node804-claude-code-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAUDE_DIR | No | Override the Claude Code data directory | ~/.claude |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| server_statusA | Show the current server configuration. Returns the version, the resolved Claude Code data directory, and the number of projects found. |
| list_claude_projectsA | List all Claude Code projects in the local session store. Reads from |
| list_claude_sessionsA | List Claude Code sessions, optionally filtered to a single project. Args: project_slug: The project slug (as returned by list_claude_projects). Leave empty to list sessions across all projects. limit: Maximum number of sessions to return. Defaults to 20. |
| get_claude_sessionA | Get the full conversation transcript from a Claude Code session. Returns user and assistant messages in order, with timestamps and tool call names. Internal thinking blocks are excluded unless include_thinking is set. Args: session_id: The session UUID (as returned by list_claude_sessions). project_slug: The project the session belongs to. include_thinking: Include assistant thinking blocks. Defaults to False. |
| get_claude_session_statsA | Get token usage, timing, and message counts for a Claude Code session. Returns input/output token totals, cache read tokens, duration in minutes, models used, and the working directory the session was run from. Args: session_id: The session UUID. project_slug: The project the session belongs to. |
| search_claude_sessionsA | Search for text across Claude Code session messages. Case-insensitive full-text search over all user and assistant messages. Returns matching snippets with surrounding context, session IDs, and timestamps. Args: query: Text to search for. project_slug: Limit search to a single project. Leave empty to search all projects. limit: Maximum number of hits to return. Defaults to 20. |
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 6 tools
Each tool targets a unique aspect: server_status for config, list_claude_projects for projects, list_claude_sessions for sessions, search_claude_sessions for full-text search, get_claude_session for transcripts, and get_claude_session_stats for metrics. There is no functional overlap.
Most tools follow a verb_noun pattern (list_claude_projects, list_claude_sessions, search_claude_sessions, get_claude_session, get_claude_session_stats). server_status is a slight deviation (noun_noun) but still clear and readable.
6 tools is well-scoped for a Claude Code session server. It covers listing, searching, retrieving details, and stats without being bloated or insufficient.
The tool surface covers core read operations for projects and sessions, including search and statistics. No obvious missing functionality for inspection, though write/delete operations are absent by design (sessions are managed externally).