Der Tw Market Data MCP-Server,
verbunden mit einem Klick.

“Nutze „list_datasets“: List available Taiwan-market datasets (discovery entry point). Returns id / 中文名 / category / tier / one-line description for each. Use t.”

“Nutze „describe_dataset“: FULL semantics of one dataset: grain (what a row is), field meanings+units, ★TIME-CORRECTNESS rules (knowledge_time_field / point_in_tim.”

“Nutze „query_dataset“: Query rows with built-in look-ahead protection. ★ POINT-IN-TIME: pass `as_of` (YYYY-MM-DD) for backtesting/agent-learning. For non-poin.”

“Nutze „find_related“: Traverse the knowledge graph for cross-table / supply-chain reasoning. - dataset_id: returns join-able datasets (+why) to plan multi-tab.”

list_datasets — List available Taiwan-market datasets (discovery entry point). Returns id / 中文名 / category / tier / one-line description for each. Use t

describe_dataset — FULL semantics of one dataset: grain (what a row is), field meanings+units, ★TIME-CORRECTNESS rules (knowledge_time_field / point_in_tim

query_dataset — Query rows with built-in look-ahead protection. ★ POINT-IN-TIME: pass `as_of` (YYYY-MM-DD) for backtesting/agent-learning. For non-poin

find_related — Traverse the knowledge graph for cross-table / supply-chain reasoning. - dataset_id: returns join-able datasets (+why) to plan multi-tab

search_filings — Semantic search over MOPS filings, financial-statement notes and company news. Answers questions a keyword filter cannot: "what risks d

explain_provenance — Where did this number come from, and when could anyone have known it? (WP-6) ★ THIS IS THE GROUNDING TOOL. Every other tool's answer is

get_inclusion_proof — Prove a row was in the snapshot TWMD published — and check it yourself. Returns the Merkle sibling path, the signed root, and the check

cite_this — Produce a bibliographic citation for TWMD data — APA, BibTeX, and a re-verifiable token. ★ FOR PAPERS, REGULATORY FILINGS AND ANYTHING