{"report":"{\"v\":1,\"package\":\"@fairquery/agent-trust-mcp\",\"version\":\"1.1.10\",\"ranAt\":\"2026-11-16T11:37:13.083Z\",\"install\":{\"ok\":true,\"integrity\":\"sha512-eR9mo5/pNpfn3t/5rIJMDrYumSQr3j3Ab/ubsKQmakdPxFbAfDQIUAL8COKVz4uJe0Md15jrkHcyEyKyts5/qg==\",\"deps\":96,\"scripts\":[],\"bins\":[\"fairquery-agent-trust-mcp\"],\"license\":\"MIT\",\"engines\":\"node >=20\",\"bin\":\"fairquery-agent-trust-mcp\"},\"start\":{\"ok\":true,\"ms\":197,\"serverName\":\"fairquery-agent-trust\",\"serverVersion\":\"1.1.10\",\"protocol\":\"2025-06-18\"},\"tools\":[{\"name\":\"pii_list_detectors\",\"description\":\"WHAT: Catalog of every PII and secret entity type, which ones run locally for free (pii_scan_text / pii_redact_text) vs only in the paid Actor (NER names/locations, street addresses, URL/PDF documents), redaction styles, and the price of every paid tool in this server.\\nWHEN: Before pii_scan_text / pii_redact_text to pick entityTypes, or to explain coverage and costs to a user.\\nWHEN NOT: To actually scan text (pii_scan_text) or redact it (pii_redact_text).\\nCOST: Free; no token.\\nRETURNS: One catalog object; local:true marks the detectors the free tools run (see PARAMETERS).\\nBEHAVIOR: No network calls; local static catalog, instant (<10 ms). No rate limits.\\nPARAMETERS: None: call with an empty object {}; the catalog is always complete and cannot be filtered. Its output feeds other tools' parameters: copy detector \\\"type\\\" values verbatim into entityTypes of pii_scan_text / pii_redact_text (only rows with local:true can match there) or pii_guard_documents (all rows, incl. PERSON / LOCATION / STREET_ADDRESS); redaction_styles keys are the allowed redactionStyle values.\\nEXAMPLE: {} -> {\\\"detectors\\\":[{\\\"type\\\":\\\"AWS_ACCESS_KEY\\\",\\\"category\\\":\\\"secret\\\",\\\"local\\\":true},...]}\",\"params\":[]},{\"name\":\"pii_scan_text\",\"description\":\"WHAT: Detect PII (emails, phones, US SSNs, Luhn-valid cards, mod-97 IBANs, UK NINOs, India Aadhaar/PAN/GSTIN, Korea RRNs, Japan My Number, Singapore NRIC/FIN, Vietnam CCCD, Taiwan national IDs, China resident IDs, IPv4/IPv6) and secrets (AWS/GitHub/GitLab/Slack/Stripe/Google/OpenAI/Anthropic/HF/npm/SendGrid/Twilio/Azure keys, JWTs, private keys, URL credentials, key=value secrets) in text.\\nWHEN: Before sending prompts, tickets, logs or files to an LLM or third party; to audit text for leaked credentials. Findings are paged across all documents.\\nWHEN NOT: To get sanitized text use pii_redact_text. For person names/addresses (NER), public URLs or PDFs use pii_guard_documents (paid). Not for images (no OCR).\\nCOST: Free. Local regex/validators only; no APIFY_TOKEN.\\nRETURNS: Paged findings across all documents, each with a masked preview; raw values are never returned. Errors: INPUT_TOO_LARGE.\\nBEHAVIOR: No network calls; text never leaves your machine; milliseconds.\\nPARAMETERS: texts: one array element per document; each finding carries doc_index = the element's 0-based position, and the 500,000-char cap applies to the SUM of all elements (over it -> INPUT_TOO_LARGE; split into several calls). entityTypes: filters findings after detection; names are case-insensitive, unknown names silently match nothing, and NER-only types (PERSON, LOCATION, STREET_ADDRESS) never match here. allowList: compared with the whole matched value, case-insensitively (allow \\\"support@yourco.com\\\", not \\\"yourco.com\\\"). entropyScan: only adds HIGH_ENTROPY_STRING findings; it never removes others. defaultPhoneRegion: affects only national-format numbers such as \\\"030 1234567\\\" (needs \\\"DE\\\"); \\\"+49 ...\\\" numbers parse with any region. limit/offset page the flat findings list across all documents, while meta.documents always summarises every document; fetch the next page with offset = nextOffset until hasMore is false.