Drive the ServiceGraph API ( https://api.servicegraph.co) to find,
shortlist, and enrich US cybersecurity firms via the pro_services
dataset.
Always pin service_provided:cybersecurity — that's the only
relevant structured tag in the live catalog. Older docs and the
catalog source mention sub-tags like pen-testing and
security-audit, but in the current release none of those exist as
separate tags — cybersecurity is the broad catch-all and every
sub-type (pen-testing, red-team, vCISO, SOC 2 readiness, IR retainer,
IAM, cloud security, AppSec) is a keyword substring search on firm
text. Confirm via /v1/datasets/pro_services/fields?include_values=1
once per session.
The industry tag also drifts between releases — newer catalogs may
use industry:cybersecurity, older ones used industry:security.
Confirm the value via /fields and pin both industry and
service_provided:cybersecurity for safety.
Any HTTP client works (curl, fetch, requests). Examples below use curl.
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.
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 industry value name and cybersecurity is in service_provided.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.
vk_* API keys minted in the dashboard. Keep the token out of the
LLM context — never read .env* into your context; dispatch via
shell.
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' )
On 401 prompt the user:
"Open https://servicegraph.co/profile/api-keys, create a key, and add
SERVICEGRAPH_API_KEY=vk_…to.env.localhere (or export it). Tell me when done. Please don't paste the key into chat."
Retry after the user signals ready.
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).
Cybersecurity examples (validate yours with /check; replace
cybersecurity with whatever /fields returns as the industry value):
text
industry:cybersecurity service_provided:cybersecurity
service_provided:cybersecurity pen-testing
service_provided:cybersecurity "security audit" "soc 2"
service_provided:cybersecurity vciso
service_provided:cybersecurity "incident response" retainer
service_provided:cybersecurity cloud aws
service_provided:cybersecurity "application security" sast
service_provided:cybersecurity rating>=4 has:clutch
service_provided:cybersecurity hipaa
The live catalog has no separate pen-testing / security-audit /
appsec tags — pin service_provided:cybersecurity and treat all
sub-types as keywords.
Sub-type → keyword mapping (all sub-types are keyword-only):
User asks forUsePen test / red teampen-testing, "red team"Security audit / assessmentaudit, assessmentvCISO / fractional CISOvciso, "fractional ciso"SOC 2 readiness"soc 2", readinessIncident response / forensics"incident response", forensics, "ir retainer"Cloud security"cloud security", aws, gcp, azureIdentity / IAMiam, identityApplication security / SAST/DAST"application security", appsec, sast, dastCompliance frameworkspci, hipaa, "iso 27001", nist
apex#Firms are identified by their apex domain ( mandiant.com, not
www.mandiant.com/about).
User: "Pen-testing firm for our SOC 2 audit."
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+pen-testing+"soc 2"&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"] }
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+vciso+(healthcare OR hipaa)&limit=10
User: "Incident response retainer in case we get breached."
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+"incident response"+retainer&limit=10
If thin, drop retainer — most IR firms offer retainer engagements as standard.
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+cloud+aws+hipaa&limit=10
User: "We got hit with ransomware last week — we need help fast."
That's emergency IR:
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+"incident response"+ransomware&limit=10
Skip validation; present briefs immediately given urgency.
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+"application security"+(sast OR "code review")&limit=10
text
GET /v1/datasets/pro_services/search?filter=service_provided:cybersecurity+"soc 2"+(readiness OR preparation)&limit=10
User pastes 8–20 cybersecurity firm domains:
GET /v1/datasets/pro_services/:apex per domain — free brief
(404 = not in catalog, no charge).POST /unlocks = 10×N credits,
atomic, detail returned.pen-testing / vciso / appsec keywords leak into IT-services rows that mention security./fields — older catalogs used industry:security, newer ones may use industry:cybersecurity. Don't hardcode."incident response" → one phrase).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.was_cached:true).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 — URL is authoritative.400field_not_in_datasetDrop the disallowed field.400invalid_apexRe-normalize.401unauthorized / invalid_audienceRe-prompt for fresh vk_….402insufficient_credits``needed and balance in payload; nothing charged.404not_found / not_in_datasetSkip; not charged.429rate_limitedHonor Retry-After.
User: "Three pen-testing firms for our SOC 2 audit, 4-star ratings, ideally with HIPAA experience for a healthcare-tech context."
text
GET /v1/datasets/pro_services/fields?include_values=1
GET /v1/datasets/pro_services/check?filter=service_provided:cybersecurity+pen-testing+"soc 2"+hipaa+rating>=4
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