Bosco Labs: official records for AI agents
PYPI · BOSCO-LABS-DATA-MCP · 3 COMPONENTS
Sanctions, KYB company checks, SEC EDGAR, EU law and more from official sources, each row sourced
Available components
Last scanned (11 hours ago)
Scores higher than 71% of PyPI servers
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Bosco-Labs/bosco-labs-data). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability57
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3317 tokens (~368/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability check failed: the tool surface changed between 0.2.3 and 0.4.0: 9 tool removals, 0 breaking changes, 9 additions. See how to fix → Fail
Tool Coverage92
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 73% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 20 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 18 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 17 Nov 26 −15
- Stability: unverified → fail ▼ security
- Malware scan: pass → unverified ▼ security
- Stability: unverified → 0.33 ▲ functional
- Schema quality: good → excellent functional
- Package version: 0.2.3 → 0.4.0 functional
- Package version: 0.2.3 → 0.3.0 functional
- 11 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 10 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- 8 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 7 Nov 26 62
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed pypi/bosco-labs-data-mcp@0.4.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | pypi |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Bosco-Labs/bosco-labs-data |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Bosco-Labs/bosco-labs-data/.github/workflows/publish-mcp.yml@refs/tags/mcp-v0.4.0 |
| Rekor log index | 3953555493 |
| Predicate type | PyPI publish attestation https://docs.pypi.org/attestations/publish/v1 |
| Subject digest | sha256:5f3f4f87e2e92d1de5daaa527a71476278c4ae5ff243722d8954748efeffdfc8 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 31 packages
| Packages resolved | 31 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
find_sec_company SEC company lookup: ticker to CIK (free) ~256
Free, no API token needed. Identify a US-listed (SEC-registered) company: CIK, official name, ticker(s), exchange(s), industry (SIC code) and state of incorporation (source: SEC EDGAR company tickers file and submissions API). Use it to turn a ticker or name into the CIK that SEC tools take, or to check which exchange a stock trades on. Pass a ticker, a CIK or part of the name (best matches first, then by company size; check `name`). A name search covers companies with a listed ticker (about 10,000); a CIK also finds filers without one. Returns one row per company: cik, name, tickers, exchanges, sic, sic_description, state_of_incorporation, fiscal_year_end (MMDD), source_url (the EDGAR company page; cite it) and next_steps (the paid Bosco Labs calls for its filings and insider trades).
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Max companies for a name search (1-5). |
| query | string | yes | A ticker (AAPL), a CIK (320193) or part of the company name ("apple") |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
get_company_accounts UK, Danish and Norwegian company accounts ~346
Financials of UK, Danish and Norwegian companies, including private ones, from the accounts they file with Companies House (UK), Erhvervsstyrelsen (DK) and the Brønnøysund Register of Company Accounts (NO). Use it for revenue, profit, equity, cash or employees of a (private) company in these countries when you know its registration number. Coverage: UK every year filed digitally (iXBRL; paper/PDF-only years are skipped, and small UK companies often file no profit and loss account); Denmark all years; Norway the last 3 fiscal years (own accounts, not group). Pass at least one registration number. Newest fiscal year first. Returns one row per company per fiscal year: company_name, country, the registration number, lei, period_end, currency, revenue, gross_profit, operating_profit, profit_before_tax, net_income, total_assets, current_assets, cash_and_equivalents, total_equity, net_assets, total_liabilities, employees, metrics_found and the source links (report_url, registry_url, source_url). A missing figure was not filed; never treat it as zero. Cost to the user: $0.04 per company-year returned.