\\nEXAMPLE: {\\\"texts\\\":[\\\"Mail jane@acme.com, key AKIAIOSFODNN7EXAMPLE\\\"]} -> 2 findings: EMAIL (masked \\\"j***@a***.com\\\"), AWS_ACCESS_KEY; risk_level \\\"critical\\\".\",\"params\":[\"texts\",\"entityTypes\",\"allowList\",\"entropyScan\",\"defaultPhoneRegion\",\"limit\",\"offset\"]},{\"name\":\"pii_redact_text\",\"description\":\"WHAT: Return sanitized copies of texts with every local PII/secret finding replaced (placeholder [EMAIL_1], mask, or salted hash).\\nWHEN: Right before sending user data to an LLM/third party. Use returnPlaceholderMap=true if you need to restore originals in the LLM answer later.\\nWHEN NOT: For a findings report only use pii_scan_text. For names/addresses NER, URLs or PDFs use pii_guard_documents (paid).\\nCOST: Free; no token.\\nRETURNS: One \\\"redacted_document\\\" row per text with output_text; meta.placeholder_map only when requested. Errors: INPUT_TOO_LARGE.\\nBEHAVIOR: Same input gives the same output except redactionStyle \\\"hash\\\" (random per-call salt). No network calls; local, milliseconds.\\nPARAMETERS: texts: one element per document, 500,000 chars in total; the same value gets the same placeholder in every document of one call ([EMAIL_1] everywhere), but numbering restarts on each call. redactionStyle: \\\"placeholder\\\" is the only reversible style; \\\"mask\\\" keeps a few characters for human review; \\\"hash\\\" output differs between calls (random salt), so do not compare hashes across calls. returnPlaceholderMap: only has an effect with redactionStyle=\\\"placeholder\\\" (ignored for mask/hash); the map in meta.placeholder_map holds the ORIGINAL values, so keep it out of the LLM prompt and restore answers with pii_restore_text (free, local). entityTypes / allowList / entropyScan / defaultPhoneRegion: identical semantics to pii_scan_text (filter after detection, whole-value case-insensitive allow-list). limit/offset page whole documents (one item per text, default 10 per page), not findings.\\nEXAMPLE: {\\\"texts\\\":[\\\"Call +1 415 555 0100 or mail jane@acme.com\\\"]} -> output_text \\\"Call [PHONE_1] or mail [EMAIL_1]\\\".\",\"params\":[\"texts\",\"redactionStyle\",\"returnPlaceholderMap\",\"entityTypes\",\"allowList\",\"entropyScan\",\"defaultPhoneRegion\",\"limit\",\"offset\"]},{\"name\":\"pii_restore_text\",\"description\":\"WHAT: Put the original values back into texts (typically an LLM answer) that contain placeholders such as [EMAIL_1], using the placeholder map from pii_redact_text or pii_guard_documents. Runs 100% on your machine.\\nWHEN: After an LLM or third party answered a prompt you sanitized with pii_redact_text (redactionStyle \\\"placeholder\\\", returnPlaceholderMap=true), before showing the answer to the user.\\nWHEN NOT: To redact (pii_redact_text) or find PII (pii_scan_text). Masked and hashed values cannot be restored; only placeholder style is reversible.\\nCOST: Free; no token.\\nRETURNS: One \\\"restored_document\\\" row per text with output_text, replacements and unknown_placeholders. Errors: INPUT_TOO_LARGE.\\nBEHAVIOR: No network calls; the map never leaves your machine; milliseconds. Max 50 texts, 200,000 chars each, 500,000 total; map up to 10,000 entries.\\nPARAMETERS: placeholderMap: pass meta.placeholder_map unchanged; every key is replaced wherever it occurs exactly (case-sensitive, longest key first, one pass, so a restored value is never replaced again). unknown_placeholders lists [TYPE_N]-shaped tokens left in the text that the map does not contain (the LLM invented or altered them); they stay as they are. A placeholder the LLM rewrote (e.g. \\\"EMAIL_1\\\" without brackets) is not restored. The output contains the ORIGINAL sensitive values: show it to the user, do not send it back to the LLM. limit/offset page whole documents (default 10 per page).\\nEXAMPLE: {\\\"texts\\\":[\\\"I will email [EMAIL_1] today.\\\"],\\\"placeholderMap\\\":{\\\"[EMAIL_1]\\\":\\\"jane@acme.com\\\"}} -> output_text \\\"I will email jane@acme.com today.