Claude Infinite Context
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level for verbose output (e.g., DEBUG for detailed logs) | |
| REDIS_URL | No | Redis connection URL | redis://localhost:6379 |
| GEMINI_MODEL | No | The Gemini model to use for state merging. Available models: gemini-3-pro-preview (latest), gemini-2.5-pro (stable), gemini-2.5-flash (fast) | gemini-3-pro-preview |
| PROJECT_ROOT | No | The project root directory. Use ${workspaceFolder} to automatically resolve to your current project directory | |
| GEMINI_API_KEY | Yes | Your Google Gemini API key (required for AI-powered state merging). Get from https://aistudio.google.com/apikey | |
| ANTHROPIC_API_KEY | No | Your Anthropic API key (optional - used as fallback if Gemini fails). Get from https://console.anthropic.com/ |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| checkpointA | Save current context to Redis before running /clear. Merges new context with existing project state using LLM-based summarization. |
| resumeB | Load the last checkpoint at session start. Returns formatted context to inject into the conversation. |
| rollbackB | Revert to a previous checkpoint version. Useful if a merge produced incorrect results. |
| statusA | Show current state metadata including version, active files, tasks, token usage, and checkpoint history. |
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 4 tools
Each tool has a clearly distinct purpose: checkpoint saves context, resume loads it, rollback reverts to a previous version, and status shows metadata. There is no overlap or ambiguity between these operations, making tool selection straightforward for an agent.
All tool names follow a consistent, simple verb-based pattern (checkpoint, resume, rollback, status) without any mixing of conventions like snake_case or camelCase. This uniformity enhances readability and predictability across the tool set.
With 4 tools, the server is well-scoped for managing context checkpoints in a session. Each tool serves a specific, essential function in the lifecycle (save, load, revert, inspect), and there are no extraneous or missing tools for this focused purpose.
The tool set provides complete coverage for the context management domain: checkpoint (create), resume (read), rollback (update/revert), and status (monitor). There are no obvious gaps, as all core operations for saving, restoring, and tracking context states are included.