ClaudeHistoryMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAUDE_HISTORY_API_KEY | No | API key for cloud sync authentication | |
| CLAUDE_HISTORY_API_URL | No | URL of the ClaudeHistory Cloud server for cloud sync | |
| CLAUDE_HISTORY_TEAM_ID | No | Optional team UUID for team sync |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_historyA | Search past Claude Code conversations. Supports filter syntax: project:name, before:date, after:date, tool:name. Dates can be relative (7d, 30d, 1w) or ISO (2024-01-15). |
| list_projectsA | List all projects that have Claude Code conversation history, with session counts and activity dates. |
| find_solutionsA | Search past conversations for solutions to errors or problems. Prioritizes results containing fix/resolution language. |
| get_session_summaryA | Get a structured summary of a conversation session. Provide either a session ID or project name (returns most recent session). |
| get_project_contextA | Get comprehensive context for a project: recent sessions, key topics, common tools, and patterns. Useful for session-start context injection. |
| find_patternsA | Discover recurring patterns in conversation history: common topics, frequent workflows, repeated issues. |
| cloud_sync_statusA | Check cloud sync configuration and connection status. Shows whether sync is configured, last sync times, and connection health. |
| cloud_sync_pushA | Push local knowledge entries and session summaries to the cloud server. Only pushes entries newer than the last sync. |
| cloud_sync_pullA | Pull knowledge entries and session summaries from the cloud server. Merges with local data without duplicates. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have clearly distinct purposes: search_history queries conversations broadly, find_solutions zeroes in on fixes, find_patterns aggregates trends, and get_session_summary/get_project_context serve different retrieval needs. The main potential confusion is between search_history and find_solutions, but descriptions and result prioritization mitigate it.
All tool names follow a consistent verb_noun pattern (search_history, list_projects, get_session_summary), with cloud_sync_* as a clear module prefix for push/pull/status. The naming is uniform and predictable.
Nine tools is well within the ideal 3-15 range, and each tool addresses a distinct aspect of conversation history management (search, summary, context, patterns, sync). The count feels neither sparse nor bloated for the server's scope.
The toolset covers core workflows: searching history, retrieving summaries, building project context, detecting patterns, and cloud sync with push/pull/status. Minor gaps exist—such as no tool for deleting or explicitly exporting history—but these are likely outside the primary purpose and easily worked around.