MCP server "content-ops" as configured in zhuangguangdahyh-dotcom/content-ops-studio. Runs ${PLUGIN_ROOT}/runtime/dist/content-ops-mcp.mjs with node. Needs 6 environment variables to run.
Convert one confirmed evidence-backed Audience painpoint into focused Xiaohongshu image-post copy, validate claims and duplication, write one Content row, and stop for version-bound G3 review.
Run final content, visual, file, and data quality checks, prepare user review, archive an approved image set, synchronize final records, and repair partial synchronization failures.
Route multi-stage content project requests across project initialization, painpoint research, content creation, visual planning, image production, finalization, and project learning while enforcing preflight checks, state transitions, and human approvals.
Synthesize per-content visual strategies from project, audience, content, assets and confirmed learning; then route six asset channels, produce candidates or formal sets, and enforce Renderer text, QA, G4, Style Lock and explicit rule governance.
Plan and complete host-mediated or manual evidence-backed Audience painpoint research for one active confirmed project, retain source and score artifacts, write pending painpoints idempotently, and stop for item-level G2 review.
Structure a new or existing client content project, prepare its local workspace contract, and plan or validate its Feishu content workspace without creating painpoints, content, or images.
Capture, classify, confirm, activate, deprecate, and compile project-level content and visual rules from user feedback without automatically modifying platform packs, industry packs, or core skills.