicks); search-click-costs (what law-firm search-ad clicks cost); search-query-patterns (what people type whe
| Parameter | Type | Required | Notes |
|---|---|---|---|
| table | string | no | The table id (the benchmarks dataset key). Leave out to list the tables. |
| query | string | no | Optional words to keep only matching rows, e.g. "hour" or "Local Services" |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
The records for one key in one dataset, with sources, status and dates. Datasets and their keys: bar-pipeline (jurisdiction, e.g. AK, AL, AR, AZ); benchmarks (table, e.g. AD-CALL-OUTCOMES, CALLS-AND-HOURS, COST-PER-SIGNED-CLIENT, LSA-LEAD-MIX); ca-courts (area, e.g. ALAMEDA, ALPINE, AMADOR, BUTTE); civil-filings (district, e.g. AK, ALM, ALN, ALS); deserts (area, e.g. 01, 01001, 01003, 01005); fees
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset | string | yes | Dataset id (list_datasets describes each one) |
| key | string | yes | The key, e.g. TX, google-ads, 19100, MDL-2738 |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
The records for up to 10 keys of one dataset side by side. Datasets and their keys: bar-pipeline (jurisdiction, e.g. AK, AL, AR, AZ); benchmarks (table, e.g. AD-CALL-OUTCOMES, CALLS-AND-HOURS, COST-PER-SIGNED-CLIENT, LSA-LEAD-MIX); ca-courts (area, e.g. ALAMEDA, ALPINE, AMADOR, BUTTE); civil-filings (district, e.g. AK, ALM, ALN, ALS); deserts (area, e.g. 01, 01001, 01003, 01005); fees (jurisdictio
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dataset | string | yes | Dataset id (list_datasets describes each one) |
| keys | array | yes | — |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Keyword search (deterministic, no model) across bar-pipeline, benchmarks, ca-courts, civil-filings, deserts, fees, filing, language, law-offices, limitations, mdl, opinions, platforms, referral, or only the datasets named. Returns the best-matching records with their dataset, sources and status. For lawyer advertising rules use search_rules. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| datasets | array | no | — |
| limit | integer | no | — |
| detail | string | no | summary (default): each record as its id, a 1-2 sentence text, status, date checked, one source URL and the page to cite. full: every field, every source and the per-record provenance. |
Finds records about US lawyer advertising rules by state, bar ad filing, ethics opinions on lawyer marketing, ad-platform policies for law firms, attorney fee caps, federal MDL dockets, Spanish-language legal demand, California court filings and law-firm marketing benchmarks. Returns up to 10 results, each an id, title and URL; pass an id to fetch for the full text with its source. Deterministic k
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | For example "Texas ad filing" or "pay per lead ethics opinion" |
The full text of one record found with search (ids like rules:TX:filing, opinions:ny-nysba-1306 or benchmarks:speed-to-sign): the rule, opinion, policy, limit or table in plain English, with its status, the day its source was checked, the source URL, the DOI and the page to cite. Not legal advice.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | An id from search |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Probative legal-marketing data or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.5.1 · scanned 31 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digestff7ce34c13bc2d8806ceb141d13fab5caf5d313461a765bfbfd680923ae147de
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_datasets | no tags | |
| cite | no tags | |
| whats_new | no tags | |
| get_state_rules | no tags | |
| get_rule | no tags | |
| compare_states | no tags | |
| search_rules | no tags | |
| list_rule_changes | no tags | |
| check_ad_elements | no tags | |
| get_ad_filing_requirements | no tags | |
| get_attorney_fee_caps | no tags | |
| list_mdl_dockets | no tags | |
| search_ethics_opinions | no tags | |
| get_ad_platform_policies | no tags | |
| get_spanish_demand_supply | no tags | |
| get_ca_court_filings | no tags | |
| calculate_fee_cap | no tags | |
| get_benchmark | no tags | |
| data_lookup | no tags | |
| data_compare | no tags | |
| data_search | no tags | |
| search | untrusted-input | untrusted-input: keyword "fetch" |
| fetch | untrusted-input | untrusted-input: keyword "fetch" |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestff7ce34c13bc2d88
Scanned2026-10-31
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.5.1.
1.5.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Probative legal-marketing data can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.