Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by cyberchitta • Uncategorized
An MCP server providing intelligent, rule-based context management for LLM development workflows.
Focused, task-specific project context to improve LLM interactions.
Dynamically fetch additional project files during conversations without manual intervention.
Validate and preview context rules before generating context.
LLM Context enables smart selection and sharing of relevant project files to optimize context in LLM conversations. It supports human workflows via clipboard tools, AI agents via CLI and MCP interfaces, and integrates with Claude Desktop for seamless AI-assisted rule creation and context provisioning. The system uses composable YAML+Markdown rules to define task-specific contexts, improving efficiency and reducing token usage while enabling dynamic file fetching during conversations.
Returns list of files modified since given timestamp. Args: root_path: Root directory path (e.g. '/home/user/projects/myproject') timestamp: Unix timestamp to check modifications since
Returns excerpted content highlighting important sections in all supported files. Args: root_path: Root directory path rule_name: Rule to use for file selection rules
Provides step-by-step instructions for creating custom rules. Args: root_path: Root directory path
Preview what files a rule selects and their sizes. Args: root_path: Root directory path (e.g. '/home/user/projects/myproject') rule_name: Name of the rule to preview (e.g. 'prm-code', 'tmp-prm-auth-jwt')
Unified tool for retrieving missing context (files, implementations, or excluded sections). