What it does
The server scores the sentiment of documents through eight tools organised into five groups. Each result must include evidence_spans, and every quote must be an exact, word-for-word substring of the source text, so scores can be traced back to passages in the document.
It suits workflows where sentiment results need to be checked against the exact wording they came from. Results are idempotent, keyed on doc_id and further fields that the source description does not finish listing.
The tools are described as commercial. The source does not describe setup steps, supported clients or runtime requirements.
Limitations and requirements
The tools are described as commercial, so use may require a paid licence; the source gives no pricing or access terms. The publisher description is incomplete and cut off, so the idempotency key and other details are not fully specified.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.FindDataTechnology/fd-sentiment
柏讯文档情绪打分 MCP:8 工具/5 组全 commercial。evidence_spans 必填且 quote 为原文逐字子串;幂等键 (doc_id, co… — 想 7×24 常驻 → 萬星
v0.0.1As shown on registry.modelcontextprotocol.io when we last read it