\\\", replacements 1.\",\"params\":[\"texts\",\"placeholderMap\",\"limit\",\"offset\"]},{\"name\":\"pii_guard_documents\",\"description\":\"WHAT: Runs the Fairquery Apify Actor llm-data-guard-pii-secrets: everything pii_scan_text does PLUS person-name/location NER, street addresses, public document URLs (txt/md/json/csv/HTML/PDF text layer, <= 10 MB) and restore mode (put originals back into LLM output using a placeholder map).\\nWHEN: Only when you need NER names/addresses, files at URLs/PDFs, or the hosted pipeline.\\nWHEN NOT: Plain text scans (pii_scan_text / pii_redact_text, free), restoring placeholders in an LLM answer (pii_restore_text, free, same result as restore mode), images (no OCR), email deliverability.\\nCOST: Paid, billed to YOUR Apify account via your APIFY_TOKEN: $1.50 per 1,000 documents + $0.20 per 1,000 findings. Example: 10 docs with 20 findings ~ $0.02.\\nRETURNS: Paged \\\"document\\\" rows (findings masked; output_text in redact/restore modes) or \\\"error\\\" rows. Tool errors: APIFY_TOKEN_MISSING, APIFY_TOKEN_INVALID, APIFY_PAYMENT_REQUIRED, APIFY_ACTOR_RUN_FAILED, APIFY_TIMEOUT, INPUT_EMPTY.\\nBEHAVIOR: Makes network calls: runs the Actor in your Apify account, which may fetch documentUrls. Latency seconds to a few minutes (300 s actor timeout). Up to 1000 texts / 100 URLs (10 MB each).\\nPARAMETERS: texts and/or documentUrls: at least one non-empty (the schema marks both optional; neither -> INPUT_EMPTY, not billed); both may be combined and each text or URL becomes one billed document row. mode=\\\"restore\\\" ignores all detector flags; a placeholder missing from placeholderMap stays as is. Cost scales with documents and findings, so narrow entityTypes to cut finding charges. limit/offset only page the returned rows: every call processes and bills the whole input again (also when only offset changes), so pick a limit (max 1000) that covers all rows instead of paging.\\nEXAMPLE: {\\\"documentUrls\\\":[\\\"https://example.com/report.pdf\\\"],\\\"mode\\\":\\\"redact\\\",\\\"detectNames\\\":true}\",\"params\":[\"texts\",\"documentUrls\",\"mode\",\"redactionStyle\",\"returnPlaceholderMap\",\"placeholderMap\",\"detectNames\",\"detectAddresses\",\"entropyScan\",\"entityTypes\",\"allowList\",\"limit\",\"offset\"]},{\"name\":\"email_check_syntax\",\"description\":\"WHAT: Offline email checks: RFC-style syntax + normalization, common domain typo \\\"did you mean\\\" (gmial.com -> gmail.com), disposable/temporary domain (bundled CC0 list, ~thousands of domains), role account (info@, sales@), free webmail provider.\\nWHEN: Fast pre-filtering of signups or lead lists, before paying for email_validate_deliverability.\\nWHEN NOT: Does NOT check DNS/MX, so it cannot tell whether the domain receives mail; use email_validate_deliverability (paid) for MX/SPF/DMARC.\\nCOST: Free; local, no token.\\nRETURNS: Paged \\\"email_check\\\" rows; verdict is invalid | risky | unknown, never valid (dns_checked is always false).\\nBEHAVIOR: No network calls (no DNS/SMTP); synchronous and CPU-bound, no rate limits: 10,000 addresses (the per-call maximum) return in well under a second.\\nPARAMETERS: emails: each element is parsed on its own (one address per element; a comma-separated list in one element is INVALID_SYNTAX, not split). Before checking, \\\"Name <addr>\\\" is reduced to addr, a leading \\\"mailto:\\\" is dropped, the domain is lowercased (local part keeps its case), a trailing dot is removed and IDN domains are converted to punycode; the normalized value is returned as email, the original as input. Duplicates are not merged: every element yields one row, in input order. Role detection ignores +tags (sales+eu@ counts as sales@) and disposable matching also covers subdomains of listed domains. limit/offset page those rows; meta.summary always counts verdicts over ALL rows, not just the current page.