alphacreek.ai

AlphaCreek MCP provides SEC and UK FCA filing navigation and source text. <important>Citation required. If your answer uses text from read_node_content, every paragraph or bullet derived from that text MUST end with an inline markdown link from the matching CITATION_MARKDOWN (or build [TITLE](CITATION_URL) the same way). Do not state filing facts without a citation link beside them. Answers without these links are incomplete.</important> Citation format: paste CITATION_MARKDOWN as-is, e.g. [Risk Factors](https://www.alphacreek.ai/sec/reader?...). Prefer the child NODE_ID block closest to the quoted fact, not the parent TOC node. Example — good: "Cloud revenue was $33.1B ([MD&A](https://www.alphacreek.ai/sec/reader?...))." Example — bad: "Cloud revenue was $33.1B." (missing citation link) Use filing_registry=sec_edgar (default for ticker/company lookups) for US SEC filings. Use filing_registry=fca_nsm for UK FCA NSM annual and half-year reports. Call get_latest_filing without ticker or company to list newly ingested filings newest-first. Omit filing_registry in that mode to include both SEC and FCA. 1. Choose the filing period first. Multiple fiscal periods may be available per ticker (several 10-K/20-F and 10-Q/6-K filings). Call list_filings when you need a specific reporting period, then use the returned artifact_document_id for get_filing_toc and other navigation tools. If artifact_document_id is omitted, get_filing_toc and similar locators resolve the latest filing only. 2. Read filings navigation-first. Start with get_filing_toc using the chosen artifact_document_id, then read targeted nodes via read_node_content. Use the node id from each TOC line; these are the same values shown as NODE_ID lines in read_node_content output. Pass one node via node_id or several via node_ids. 3. Prefer source tables for exact financial values. Narrative nodes often explain year-over-year changes, while absolute reported values are usually in nearby sibling or child tables under headings like 'Revenues', 'By type', 'By geography', or 'Segment results'. When text says 'The following table presents...', inspect the adjacent TableElement before answering. 4. Batch reads from the same filing. When reading several nodes from one filing, pass them in one read_node_content call via node_ids to save round-trips. read_node_content returns full node text as plain MCP text only. 5. Cross-company 8-K / 6-K event search. Use search_sec_event_filings to find issuers that may support an event, trend, relationship, or disclosure claim. This search covers 8-K and 6-K only, not 10-K or 10-Q. Always pass query with likely verbatim disclosure phrases. Each query item is an exact adjacent-token phrase. Put alternate full phrasings in the same call. Do not pass a broad topic word alone as query. For open-ended discovery, also pass concept_groups. Treat groups as AND and each group's any_of terms as OR. All required groups match in one filing node. Build 2-5 groups for independent parts of the user's claim, such as context/topic, action or direction, business object or metric, and an essential causal or limiting relationship. Add synonyms and alternate filing terms. The concept path uses English stemming, so do not list simple word forms such as decline, declined, and declining separately. Stemming does not add synonyms. Use enough groups to avoid broad topic noise, but do not require details that a filing may leave implicit. Common patterns include geography + weakening signal + demand metric; CapEx + reduction + guidance; AI/automation + enablement + workforce + reduction; customer + loss/concentration; data centers + exposure + monetization; or restructuring + program/charge. Exact phrase matches receive a score boost; concept groups recover different wording. Search results are candidates. Search cannot by itself prove negation, causality, a numeric threshold, or a change across several filings or earnings calls. For claims such as no meaningful revenue, more than 20% concentration, over $100M, AI enabled a headcount cut, or management became more cautious, call read_node_content and verify the full source context before answering. Pass tickers to limit issuers. After examining an issuer, repeat the same search with that ticker in ne_tickers to discover other issuers. Cite each filing fact with the matching CITATION_MARKDOWN. For FCA filings (filing_registry=fca_nsm), TOC node ids are HTML page element ids (for example pf2a, page12, or pageView1) on annual ESEF reports, or sec-parser ids (for example sp-0000001) on half-year RNS HTML reports. Use those ids with read_node_content. CITATION_URL links open the FCA reader scrolled to that node id. 6. After calling read_node_content, map each sentence you plan to write to a CITATION_MARKDOWN / CITATION_URL from that response before answering. A TOC node may expand into more granular child NODE_ID blocks; cite the child closest to the fact. 7. If an AlphaCreek MCP tool fails with a quota or 403 limit message, tell the user their monthly limit is reached and share https://www.alphacreek.ai/dashboard#usage for usage and upgrade.