Pawsift MCP Server

Most monitoring and observability work still happens through a UI a human drives. Pawsift MCP MCP server moves it into the conversation instead. Downloads the right binary for your OS and architecture, installs it to ~/.local/bin/pawsift (or %USERPROFILE%\.local\bin\pawsift.exe on Windows), and automatically registers the server in your Gemini CLI and Claude Code (CLI).

The short version

• High-Throughput Processing — Regex-free manual string parser and hash-based dedup (using hash/maphash) for hot-path log processing at 5,000+ logs/sec
• Zero-Touch Session Tracking — Automatically detects app restarts via ActivityManager and rotates sessions
• Token Efficient — Pre-aggregates errors, folds repetitive consecutive logs, and uses Hierarchical Mapping to group identical messages under sub-headers
• Surgical Querying — Filter logs by level, tag, and search terms with strict line limits to protect the context window
• Tag Discovery — Quickly list all active tags in the current session
• Contextual Windows — Fetch logs surrounding a specific event for precise debugging

The tools it exposes

The server publishes 10 tools. What each one is for:

• pawsift_set_target_package — Configures the watcher to monitor a specific Android application. When this package starts, the session ID is automatically rotated to isolate new
• pawsift_get_status — Returns the current status dashboard: target package, session ID, watcher activity, connected device, and current log count
• pawsift_get_error_summary — Returns a count-first Markdown list of unique ERROR and FATAL logs with their latest [ID]. Use the ID for surgical context retrieval
• pawsift_get_tag_summary — Returns a count-first Markdown list of all unique log tags in the current session
• pawsift_query_logs — Retrieves filtered logs (by level and/or tag) using Hierarchical Mapping. Supports folding of consecutive identical messages
• pawsift_get_log_context — Retrieves lines surrounding a specific log ID. Essential for seeing what led up to a crash or event
• pawsift_search_logs — Performs a global search across the entire log history using Hierarchical Mapping
• pawsift_clear_logs — Permanently deletes all logs from the database and clears the Android device logcat buffer
• pawsift_set_retention_policy — Configure retention limits: maximum total logs, maximum sessions to keep, and cleanup interval in seconds
• Folding — When fold=true (the default in pawsift_query_logs and pawsift_search_logs), consecutive identical log messages are collapsed into a single entry

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Pawsift MCP's toolset — pawsift_set_target_package, pawsift_get_status, pawsift_get_error_summary and 7 more — is a fair guide to whether it matches your workflow. It is maintained by dolphprefect; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pawsift MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Pawsift MCP.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.