\\nEXAMPLE: {\\\"emails\\\":[\\\"someone@gmial.com\\\"]} -> verdict \\\"risky\\\", reasons [\\\"POSSIBLE_TYPO\\\",\\\"DNS_NOT_CHECKED\\\"], did_you_mean \\\"someone@gmail.com\\\".\",\"params\":[\"emails\",\"limit\",\"offset\"]},{\"name\":\"email_validate_deliverability\",\"description\":\"WHAT: Runs the Fairquery Apify Actor email-validator-mx-disposable: syntax, domain existence, MX/null-MX, disposable, role, free provider, typo suggestion, SPF/DMARC policy, mail provider; final verdict valid | risky | invalid | unknown.\\nWHEN: Only when MX/DNS matters (can the domain receive mail?), e.g. cleaning lists before a send or verifying a lead's domain; pre-filter with email_check_syntax to avoid paying for obviously bad rows.\\nWHEN NOT: Offline format, typo, disposable or role checks (free email_check_syntax). Leads that also need sanctions screening: trust_screen_lead (one merged decision). It does not SMTP-probe mailboxes.\\nCOST: Paid, billed to YOUR Apify account via your APIFY_TOKEN: $0.79 per 1,000 emails (+ $0.05 per 1,000 runs). 100 emails ~ $0.08.\\nRETURNS: Paged \\\"email\\\" rows (verdict valid | risky | invalid | unknown with reasons[]) or \\\"error\\\" rows. Tool errors: APIFY_TOKEN_MISSING, APIFY_TOKEN_INVALID, APIFY_PAYMENT_REQUIRED, APIFY_ACTOR_RUN_FAILED, APIFY_TIMEOUT.\\nBEHAVIOR: No email is sent; results change only with live DNS. Makes network calls: runs an Apify Actor (DNS/MX lookups) in your account; latency seconds to minutes (300 s timeout).\\nPARAMETERS: emails: elements may also hold comma/semicolon/newline-separated lists or \\\"Name <addr>\\\" forms; the Actor splits them, trims, and skips case-insensitive duplicates, so you pay once per unique address. The allow* flags only decide whether a condition downgrades the verdict to \\\"risky\\\": the matching reason code (ROLE_ACCOUNT, DISPOSABLE_DOMAIN, FREE_PROVIDER) is reported in reasons[] either way, and they can never turn an \\\"invalid\\\" address (bad syntax, no domain, null MX, no mail server) into \\\"valid\\\". POSSIBLE_TYPO and IMPLICIT_MX_ONLY always make it \\\"risky\\\" regardless of flags. Typical presets: B2B lead list = allowFreeProviders false + allowRoleAccounts false; consumer signups = defaults. checkSpfDmarc only adds has_spf / has_dmarc / dmarc_policy fields; it never changes the verdict or the price. limit/offset only page the returned rows: every call validates and bills the whole list again (also when only offset changes), so set limit (max 1000) to cover all rows instead of paging.\\nEXAMPLE: {\\\"emails\\\":[\\\"john@stripe.com\\\"]} -> verdict \\\"valid\\\", has_mx true, mail_provider \\\"Google Workspace / Gmail\\\".\",\"params\":[\"emails\",\"checkSpfDmarc\",\"allowRoleAccounts\",\"allowDisposable\",\"allowFreeProviders\",\"limit\",\"offset\"]},{\"name\":\"sanctions_list_sources\",\"description\":\"WHAT: Static list of the official sanctions lists sanctions_screen_names checks (id, name, authority, download URL), the score scale and the legal disclaimer.\\nWHEN: To choose the lists parameter, cite sources in a report, or explain coverage before paying.\\nWHEN NOT: To screen a name (sanctions_screen_names, paid). It does not download lists or report freshness.\\nCOST: Free; no token.\\nRETURNS: One static object, including the disclaimer to show with screening results.\\nBEHAVIOR: No network calls; static local catalog, instant. No rate limits.\\nPARAMETERS: None: call with an empty object {}; the result is static and cannot be filtered. Its output feeds sanctions_screen_names: each sources[].id (OFAC_SDN, OFAC_CONS, EU, UK, UN) is a valid value for its lists parameter, and score_scale explains how its minScore threshold is applied.\\nEXAMPLE: {} -> {\\\"sources\\\":[{\\\"id\\\":\\\"OFAC_SDN\\\",\\\"authority\\\":\\\"US Treasury OFAC\\\",...},...]