| Name | Type | Req | Description |
|---|---|---|---|
| dk_cvr_numbers | – | – | Danish 8-digit CVR numbers, e.g. 24256790 |
| max_results | integer | – | Max company-years per country to return (1-10). |
| no_org_numbers | – | – | Norwegian 9-digit org numbers, e.g. 923609016 |
| uk_company_numbers | – | – | Companies House numbers, e.g. 03117531 |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
get_eu_annual_reports EU annual report financials (ESEF) ~390
Audited annual financials of European listed companies, from their official ESEF annual reports (source: filings.xbrl.org; EU/EEA, UK and Ukraine, about 27,600 reports from 28 countries; Germany is not covered). Use it for revenue, profit, margins, EPS, balance sheet, cash flow or dividends of a listed European company. Pass exactly one of `lei` (most precise) or `company` (case-insensitive part of the registered name; it can match several companies, so check `company_name`). `countries` narrows a name search. Newest fiscal year first. Returns one row per annual report: lei, company_name, country, period_end, currency, revenue, gross_profit, operating_profit, ebitda, net_income, eps_basic/diluted, total_assets, total_equity, total_liabilities, cash_and_equivalents, operating_cash_flow, dividend_per_share, operating_margin, net_margin, return_on_equity, equity_ratio, revenue_growth, prior_year (same metrics for the comparative year) and viewer_url (cite it: the report page where every value can be checked). Money is in full units of `currency`; ratios are decimals (0.25 = 25%). A missing metric was not tagged in the report; never treat it as zero. Cost to the user: $0.05 per annual report (with APIFY_TOKEN plus $0.01 per call). Takes about 10-60 s.
| Name | Type | Req | Description |
|---|---|---|---|
| company | – | – | Part of the name, e.g. "heineken" |
| countries | – | – | ISO alpha-2 filing countries, e.g. ['NL'] |
| lei | – | – | 20-character Legal Entity Identifier |
| max_results | integer | – | Max annual reports to return (1-10). |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
get_lei_record LEI lookup (GLEIF, free) ~289
Free, no API token needed. Legal Entity Identifier (LEI) lookup in the official GLEIF register: about 2.9 million companies, funds and other legal entities worldwide (source: GLEIF API, CC0 open data). Use it to identify a company: its exact legal name, LEI, whether it is active, its jurisdiction and country, its local registration number and its ultimate parent company. Pass an LEI (exact record) or a company name (best matches first; check `legal_name`). Returns one row per entity: lei, legal_name, entity_status (ACTIVE/INACTIVE), registration_status (ISSUED, LAPSED, ...), jurisdiction, legal_address_country, legal_address_city, headquarters_country, registered_as (local registry number), ultimate_parent (lei, legal_name; when reported), source_url (the GLEIF record; cite it) and next_steps (the paid Bosco Labs call for this company's financials: tool and arguments on the remote MCP server and HTTP API, stdio_tool in this package).
| Name | Type | Req | Description |
|---|---|---|---|
| max_results | integer | – | Max companies for a name search (1-5). |
| query | string | yes | A 20-character LEI, e.g. 724500Y6DUVHQD6OXN27, or a company name, e.g. "Heineken" |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_dod_contract_awards Pentagon (DoD) contract awards ~417
US Department of Defense contract awards (or any other federal agency's) since FY2008: who won, how much was obligated, which service, the parent company and the winner's US stock ticker with SEC shares outstanding (source: USAspending.gov / FPDS, tickers from the SEC). Use it for "which contracts did Lockheed/Kratos win", the largest recent Pentagon awards, or awards in an industry (NAICS/PSC). Default: DoD award-days of at least $7.5M (the DoD's public announcement threshold), signed in the last 135 days. DoD data is published with a delay of up to ~3 months, so the most recent weeks are incomplete. Newest signing dates first, then largest amounts. Slow: a call can take a minute or more, so keep max_results small. Returns one row per award per signing day: action_date, recipient_name, parent_name, ticker, amount_usd (summed obligations that day), new_award, awarding_agency, awarding_sub_agency, award_id, naics_description, psc_description, description (shortened), shares_outstanding and usaspending_url (the award page; cite it). Cost to the user: $0.005 per award row returned.
