{"id":"galbaz1-video-research-mcp","name":"video-research-mcp","homepage":null,"repo_url":"https://github.com/Galbaz1/video-research-mcp","category":"ai-ml","subcategories":[],"tags":["mcp","claude-code","video-analysis","deep-research","weaviate","research-citations","knowledge-graph","media-production"],"what_it_does":"video-research-mcp is a Claude Code plugin that installs and configures MCP servers to enable video understanding/analysis, deep research with evidence grading, academic/paper search and extraction, web search with citations, and an optional knowledge store (Weaviate) for persistent semantic recall. It also describes standalone MCP server usage and related explainer/video/scene-generation MCP servers.","use_cases":["Analyze local video files (e.g., meetings), extracting timestamps/decisions/action items and producing concept maps","Analyze YouTube tutorials with timestamps and sentiment/comment analysis","Run deep research workflows with evidence-tier labeling and source-grounded claims","Ingest and query past analyses via a Weaviate-backed knowledge store (semantic recall)","Analyze documents (URLs/files/directories) to extract entities/relationships and synthesize across sources","Search the web and retrieve cited results","Generate explainer video projects and media production pipelines via additional MCP servers (video-explainer-mcp / video-agent-mcp)"],"not_for":["Highly regulated environments requiring strict data residency/compliance guarantees (not evidenced in provided materials)","Environments where you cannot provide and secure multiple third-party API keys (Gemini, optional ElevenLabs/OpenAI/Weaviate/Cohere/Semantic Scholar)","Use cases requiring an officially documented public REST/GraphQL API for direct integration beyond MCP/Claude-Code workflows","Guarantees of deterministic outputs or strict SLAs for research/media generation (not documented)"],"best_when":"You want an MCP-capable agent workflow that combines video analysis + citation-grounded research and optionally persistent semantic memory using Weaviate.","avoid_when":"You need formal API contracts (OpenAPI) or strong, documented reliability/error-handling semantics at the protocol level; also avoid when secrets/data cannot be sent to external AI providers or stored in third-party services.","alternatives":["Other MCP servers or SDKs for video understanding and web research (separate tools for each capability)","Weaviate + separate RAG pipelines (custom document processing and retrieval)","Commercial all-in-one research/video automation platforms (if available)","Claude Code plugins focused solely on research or solely on media generation"],"af_score":63.2,"security_score":54.8,"reliability_score":35.0,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:35:15.433000+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":["python"],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["API keys via environment variables (GEMINI_API_KEY; optional WEAVIATE_API_KEY, COHERE_API_KEY, ELEVENLABS_API_KEY, OPENAI_API_KEY, YOUTUBE_API_KEY, S2_API_KEY)","MCP client authentication is effectively inherited from the MCP server process environment"],"oauth":false,"scopes":false,"notes":"Authentication is configured via environment variables for upstream services; no OAuth flow or explicit fine-grained scopes are described in the provided README."},"pricing":{"model":"Gemini/other upstream providers (e.g., Weaviate/Op","free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing or free tier information for the package itself is provided; costs depend on enabled third-party APIs (Gemini, ElevenLabs/OpenAI, Weaviate, etc.)."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":63.2,"security_score":54.8,"reliability_score":35.0,"mcp_server_quality":72.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":85.0,"rate_limit_clarity":35.0,"tls_enforcement":85.0,"auth_strength":55.0,"scope_granularity":20.0,"dependency_hygiene":40.0,"secret_handling":70.0,"security_notes":"Security is largely based on external provider API keys via environment variables. The README specifies environment-variable configuration but does not describe secure storage, redaction, logging behavior, or transport guarantees beyond typical HTTPS usage. No evidence of fine-grained access controls/scope granularity is provided. Multiple integrations (Gemini, Weaviate, optional providers) increase the risk surface; users should ensure keys are not logged and understand what data is sent to third parties (e.g., video uploads >20MB to Gemini File API).","uptime_documented":0.0,"version_stability":55.0,"breaking_changes_history":45.0,"error_recovery":40.0,"idempotency_support":"false","idempotency_notes":"The README describes caching and session limits, but does not explicitly state which MCP tool calls are idempotent or provide safe retry semantics.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Large local files (>20MB) are uploaded to Gemini File API for context-caching; agents may incur upload latency/cost and should avoid repeated uploads where possible.","Weaviate-backed semantic recall is optional; without configuration, recall falls back to keyword grep, which may reduce answer quality.","Some advanced capabilities depend on optional keys/services (YouTube Data API, Semantic Scholar, Cohere reranker, ElevenLabs/OpenAI/Sora, MLflow tracing).","The package relies on Claude Code plugin installation/assets plus MCP servers; integration may vary by client (Claude Code vs generic MCP client)."]}}