}\",\"params\":[]},{\"name\":\"sanctions_screen_names\",\"description\":\"WHAT: Runs the Fairquery Apify Actor sanctions-watchlist-screener: fuzzy-match people/organisations against OFAC SDN, OFAC Consolidated, EU, UK and UN lists from the official sources (re-downloaded when the cached copy in your Apify account is older than 6 h; every row reports each list's publication date); optional country/DOB filters.\\nWHEN: KYC/KYB onboarding, vendor/counterparty checks, bulk re-screening. Put all names in ONE call (each call is one run with its own start fee; list loading takes ~2-5 s from the cache, or 10-40 s, up to ~60 s, when lists are re-downloaded).\\nWHEN NOT: PEP/adverse media, certified compliance decisions. For coverage info use free sanctions_list_sources. Leads that also have an email to validate: trust_screen_lead (one merged decision).\\nCOST: Paid, billed to YOUR Apify account via your APIFY_TOKEN: $3.00 per 1,000 names + $7.00 per 1,000 runs. 200 names in one call ~ $0.61.\\nRETURNS: Paged \\\"screening\\\" rows (status potential_match | no_match, matches[] best first, lists_unavailable) or \\\"error\\\" rows. Tool errors: INPUT_EMPTY, APIFY_TOKEN_MISSING, APIFY_TOKEN_INVALID, APIFY_PAYMENT_REQUIRED, APIFY_ACTOR_RUN_FAILED, APIFY_TIMEOUT. Not a certified screening service. Automated fuzzy matching against public lists; false positives and misses are possible. Review every potential match manually and consult official sources/legal counsel before acting.\\nBEHAVIOR: Results are stable for a given list snapshot. Makes network calls: runs an Apify Actor in your account; latency seconds to minutes (300 s timeout). Up to 10,000 names.\\nPARAMETERS: names and/or queries: at least one non-empty (the schema marks both optional; neither -> INPUT_EMPTY, not billed). Both may be combined; every entry is billed once, so use names for bare strings and queries when you have country/dateOfBirth/entityType or want your own id echoed. In queries, dateOfBirth removes listed individuals born more than 1 year apart, while country never removes matches (it only sets country_match); entityType \\\"entity\\\" covers organisations, vessels and aircraft. lists: omit to screen all five; a list that cannot be downloaded is reported in lists_unavailable instead of failing the run. minScore: a match is returned only if its 0-100 similarity is >= minScore; 85 balances recall and noise, 90-95 for large batches, 75-80 for transliterated names; it does not change the price. maxMatchesPerName caps matches[] only; match_count still reports all matches. limit/offset only page the returned rows: every call screens and bills all names again (also when only offset changes), so set limit (max 1000) to cover all rows instead of paging.\\nEXAMPLE: {\\\"queries\\\":[{\\\"name\\\":\\\"Banco Nacional de Cuba\\\",\\\"entityType\\\":\\\"entity\\\"}],\\\"minScore\\\":90} -> status potential_match (OFAC_SDN).\",\"params\":[\"names\",\"queries\",\"lists\",\"minScore\",\"maxMatchesPerName\",\"limit\",\"offset\"]},{\"name\":\"osv_query_packages\",\"description\":\"WHAT: Query the public OSV.dev database (api.osv.dev querybatch) directly from your machine for exact package versions; returns which are vulnerable and the advisory IDs.\\nWHEN: Quick \\\"is lodash 4.17.20 vulnerable?\\\" checks for up to 200 packages; then osv_get_vulnerability for details of specific IDs.\\nWHEN NOT: Parsing manifests/lockfiles, severity filtering, fixed/recommended versions in one shot -> osv_audit_dependencies (paid).\\nCOST: Free; no token, nothing sent to Fairquery or Apify.\\nRETURNS: Paged \\\"package\\\" rows (vulnerable, vuln_ids) or per-entry INVALID_ECOSYSTEM \\\"error\\\" rows. Tool errors: OSV_FETCH_FAILED (retryable).\\nBEHAVIOR: One HTTPS request to api.osv.dev (Google-run public API) for all packages; typically <2 s, 20 s timeout. Results change only when OSV publishes advisories.