find-law-firm#

Drive the ServiceGraph API ( https://api.servicegraph.co) to find, shortlist, and enrich US business-to-business law firms via the pro_services dataset.

The catalog is B2B-only. A historical audit dropped over half of high-rank "legal" firms because they served personal/consumer matters (divorce, personal injury, criminal defense, family law, estate planning). The remaining catalog skews toward corporate, IP, M&A, securities, employment, commercial litigation, regulatory, data privacy, real-estate transactions, and corporate tax.

Always pin industry:legal. Sub-areas of law are NOT separate tags — industry:legal is the most specific structured level — so practice-area specialization (IP, M&A, employment, securities, etc.) is a keyword substring search on firm text.

Any HTTP client works (curl, fetch, requests). Examples below use curl.

When NOT to use this skill#

The single biggest failure mode is firing on consumer-personal legal asks. Refuse those — don't fall back to a partial filter.

• Personal/family matters where the user is the end client: divorce, child custody, family law, estate planning, wills/trusts, personal injury, criminal defense, individual bankruptcy, immigration for the user themselves, landlord/tenant disputes.
• DIY legal research: "is this enforceable?", "do I owe…?", "what does this clause mean?".
• In-house counsel hires (GC, paralegal, contracts manager).
• Non-US firms / individual freelancers / contract attorneys.

MCP server (preferred for authed calls)#

If your harness has the ServiceGraph MCP server loaded (tools containing servicegraph), prefer those — OAuth 2.1 + PKCE keeps the token in the harness sandbox. Otherwise use the REST flow below.

API surface (dataset id: pro_services)#

Every endpoint requires the bearer ( Authorization: Bearer vk_…). No anonymous tier.

EndpointCostUse it forGET /v1/datasets/pro_services/fields[?include_values=1]freeConfirm legal is in the industry value list.GET /v1/datasets/pro_services/check?filter=…freeValidate filter.POST /v1/datasets/pro_services/translate-intentfree{intent} → DSL filter + sanity count.GET /v1/datasets/pro_services/search?filter=…&limit=freeBrief firm cards + per-row unlock hint + total.GET /v1/datasets/pro_services/:apexfreeOne row brief; detail only if unlocked.POST /v1/datasets/pro_services/unlocks10 credits / firm{apexes:[...]} ≤100; atomic; 30-day TTL on detail.GET /v1/me/creditsfreeBalance.

Cost model. Discovery / validation / search / brief reads are free. Detail (url, phone, email, social, address, full platforms map) costs 10 credits per firm and lasts 30 days.

Note: service_provided tags are not populated for industry:legal in the current catalog (Clutch and similar directories don't break legal down further). Use barewords for practice areas.

Auth#

vk_* API keys minted in the dashboard. Keep the token out of the LLM context — never read .env* into your context; dispatch via shell.

1. Try the call first through a shell wrapper that sources .env.local: bash

   ( set -a; [ -f .env.local ] && . ./.env.local; set +a;
     curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
          'https://api.servicegraph.co/v1/datasets/pro_services/fields' )
   
   

2. On 401 prompt the user:

   "Open https://servicegraph.co/profile/api-keys, create a key, and add SERVICEGRAPH_API_KEY=vk_… to .env.local here (or export it). Tell me when done. Please don't paste the key into chat."

3. Retry after the user signals ready.

Filter DSL#

GitHub-search-style.

text

filter   := orExpr
orExpr   := andExpr ("OR" andExpr)*
andExpr  := notExpr (("AND")? notExpr)*    # whitespace = implicit AND
notExpr  := ("NOT" | "-") notExpr | atom
atom     := "(" filter ")" | predicate
predicate:= IDENT op valueOrList | bareword
op       := ":" | "=" | ">=" | "<=" | ">" | "<"
valueOrList := value ("," value)*
value    := IDENT | NUMBER | tagAtEvidence
tagAtEvidence := IDENT "@" ("low"|"medium"|"high")
bareword := IDENT | NUMBER          # → keyword:<bareword>

Four rules that bite: AND binds tighter than OR (use parens); comma list = OR within one predicate; negation is -x or NOT x; bareword = keyword search (quote multi-word phrases).

Legal-flavored examples (validate yours with /check):

text

industry:legal state:CA patent
industry:legal state:NY,DE m&a
industry:legal employment
industry:legal securities ipo
industry:legal "data privacy" gdpr
industry:legal "commercial litigation" state:TX
industry:legal -company_size_signal:solo rating>=4 review_count_total>=20
industry:legal corporate startup

Practice area → keyword mapping (sub-areas are not structured tags):

User asks forAdd as keyword(s)IP / patents / trademarkspatent, trademark, ipM&A / mergers and acquisitionsm&aSecurities / IPO / capital marketssecurities, ipoEmployment law (employer-side)employment, laborCommercial litigation / disputeslitigation, commercialRegulatory / complianceregulatory, complianceData privacy / cyber / GDPR / CCPAprivacy, gdpr, ccpa, cyberReal estate (commercial)"real estate", "commercial real estate"Tax (corporate)taxCorporate / formation / governancecorporate, formation, governanceAntitrustantitrustBankruptcy (corporate)bankruptcyImmigration (corporate sponsorship)immigration

Identifying firms — apex#

Firms are identified by their apex domain ( dlapiper.com, not www.dlapiper.com/about).

