# Esef Filings

> XBRL filings index MCP — wraps the filings.xbrl.org JSON:API index run by

- name: io.github.pipeworx-io/esef-filings
- version: 0.1.10
- connection class: R0 (autonomous)
- trust: 97/100
- quality: –/100 (not scored)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.pipeworx-io%2Fesef-filings
- tools: https://api.protogrid.dev/v1/servers/io.github.pipeworx-io%2Fesef-filings/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "esef-filings": {
      "type": "http",
      "url": "https://gateway.pipeworx.io/esef-filings/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-98% +updated-20d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality –/100 (not scored)

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: n/a (weight 30)

- n/a `tools.descriptions`, `tools.description_length`, `tools.schemas`, `tools.annotations`, `tools.directory_hints`, `tools.token_cost`, `tools.api_dump`: tool list unknown (behind auth, not probed, or empty)

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool list unknown

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: unknown
- tools last changed: 2026-10-20T06:47:52.803Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.pipeworx-io/esef-filings.svg)](https://protogrid.dev/servers/io.github.pipeworx-io/esef-filings)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `esef_entity_filings` removed
  - List every annual report one company has published to the XBRL International filings index, resolving a company name, LEI, or national registration number to the filer. Answers "what years has Citycon filed?" or "give me Nokia's latest annual report". Returns the resolved company (name, identifier, and how the match was made) plus each filing with period end, country, regime, validation error/warning counts and links to the xBRL-JSON, HTML report and viewer. Covers 25,640 filings in two regimes: ESEF (~16,000 annual financial reports from 19 European countries — AT BE CY CZ DK ES FI FR GB GR IS IT LT NL NO PL PT RO SE) and UAIFRS (~9,600 Ukrainian IFRS filings, country UA). Pass `country` or `regime` to pin the scope you mean. Portuguese (PT), Spanish (ES) and Norwegian (NO) ESEF reports are also read directly from where each country publishes them — CMVM for Portugal, CNMV for Spain, Oslo Børs NewsWeb for Norway — so PT, ES and NO coverage follows official publication (typically within a day) rather than the index's months-long lag; each row names its `source` and those rows carry the official `published_at`. Swedish (SE) reports are likewise read from Finansinspektionen (FI), the Swedish OAM, which is the only source for Swedish FY2025 reports, Belgian (BE) reports from the FSMA's STORI database, the Belgian OAM, Maltese (MT) reports from the Malta Stock Exchange OAM, the only source for Maltese FY2025 reports, Croatian (HR) reports from HANFA's SRPI, the Croatian OAM and the only source for Croatian FY2025 reports, Hungarian (HU) reports from the MNB's Közzétételek site, the Hungarian OAM and the only source for Hungarian FY2025 reports, Lithuanian (LT) reports from oam.lt, the Lithuanian OAM run by Nasdaq Vilnius, as well as the index, Romanian (RO) reports from the ASF OAM, the only source for Romanian FY2025 reports, Cypriot (CY) reports from the Cyprus Stock Exchange public OAM, the only source for Cypriot FY2025 reports, and Latvian (LV) reports from CSRI, the Latvian OAM, the only source for Latvian FY2024 and FY2025 reports. Luxembourgish (LU), Slovenian (SI) and Estonian (EE) reports are also answered directly from the LuxSE OAM, SEOnet or the Estonian FSA's OAM for each request, because these three OAMs' terms require the operator's consent for commercial reuse of their documents beyond ordinary access; a lookup made once on a caller's behalf is not that. Greek (GR) and Irish (IE) reports are likewise answered directly from Euronext Athens and the Euronext Dublin OAM for each request — these two sites' terms forbid bots and automated access outright rather than just reuse, so these are Bruce-authorized live lookups rather than a re-derivation of the usual reasoning, kept live and never mirrored for the same reason. Bulgarian (BG) reports are answered directly from BEIS, a Bulgarian disclosure agent whose terms ask only for attribution (unlike Bulgaria's other disclosure agents, which this pack does not call) and covers only the roughly three issuers that use it. None of GR/IE/BG carry machine-readable facts (esef_filing_facts declines a live-lookup id and points at its `package_url`/`source_url`); SI is limited to the ~20 most recent Slovenian annual-report announcements; IE rows carry no `period_end` (Irish fiscal year ends vary by issuer); GR's `period_end` is inferred from the filing's reporting year, not stated exactly, and flagged `period_end_inferred`. All six (LU, SI, EE, GR, IE, BG) are pinned-country lookups only — pass `country` explicitly. The same annual report is frequently indexed once per language edition (a Finnish and an English row for one financial year), so results are also grouped into distinct reports with the English edition preferred, and both a filing count and a distinct-report count are returned.
- 2026-10-20 `esef_search_filings` removed