\\nPARAMETERS: packages: each entry is checked independently and returns exactly one row, in input order. An unknown ecosystem yields a per-entry INVALID_ECOSYSTEM error row while the other entries still run. A version range such as \\\"^4.17.0\\\" or \\\">=2\\\" is not resolved and normally returns no vulnerabilities (a false \\\"safe\\\"), so pin versions from your lockfile first. Duplicate entries are queried and returned twice. limit/offset page the rows (all packages are sent to OSV in a single request); meta.vulnerable_count counts all packages, not only the page.\\nEXAMPLE: {\\\"packages\\\":[{\\\"ecosystem\\\":\\\"npm\\\",\\\"name\\\":\\\"lodash\\\",\\\"version\\\":\\\"4.17.20\\\"}]} -> vulnerable true, vuln_ids [\\\"GHSA-35jh-r3h4-6jhm\\\",...].\",\"params\":[\"packages\",\"limit\",\"offset\"]},{\"name\":\"osv_get_vulnerability\",\"description\":\"WHAT: Fetch full OSV records (summary, details, aliases, severity vectors, affected ranges, fixed versions, references) for advisory IDs directly from api.osv.dev.\\nWHEN: You have IDs (from osv_query_packages or a report) and need details or the fixed version.\\nWHEN NOT: To find which vulns affect a package version (osv_query_packages) or a whole manifest (osv_audit_dependencies, paid).\\nCOST: Free; no token.\\nRETURNS: Paged \\\"vulnerability\\\" rows with the raw OSV record fields, or \\\"error\\\" rows (VULN_NOT_FOUND | OSV_FETCH_FAILED, see PARAMETERS).\\nBEHAVIOR: One HTTPS call per ID to api.osv.dev, in parallel; typically <2 s, 20 s timeout each.\\nPARAMETERS: ids: each ID is fetched separately and yields exactly one row in input order, so one bad ID never fails the others: an unknown ID returns a VULN_NOT_FOUND row (not retryable), a network/5xx problem an OSV_FETCH_FAILED row (retryable - retry just that ID). Prefer the ecosystem/GHSA IDs returned by osv_query_packages (vuln_ids); a CVE-... ID only resolves when OSV indexes that CVE as its own record, otherwise look up the GHSA alias. IDs are matched as given (no trimming of URLs or prefixes), and duplicates are fetched twice. limit/offset only page the returned rows; every call re-fetches all given IDs, so for a next page resend the same ids with offset = nextOffset.\\nEXAMPLE: {\\\"ids\\\":[\\\"GHSA-35jh-r3h4-6jhm\\\"]} -> lodash command injection, fixed in 4.17.21.\",\"params\":[\"ids\",\"limit\",\"offset\"]},{\"name\":\"osv_audit_dependencies\",\"description\":\"WHAT: Runs the Fairquery Apify Actor osv-dependency-vulnerability-check: parses package.json, package-lock.json (v1-v3), requirements.txt or go.mod (or a package list), checks OSV, and returns per-package max severity/CVSS, fixed versions, a recommended upgrade version and one row per vulnerability (deduped aliases).\\nWHEN: Only for manifests, severity filtering or fix recommendations: full project audits from a pasted manifest, CI-style reports; for a few exact versions use osv_query_packages (free).\\nWHEN NOT: Quick checks of a few exact versions (osv_query_packages, free) or one advisory (osv_get_vulnerability, free).\\nCOST: Paid, billed to YOUR Apify account via your APIFY_TOKEN: $0.50 per 1,000 packages + $1.50 per 1,000 vulnerabilities found (+ $0.05 per 1,000 runs). Use minSeverity=\\\"HIGH\\\" to cut vuln rows. lodash+django (2 pkgs, 41 vulns) ~ $0.06.\\nRETURNS: Paged rows type=\\\"package\\\" (vulnerable, vuln_count, max_severity, fixed_versions, recommended_version), type=\\\"vulnerability\\\" (id, cve_ids, severity, cvss_score, fixed_versions, osv_url) or type=\\\"error\\\". Tool errors: INPUT_EMPTY, APIFY_TOKEN_MISSING, APIFY_TOKEN_INVALID, APIFY_PAYMENT_REQUIRED, APIFY_ACTOR_RUN_FAILED, APIFY_TIMEOUT.\\nBEHAVIOR: Makes network calls: runs an Apify Actor (querying OSV.dev) in your account; latency seconds to minutes (300 s timeout). Up to 1000 packages or a 2,000,000-char manifest.\\nPARAMETERS: packages or manifestText = input (one required); manifestType = format, default auto-detect; minSeverity = only report at/above ALL|LOW|MEDIUM|HIGH|CRITICAL (default ALL); includeDevDependencies (default true); limit = page size (default 100, max 1000); offset = items to skip for paging (default 0).