Recipes#

A. IP / patent firm in a state#

User: "Three boutique IP law firms in California for hardware-startup patent prosecution."

text

GET /v1/datasets/pro_services/search?filter=industry:legal+state:CA+patent+-company_size_signal:large_50plus&limit=10
# Present, get pick of 3. "Unlocking 3 = 30 credits, 30-day TTL."
POST /v1/datasets/pro_services/unlocks
  { "apexes": ["firm-a.com", "firm-b.com", "firm-c.com"] }

B. M&A counsel for a fundraise#

text

GET /v1/datasets/pro_services/search?filter=industry:legal+state:NY+m&a&limit=10

C. Securities / IPO experience#

text

GET /v1/datasets/pro_services/search?filter=industry:legal+securities+ipo&limit=10

D. Indirect intent — "outside counsel for GDPR/SOC2"#

User: "Our compliance is getting complex — we need outside counsel for GDPR, CCPA, and SOC2 oversight."

text

GET /v1/datasets/pro_services/search?filter=industry:legal+(gdpr OR ccpa OR privacy)+compliance&limit=10

Or use the intent translator:

text

POST /v1/datasets/pro_services/translate-intent
  { "intent": "outside counsel for GDPR/CCPA compliance and SOC2 oversight" }

E. Employment law for a tech employer#

text

GET /v1/datasets/pro_services/search?filter=industry:legal+employment+tech+company_size_signal:medium_10_50,small_2_10&limit=10

F. Quality threshold + commercial litigation#

text

GET /v1/datasets/pro_services/search?filter=industry:legal+commercial+litigation+state:TX+rating>=4&limit=10

G. BYO apex list — enrich domains#

User pastes 8–20 law-firm domains:

1. GET /v1/datasets/pro_services/:apex per domain — free brief (404 = not in catalog, no charge). A 404 often means the firm is consumer-focused (divorce, PI) and was filtered out of the B2B catalog.
2. User picks N to fully enrich. POST /unlocks = 10×N credits, atomic, detail returned.
3. Re-runs within 30-day TTL are free.

Gotchas#

• Always pin industry:legal. Without it, "patent" or "m&a" as keywords leak into marketing/IT meta tags.
• Refuse consumer-personal legal asks. Divorce, personal injury, criminal defense, family law, estate planning, wills, individual immigration, personal bankruptcy — NOT in the catalog. Tell the user the catalog is B2B-only and suggest elsewhere (state bar referral, Avvo). Do NOT return a partial result hoping it's close enough.
• industry:legal is the only structured handle. Practice areas are keyword-only. Multi-word areas split into ANDed barewords unless quoted ( "commercial litigation" → one phrase).
• Catalog skews toward mid/large B2B firms. Solo practitioners and <5-attorney shops are under-represented. For "boutique", exclude company_size_signal:large_50plus rather than requiring solo.
• DIY/legal-research questions ("is this NDA enforceable?", "explain fair use") are NOT procurement.
• Software-product comparisons (Ironclad vs DocuSign) are NOT procurement.
• Briefs DO include apex, name, location, ratings. They DON'T include url, phone_primary, email_primary, legal_name, address_full, full platforms — those require an unlock.
• not_found / not_in_dataset 404 = not in pro_services. Skip; not charged.
• Unlock is atomic. N apexes either all charge (up to 10×N credits) or none on 402.
• Within-TTL re-views are free ( was_cached:true).

Errors#

JSON envelope: {"error": {"code": "...", "message": "..."}}.

StatusCodeWhat to do400filter_parse_error``position included; fix and re-validate with /check.400kind_in_filterStrip any kind: from filter.400field_not_in_datasetDrop the disallowed field.400invalid_apexRe-normalize.401unauthorized / invalid_audienceRe-prompt for fresh vk_….402insufficient_credits``needed and balance; nothing charged.404not_found / not_in_datasetSkip; not charged.429rate_limitedHonor Retry-After.

End-to-end example#

User: "Three boutique IP law firms in California that handle patent prosecution for hardware startups, ideally with at least a 4-star rating."

text

GET /v1/datasets/pro_services/fields?include_values=1
GET /v1/datasets/pro_services/check?filter=industry:legal+state:CA+patent+rating>=4+-company_size_signal:large_50plus
GET /v1/datasets/pro_services/search?filter=...&limit=10
# Present briefs. "Unlocking 3 = 30 credits, 30-day TTL."
POST /v1/datasets/pro_services/unlocks
  { "apexes": ["firm-a.com", "firm-b.com", "firm-c.com"] }
GET /v1/me/credits