  - Search the XBRL International filings index (filings.xbrl.org) for published company annual reports. Answers "which European companies have filed an annual report for 2023", "does Nokia have an ESEF filing", "list Finnish filings with validation errors", "Portuguese filings with a period end after 2024-06-30", "Spanish annual reports for 2025". Returns per filing: company name, LEI or national identifier, country, reporting regime, period end, source (xbrl.org, cmvm, cnmv, newsweb or fi) and official publication time where known, XBRL validation error/warning counts, report language, and direct links to the machine-readable xBRL-JSON, the inline-XBRL HTML report and the viewer. Filter by company name (substring), country (ISO-2), regime, exact period end date, calendar year, or a period_end_from/period_end_to date range. Any other argument name is rejected with a user_error rather than silently ignored. Covers 25,640 filings in two regimes: ESEF (~16,000 annual financial reports from 19 European countries — AT BE CY CZ DK ES FI FR GB GR IS IT LT NL NO PL PT RO SE) and UAIFRS (~9,600 Ukrainian IFRS filings, country UA). Pass `country` or `regime` to pin the scope you mean. Portuguese (PT), Spanish (ES) and Norwegian (NO) ESEF reports are also read directly from where each country publishes them — CMVM for Portugal, CNMV for Spain, Oslo Børs NewsWeb for Norway — so PT, ES and NO coverage follows official publication (typically within a day) rather than the index's months-long lag; each row names its `source` and those rows carry the official `published_at`. Swedish (SE) reports are likewise read from Finansinspektionen (FI), the Swedish OAM, which is the only source for Swedish FY2025 reports, Belgian (BE) reports from the FSMA's STORI database, the Belgian OAM, Maltese (MT) reports from the Malta Stock Exchange OAM, the only source for Maltese FY2025 reports, Croatian (HR) reports from HANFA's SRPI, the Croatian OAM and the only source for Croatian FY2025 reports, Hungarian (HU) reports from the MNB's Közzétételek site, the Hungarian OAM and the only source for Hungarian FY2025 reports, Lithuanian (LT) reports from oam.lt, the Lithuanian OAM run by Nasdaq Vilnius, as well as the index, Romanian (RO) reports from the ASF OAM, the only source for Romanian FY2025 reports, Cypriot (CY) reports from the Cyprus Stock Exchange public OAM, the only source for Cypriot FY2025 reports, and Latvian (LV) reports from CSRI, the Latvian OAM, the only source for Latvian FY2024 and FY2025 reports. Luxembourgish (LU), Slovenian (SI) and Estonian (EE) reports are also answered directly from the LuxSE OAM, SEOnet or the Estonian FSA's OAM for each request, because these three OAMs' terms require the operator's consent for commercial reuse of their documents beyond ordinary access; a lookup made once on a caller's behalf is not that. Greek (GR) and Irish (IE) reports are likewise answered directly from Euronext Athens and the Euronext Dublin OAM for each request — these two sites' terms forbid bots and automated access outright rather than just reuse, so these are Bruce-authorized live lookups rather than a re-derivation of the usual reasoning, kept live and never mirrored for the same reason. Bulgarian (BG) reports are answered directly from BEIS, a Bulgarian disclosure agent whose terms ask only for attribution (unlike Bulgaria's other disclosure agents, which this pack does not call) and covers only the roughly three issuers that use it. None of GR/IE/BG carry machine-readable facts (esef_filing_facts declines a live-lookup id and points at its `package_url`/`source_url`); SI is limited to the ~20 most recent Slovenian annual-report announcements; IE rows carry no `period_end` (Irish fiscal year ends vary by issuer); GR's `period_end` is inferred from the filing's reporting year, not stated exactly, and flagged `period_end_inferred`. All six (LU, SI, EE, GR, IE, BG) are pinned-country lookups only — pass `country` explicitly. Coverage of the cur
- 2026-10-20 `forget` removed
  - Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.
- 2026-10-20 `ai_visibility_check` removed
  - Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model is Workers AI Llama-3.3-70b (free); pass `_apiKey` to also probe Anthropic (BYO key — you pay Anthropic directly for those calls). Returns per-model {score, confidence, signals, raw_response} + a combined view. Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring.
- 2026-10-20 `generate_llms_txt` removed
  - Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.
- 2026-10-20 `suggest_questions` removed
  - What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).
- 2026-10-20 `pipeworx_trending` removed
  - What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.
- 2026-10-20 `research_row` removed
  - Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence — {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null — never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required — homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002) — never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value — a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem) — every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).
- 2026-10-20 `archive_compare` removed
  - What changed on a web page between two dates? Resolves the archived capture nearest each date (Internet Archive Wayback Machine, Common Crawl, Arquivo.pt), extracts the readable text of both, and returns a text-level diff: the segments removed and added, a similarity score, and both capture timestamps with their gaps from the requested dates. It diffs readable text, not markup, so a restyled page with the same words reads changed:false. Identical captures answer changed:false with the reason (same capture, identical content digest, or identical text), never an empty diff. A date with no capture within max_gap_days (default 30) answers status "no_capture", naming which side is missing and the nearest captures to it. Typical uses: how a privacy policy, terms of service, pricing or product page changed; whether a statement was on a page at a given time.
- 2026-10-20 `archive_evidence` removed
  - What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates.

Full history: https://api.protogrid.dev/v1/servers/io.github.pipeworx-io%2Fesef-filings/changes

## Remotes

- https://gateway.pipeworx.io/esef-filings/mcp (streamable-http, auth none, reachable true, uptime30d 0.9831933)

## Packages

_none_

## Tools (0)

_none observed_