\\nEXAMPLE: {\\\"manifestText\\\":\\\"django==3.2.0\\\\nrequests==2.19.0\\\",\\\"minSeverity\\\":\\\"HIGH\\\"}\",\"params\":[\"packages\",\"manifestText\",\"manifestType\",\"minSeverity\",\"includeDevDependencies\",\"limit\",\"offset\"]},{\"name\":\"trust_screen_lead\",\"description\":\"WHAT: One call per batch of leads/counterparties: runs email_validate_deliverability on their emails and sanctions_screen_names on their person/company names IN PARALLEL, then merges results per lead with an overall decision: block (invalid email or sanctions potential_match), review (risky email), pass.\\nWHEN: Onboarding customers/vendors, qualifying inbound leads, CRM hygiene where both email quality and sanctions exposure matter.\\nWHEN NOT: Email only -> email_validate_deliverability; names only -> sanctions_screen_names (same per-item prices, no merge step). Free pre-filter first: email_check_syntax. Use this tool only when a lead needs both checks and one decision.\\nCOST: Paid, billed to YOUR Apify account via your APIFY_TOKEN: $0.79 per 1,000 leads with email + $3.00 per 1,000 leads with name (= $3.79 per 1,000 full leads) + $7.00 per 1,000 calls for the sanctions run. 100 full leads ~ $0.39.\\nRETURNS: Paged \\\"lead\\\" rows (decision pass | review | block with reasons[]; sanctions_matches holds the top 3); meta.summary counts by decision. Partial failure: the affected check shows \\\"unavailable\\\" and meta.errors lists codes. Tool errors: INPUT_EMPTY, APIFY_TOKEN_MISSING.\\nBEHAVIOR: No email is sent. Runs the email and sanctions Apify Actors in parallel (2 runs per call) in your account; ~5-45 s (sanctions lists come from a cache at most 6 h old, or are downloaded), 300 s timeout.\\nPARAMETERS: leads: each record needs email and/or name (if no lead has either -> INPUT_EMPTY, nothing billed); a lead with only an email skips sanctions (sanctions_status \\\"not_checked\\\") and one with only a name skips email (email_verdict \\\"not_checked\\\"), so a lead is billed for each check it gets (prices under COST), plus the per-call sanctions run fee when any lead has a name. Identical emails across leads are validated and billed once. ref joins sanctions results back to the lead, so keep refs unique (default = the lead's 0-based index as a string). country and entityType apply to that lead's sanctions check only: entityType filters candidates, while country only annotates matches (never removes them). minScore: sanctions similarity threshold; default 88 here (stricter than the 85 of sanctions_screen_names) to keep block decisions low-noise; each name returns at most its top 3 matches. allowFreeProviders=false turns gmail.com-type addresses into email_verdict \\\"risky\\\", i.e. decision \\\"review\\\" (never \\\"block\\\"). Decision precedence: any sanctions potential_match or invalid email -> block; else risky email or an incomplete check -> review; else pass. limit/offset page the merged lead rows, but every call re-runs and re-bills both checks for all leads (also when only offset changes), so set limit (max 1000) to cover all leads; meta.summary counts all leads.\\nEXAMPLE: {\\\"leads\\\":[{\\\"ref\\\":\\\"L1\\\",\\\"email\\\":\\\"cfo@acme.com\\\",\\\"name\\\":\\\"Acme Trading LLC\\\",\\\"country\\\":\\\"US\\\"}]} -> {decision:\\\"pass\\\",email_verdict:\\\"valid\\\",sanctions_status:\\\"no_match\\\"}\",\"params\":[\"leads\",\"minScore\",\"allowFreeProviders\",\"limit\",\"offset\"]},{\"name\":\"mcp_server_precheck\",\"description\":\"WHAT: Pre-install check for one MCP server. Scans tool names, descriptions and parameter text for injection phrasing, concealed characters, hidden markup and cross-server shadowing.\\nWHEN: Before installing or enabling an MCP server, once you have a tools/list result or the package on disk.