Chronicle MCP
If you're accumulating ChatGPT or Claude export files and want to query them without manually pasting logs into your context window, Chronicle normalizes those archives into searchable JSON and lets you pull specific message ranges on demand. It parses ChatGPT's recursive node structures and Claude's flat message lists into a standard format, then exposes 27 tools including keyword search, pagination, and range reads. The real hook is the token optimization: code blocks get collapsed into metadata summaries and long messages truncate automatically, cutting context usage by up to 40%. The CLI handles cross-platform IDE config for Cursor, Cline, and Claude Desktop, and includes a split subcommand to break monolithic conversation dumps into individual threads. Useful when you want past conversations indexed locally instead of retyped.
- GitHub stars
- 3
- tools
- 8
- transport
- STDIO
- env vars
- 2
- last updated
- Oct 25, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
search_historyUnified search and filter interface for local chat transcripts. Supports keyword, Okapi BM25 semantic, date range, and related chat lookups.
Unified search and filter interface for local chat transcripts. Supports keyword, Okapi BM25 semantic, date range, and related chat lookups.
No parameter schema in public metadata yet.
get_chat_logsUnified read interface for stored transcripts. Fetches paginated file lists, summaries, file metadata, or message ranges with token-saving options.
Unified read interface for stored transcripts. Fetches paginated file lists, summaries, file metadata, or message ranges with token-saving options.
No parameter schema in public metadata yet.
get_handoff_statusReturns the current workspace handoff state: the active chain of receipts, whether the workspace is blocked, and the next safe action.
Returns the current workspace handoff state: the active chain of receipts, whether the workspace is blocked, and the next safe action.
No parameter schema in public metadata yet.
sync_workspace_dataIngests, imports, and syncs external conversation transcripts or workspace logs from various tools and formats.
Ingests, imports, and syncs external conversation transcripts or workspace logs from various tools and formats.
No parameter schema in public metadata yet.
compile_project_insightsAggregates and compiles insights from chat logs, including action item extraction, index indexing, chat comparisons, and brief generation.
Aggregates and compiles insights from chat logs, including action item extraction, index indexing, chat comparisons, and brief generation.
No parameter schema in public metadata yet.
save_handoff_receiptSaves a structured handoff receipt that documents the current run's state so the next agent can continue safely.
Saves a structured handoff receipt that documents the current run's state so the next agent can continue safely.
No parameter schema in public metadata yet.
maintain_storagePerforms server operations, storage cleanups, settings configuration, and capabilities lookup.
Performs server operations, storage cleanups, settings configuration, and capabilities lookup.
No parameter schema in public metadata yet.
manage_session_stateManages active session caching, folder monitoring, file merges, markdown exports, and file deletions.
Manages active session caching, folder monitoring, file merges, markdown exports, and file deletions.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
CHRONICLE_BASE_DIRFolder for the chat archive and search index. Defaults to ~/.chronicle (or the folder saved with chronicle --chats-folder).
TRANSCRIPTS_DIROverride folder scanned by sync_workspace_data(source_type='agent_transcripts'). Defaults to each editor's own transcript folder.
Readme
Chronicle MCP: Local AI Chat History Search & Memory
Private, offline memory for your AI coding agents. Chronicle MCP (chronicle-mcp-server) is a local stdio MCP server that indexes your Cursor, Claude, ChatGPT and Cline chat transcripts on your own machine and serves BM25 search over them, so agents can recall past conversations without re-pasting them, using up to 40% fewer context tokens. Your archive and index stay on disk: no cloud service, account, or API key.
Details
- Repository
- github.com/leviathan0x0/chronicle-mcp
- Website
- github.com/Leviathan0x0/Chronicle-MCP
- Categories
- AI & LLM Tools, Communication & Messaging, Search & Web Crawling
- Package
chronicle-mcp-server- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Blogburst Mcp Servershensi8312/blogburst-mcp-serverAI social media agent — generate content, auto-pilot posting, analytics for 9+ platforms.3stars
Guardianshieldsparkvibe-io/guardianshieldAI security layer: code scanning, PII detection, prompt injection, secrets, CVEs3stars
Mcpwireboard/mcpOfficial MCP server for WireBoard. Lets LLM agents query your analytics in conversation.0stars
Draw2agentzero-abd/draw2agentDraw on your website, let your AI agent see it. Visual context for code generation via MCP.3stars
Mcpcueapi/cueapi-mcpSchedule agent work and report write-once outcomes via CueAPI from any MCP host.2stars
Afterpathsburnssa/afterpathsSession memory for AI coding agents. Search past sessions, extract rules, and track what works.2stars