| Name | Type | Req | Description |
|---|---|---|---|
| agencies | – | – | Top-tier agency; omit for DoD; e.g. "Department of Homeland Security" |
| date_from | – | – | Signing date; default: 135 days before date_to |
| date_to | – | – | – |
| max_results | integer | – | Max award rows to return (1-50). |
| min_amount_usd | integer | – | Min obligated per award and day |
| naics_codes | – | – | Industry codes, e.g. 336414 |
| psc_codes | – | – | Product/service codes, e.g. 1410, R425 |
| recipients | – | – | Winner or parent name contains, e.g. "kratos" |
| tickers | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_eu_tenders EU public tenders (TED) ~329
European public procurement notices from TED (Tenders Electronic Daily), the EU's official procurement journal: every above-threshold public contract in the EU/EEA, Switzerland and more, about 22,000 notices a week (source: official TED Search API). Use it to find open calls for tenders (with deadline and estimated value), contract awards (winners and awarded value) or planned purchases, by keyword, buyer country or sector. Default: open calls for tenders published in the last 7 days. Newest first. Returns one row per notice: notice_id, published, notice_type, title, description (shortened), buyer_name, buyer_country, main_cpv, estimated_value, awarded_value, currency, winner_names, deadline, procedure_type and ted_url (the notice; cite it). Cost to the user: $0.002 per notice returned.
| Name | Type | Req | Description |
|---|---|---|---|
| countries | – | – | Buyer countries, ISO codes, e.g. ['DE', 'FR'] |
| cpv_codes | – | – | CPV sector prefixes: 72 IT services, 45 construction, 3312 medical |
| keywords | – | – | All words must appear, any language, e.g. cloud |
| max_results | integer | – | Max notices to return (1-100). |
| min_value_eur | – | – | Leaves out notices without an EUR value |
| notice_types | – | – | Omit for open calls for tenders (contract_notice); contract_award = who won and for how much |
| published_from | – | – | Default: 7 days ago |
| published_to | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_sec_filings SEC EDGAR filings feed ~427
SEC EDGAR filings of US-listed companies and other filers: any form (8-K, 10-K, 10-Q, S-1, 13D/13G, Form 4, DEF 14A, 20-F, ...), from filings accepted minutes ago back to 1994 (source: SEC EDGAR submissions API, indexes and live feed). Use it to find a company's latest reports, earnings release dates and times, officer changes or other 8-K events, or market-wide filings of one type. Filter by tickers or CIKs (omit both for the whole market), form types, 8-K item codes or earnings releases only. Filing date range: date_from/date_to, or the last `lookback_days` days. Newest first. Returns one row per filing: filing_date, accepted_at, market_timing (before_open, market_hours, after_close), form, ticker, company_name, cik, items (8-K item codes), item_descriptions, report_date and links: primary_document_url (the document; cite it), filing_index_url. Cost to the user: $0.001 per filing returned.
| Name | Type | Req | Description |
|---|---|---|---|
| ciks | – | – | – |
| date_from | – | – | – |
| date_to | – | – | – |
| earnings_releases_only | boolean | – | Only 8-K item 2.02 earnings releases |
| form_types | – | – | e.g. 8-K, 10-K, 10-Q, S-1, 13D, DEF 14A |
| item_codes_8k | – | – | Only 8-Ks with these items, e.g. 5.02 (officer change), 1.01, 2.01 |
| lookback_days | – | – | Days back when date_from is omitted; omit to get a company's latest filings of any date (tickers/CIKs) or the last 7 days (whole market) |
| max_results | integer | – | Max filings to return (1-100). |
| tickers | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_sec_insider_trades SEC insider trades (Form 4) ~429
US insider trades reported to the SEC on Form 4 (officers, directors, 10% owners), from today's filings back to 2006 (source: SEC EDGAR Form 4 XML and the SEC insider data sets). Use it for "who is buying/selling stock X", insider activity before an event, or market-wide insider buying (cluster buys). Filter by tickers or CIKs (omit both for the whole market; a whole-market scan of many days can take a minute or more, so prefer tickers). Filing date range: date_from/date_to, or the last `lookback_days` days. Newest first. Returns one row per transaction: filing_date, ticker, issuer_name, insider_name, insider_roles, officer_title, transaction_date, transaction_code (P buy, S sell, ...), shares, price, value_usd, shares_owned_after, plan_10b5_1 (pre-planned sale; unknown before 2023-04), usable_from (first day a backtest may act on the row), in_cluster and filing_url (the SEC filing; cite it). Cost to the user: $0.0018 per transaction returned.
