Open-data ontology MCP: a semantic concept layer over multi-datasource financial/economic data
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"fd-open-data-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# fd-open-data-mcp > **Wire (柏讯) product line** · the open-data supply line of [FindData](https://www.finddatatech.cloud/products/wire) — 柏讯线开源核心：开放数据本体与语义供给。 **English** | [中文](README.zh-CN.md) An **open-data ontology MCP**: a semantic concept layer over multi-datasource financial/economic data. You ask for data by **concept + entity** (e.g. "price.close of Moutai", "GDP of China"); the system resolves concepts to physical columns in each source, ranks candidate sources by quality and reachability, fetches from the best one (with failover), caches per concept, and refreshes on a per-concept schedule. It consumes finddata's `fd-*` datasource registry and `fd-entities-indicators` **read-only**, and adds the unified layer on top. ## One-command install A single self-contained block that bootstraps the whole finddata open-data stack (hub + all datasource packages + the ontology database). Re-runnable; stops at the first error. ```bash # 1) Install the full stack from PyPI. # fd-open-data-protocol comes in transitively; fd-polygon and fd-cn-report # self-register via entry points. Drop "[data]" for a light install (MCP # server + CLI only, no akshare/yfinance SDKs). "[data]" excludes the # browser-rendering stack; add it via "[data,browser]" when # scrapling/playwright is needed. pip install "fd-open-data-mcp[data]" fd-polygon fd-cn-report # 2) Initialize the ontology DB and wire every layer: catalog -> concepts # -> column bindings -> per-source entity ids -> refresh schedules # -> manifest. fd-open-data-mcp migrate \ && fd-open-data-mcp import-catalog \ && fd-open-data-mcp consume-concepts \ && fd-open-data-mcp propose-bindings \ && fd-open-data-mcp seed-entities \ && fd-open-data-mcp generate-schedules \ && fd-open-data-mcp register-discovered # 3) Start the MCP server (stdio transport, for any MCP client). fd-open-data-mcp serve ``` Real-data fetching needs datasource keys in the environment (never commit them): `POLYGON_A…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.