\\nWHEN NOT: For a dependency audit with no tool list, call osv_audit_dependencies. For a few exact versions, call osv_query_packages. This tool does not install, start or execute the package.\\nCOST: The scan is free and stays on this machine. auditDependencies=true is optional and bills YOUR Apify account via your APIFY_TOKEN: $0.50 per 1,000 packages + $1.50 per 1,000 vulnerabilities found. That mode also looks up license and publish age on the public npm registry (package name only). With no token the scan still returns and the audit row is APIFY_TOKEN_MISSING.\\nRETURNS: Paged \\\"finding\\\" rows (rule, severity, tool, field, evidence) and, when an audit was requested, one \\\"dependency_audit\\\" row plus any OSV rows. meta.risk_level is none, low, medium, high, critical or not_assessed. meta.shared_externally.tool_names_and_descriptions is always false. Errors: INPUT_EMPTY, INVALID_JSON, INVALID_PACKAGE_NAME, PATH_NOT_FOUND, PATH_NOT_ALLOWED, INPUT_TOO_LARGE.\\nBEHAVIOR: Default auditDependencies=false: no network calls and no process spawn. Reads only package.json, package-lock.json, npm-shrinkwrap.json, manifest.json and server.json inside a directory you name, or one .json file you name. Refuses sensitive filenames and does not follow a symlink that leaves that directory. packageName resolves only under that directory or the current working directory. auditDependencies=true may call registry.npmjs.org and the OSV Actor (300 s timeout).\\nPARAMETERS: At least one of tools, toolsListJson, path or packageName (none of them -> INPUT_EMPTY, not billed). tools: structured tools/list entries. toolsListJson: raw JSON of a tools/list result, an MCPB manifest or a tools array; invalid JSON -> INVALID_JSON and nothing else is read. path: a local directory or a .json file; a sensitive basename -> PATH_NOT_ALLOWED and the file is not read. packageName: npm name, looked up as node_modules/<name> under path or the working directory, or a directory whose package.json name matches; if it is not on disk the result notes PACKAGE_NOT_LOCAL and does not download it. Each field is scanned up to 20,000 characters and the raw total must be <= 500,000. auditDependencies defaults to false. minSeverity and includeDevDependencies are forwarded to the OSV Actor only when the audit runs (same meaning as osv_audit_dependencies). limit/offset page the combined rows. When the audit flag is true, every call runs the paid audit again, including a call that only changes offset.\\nEXAMPLE: {\\\"tools\\\":[{\\\"name\\\":\\\"sum\\\",\\\"description\\\":\\\"Add two numbers.\\\"}]} -> risk_level \\\"none\\\", shared_externally.tool_names_and_descriptions false. A poisoned description returns finding rows and a higher risk_level.\",\"params\":[\"tools\",\"toolsListJson\",\"path\",\"packageName\",\"auditDependencies\",\"minSeverity\",\"includeDevDependencies\",\"limit\",\"offset\"]}],\"toolsHash\":\"e77b7d266dc3e953f1c739e5cd16241761f89e9562fd4690d56e61083130f8fa\",\"wrote\":[],\"callsAt\":\"2026-11-16T11:37:19.187Z\",\"calls\":[{\"tool\":\"pii_list_detectors\",\"ok\":true,\"ms\":4,\"bytes\":5529},{\"tool\":\"sanctions_list_sources\",\"ok\":true,\"ms\":0,\"bytes\":1593}],\"host\":{\"commit\":\"eaaffffaf52255d1b77dc4aacffdfaf353f0c12c\",\"run\":\"https://github.com/itsHaddad/bragproof/actions/runs/43857070216\"},\"network\":{\"names\":[\"registry.npmjs.org\"],\"conns\":[],\"callNames\":[],\"callConns\":[]}}","token":"eyJhbGciOiJSUzI1NiIsImtpZCI6IjM4ODI2YjE3LTZhMzAtNWY5Yi1iMTY5LThiZWI4MjAyZjcyMyIsInR5cCI6IkpXVCIsIng1dCI6InlrTmFZNHFNX3RhNGsyVGdaT0NFWUxrY1lsQSJ9.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.T_8iLWjlpyeRBapPGR3DKIeU9x4umb_DAan34N-vGn0j7xajdVq0G2qZZOuR1ypmM_3rb2Hrhrh0-UjYuV1VkwWNbOIDsm_qiBVsFxNn1rcVEaH2ml4xrKui6ohZiBU3UkYSEue7Jx7e6l86UzJFO1qG3aKzXCCHf8jvrXv7NTSkYefjvGiCusFsTGA6fnrzN9JJSC1qUYQzlmXY0VcjzLj1ty3X5hjZ1TTaUxFrAEwGc4GEynocq72zr9LF_zhcGfuxTlmU8JjJ-Zx0Z64SJeLkTYt2aAoTUmrlaUfQFUGHhP-8LA0D5GFIAW1O00diOZtZuKfbV3UZyaqKE2fc6g"}