| Name | Type | Req | Description |
|---|---|---|---|
| ciks | – | – | – |
| cluster | – | – | Only trades in a cluster: 2+ directors/officers of one company trading the same way within 30 days, together >= $100,000 |
| date_from | – | – | – |
| date_to | – | – | – |
| insider_roles | – | – | – |
| lookback_days | – | – | Days back when date_from is omitted; omit for the default (90 days for tickers/CIKs, 7 days for the whole market) |
| max_results | integer | – | Max transactions to return (1-100). |
| min_value_usd | integer | – | Skip smaller trades |
| tickers | – | – | – |
| transaction_codes | – | – | Form 4 codes; omit for P (open-market purchase) and S (sale). Others: A award, M option exercise, F tax withholding, G gift. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
search_us_house_stock_trades US House stock trades ~331
Stock, option, fund and bond trades disclosed by members of the US House of Representatives under the STOCK Act (Periodic Transaction Reports), from January 2014 to today (source: official filings of the Clerk of the House). Use it for "what did Representative X trade", "which House members traded NVDA", or recent congressional trades. Filter by member name, tickers, transaction type and filing date (default: the last 30 days); use `years` for older history. Newest filings first. Returns one row per trade: member_name, state_district, filing_date, transaction_date, days_to_disclose, owner (self, spouse, joint, child), ticker, asset_description, asset_type, transaction_type, amount_min/amount_max (USD range as filed), amount_text, is_amendment and pdf_url (the filing; cite it). Amounts are ranges, not exact values. The Senate is not covered. Cost to the user: $0.0018 per trade returned.
| Name | Type | Req | Description |
|---|---|---|---|
| filed_from | – | – | Default: 30 days ago |
| filed_to | – | – | – |
| max_results | integer | – | Max trades to return (1-100). |
| members | – | – | Part of the member name, e.g. "Pelosi" |
| min_amount_usd | – | – | e.g. 15001 skips the $1,001-$15,000 range |
| tickers | – | – | – |
| transaction_types | – | – | – |
| years | – | – | Whole filing years for history, e.g. [2020, 2021] |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
How do I install the Bosco Labs: official records for AI agents MCP server?
Bosco Labs: official records for AI agents runs locally as a PyPI package, launched with uvx bosco-labs-data-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · bosco-labs-data-mcp
claude mcp add bosco-labs-bosco-labs-data -- uvx bosco-labs-data-mcp
What is the Bosco Labs: official records for AI agents MCP server?
Bosco Labs: official records for AI agents is an MCP server listed in the public MCP registry as io.github.Bosco-Labs/bosco-labs-data. Sanctions, KYB company checks, SEC EDGAR, EU law and more from official sources, each row sourced. This page covers its PyPI package (bosco-labs-data-mcp).
Is the Bosco Labs: official records for AI agents MCP server safe to use?
Bosco Labs: official records for AI agents scores 77 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. 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 Bosco Labs: official records for AI agents MCP server expose?
Bosco Labs: official records for AI agents exposes 9 tools: get_lei_record, find_sec_company, get_eu_annual_reports, get_company_accounts, search_sec_insider_trades, and 4 more. Their descriptions and schemas cost roughly 3,214 tokens of context every time the server is loaded.
Is the Bosco Labs: official records for AI agents MCP server still maintained?
Bosco Labs: official records for AI agents is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Bosco Labs: official records for AI agents MCP server under?
Bosco Labs: official records for AI agents declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Bosco Labs: official records for AI agents MCP server?
VerifyMCP ran 16 checks on Bosco Labs: official records for AI agents, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.