{"id":"kevinwatt-ffmpeg-mcp-lite","name":"ffmpeg-mcp-lite","homepage":"https://pypi.org/project/ffmpeg-mcp-lite/","repo_url":"https://github.com/kevinwatt/ffmpeg-mcp-lite","category":"ai-ml","subcategories":[],"tags":["mcp","ffmpeg","video","audio","subtitles","media-processing","python","claude","model-context-protocol"],"what_it_does":"ffmpeg-mcp-lite is an MCP server that exposes FFmpeg-based media tools to AI clients (e.g., Claude/Dive). It can get media metadata, convert formats, compress, trim, extract audio, extract frames, merge videos, and burn in subtitles.","use_cases":["Converting videos/audio into common formats (mp4/mkv/webm/mov, mp3/aac/wav/flac/ogg/opus)","Compressing or encoding with quality/preset controls","Trimming clips by timestamps/duration","Extracting audio tracks from a source video","Extracting frames as images for review or processing","Burning subtitles into video using SRT/ASS/VTT styles","Concatenating/merging multiple videos"],"not_for":["Serving as a secure, multi-tenant remote media processing service without additional isolation (it runs locally as a subprocess-based MCP server)","Workloads requiring strict uptime/SLA or managed hosting guarantees","APIs requiring documented rate limits, pagination, or webhooks"],"best_when":"You need local/desktop integration of FFmpeg capabilities into an MCP-capable AI workflow and you can supply input files and manage FFmpeg/ffprobe binaries on your system.","avoid_when":"You need authenticated, network-accessible APIs with clear enterprise security controls, or you cannot install/run FFmpeg and an MCP server process.","alternatives":["Local CLI usage of ffmpeg/ffprobe directly (scripts/wrappers)","Other MCP servers or SDKs that wrap ffmpeg for media pipelines","Workflow tools like HandBrake/MediaConvert (where applicable) for simpler conversion tasks"],"af_score":59.8,"security_score":22.2,"reliability_score":26.2,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:33:00.816526+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":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["None explicitly documented (local MCP server invoked via client config)"],"oauth":false,"scopes":false,"notes":"Authentication/authorization are not described in the README. Tools execute FFmpeg locally via the MCP server process, so access control is primarily determined by the host environment and the MCP client’s local trust model."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information is provided; appears to be a self-hosted/local tool."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":59.8,"security_score":22.2,"reliability_score":26.2,"mcp_server_quality":78.0,"documentation_accuracy":65.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":0.0,"tls_enforcement":0.0,"auth_strength":20.0,"scope_granularity":0.0,"dependency_hygiene":35.0,"secret_handling":60.0,"security_notes":"No network/API auth model is documented; the server runs locally and executes external ffmpeg/ffprobe binaries. This shifts risk to input validation (paths/arguments), filesystem permissions, and process isolation. TLS and rate limiting are not applicable/not documented because it is an MCP/local subprocess integration. Dependency hygiene is not verifiable from the provided data beyond mcp>=1.0.0 and lack of further security detail.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":30.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":"Operations are FFmpeg actions that likely write output files; idempotency (safe retries without duplicates/overwrites) is not explicitly documented.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Relies on local ffmpeg/ffprobe binaries (may fail if missing or misconfigured).","Media processing can be resource intensive (CPU/disk) and may be slow for large files.","Outputs may overwrite existing files depending on how output paths are handled (not documented).","Time parsing (timestamps vs seconds) is described but not formally specified; agents may mis-specify time formats."]}}