bilibili-mcp
B站（Bilibili）MCP Server that exposes ~27 tools for authentication, search/collection (videos, comments, subtitles, danmaku), content posting (dynamic, video upload, opus), analytics/rankings, and messaging/interaction via MCP clients (e.g., OpenClaw, Claude Code, Cursor, Cline).
Score Breakdown
⚙ Agent Friendliness
🔒 Security
README states credentials are saved locally and not uploaded, and mentions request interval control to avoid frequency issues. However, there is no stated scope minimization, token protection model, encryption-at-rest, or guidance on securing the credential file. Security and dependency posture cannot be fully verified from the provided content.
⚡ Reliability
Best When
You want an agent-friendly local MCP tool to integrate Bilibili actions into AI workflows (especially for interactive login + content reading/analysis, and optionally posting).
Avoid When
You need formal enterprise compliance, guaranteed uptime, or you cannot securely manage local credentials/storage.
Use Cases
- • Let an AI agent log into a Bilibili account and perform account-scoped actions (search, read, post).
- • Search and collect videos plus related data (comments, replies, subtitles, danmaku) for analysis/summarization.
- • Automate content operations such as replying to comments, sending private messages, favoriting-related browsing (read-only tooling).
- • Assist creators with periodic “hot/trending/weekly” research and ranking-based discovery.
- • Publish content (dynamic/op us/video upload) with optional scheduling.
Not For
- • Use as a general-purpose public Bilibili API gateway without running the server locally.
- • Unattended, high-volume automation without verifying platform rules and rate/abuse constraints.
- • Systems that require a hosted, centrally managed service with audited uptime/SLA.
Interface
Authentication
Authentication appears to be session/credential based stored locally; the README does not describe fine-grained scopes or token lifecycle/rotation.
Pricing
Open-source (MIT) and self-hosted; runtime cost depends on your environment and Bilibili platform behavior.
Agent Metadata
Known Gotchas
- ⚠ Credential file is local; ensure it is protected and not accidentally committed.
- ⚠ Write operations (reply, private messages, publishing) should be used cautiously; retries may duplicate actions if not idempotent.
- ⚠ Rate limiting is only broadly mentioned; agents may still trigger bans/errors under heavy usage.
- ⚠ Video upload may require ffmpeg and introduces heavier operational requirements.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for bilibili-mcp.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.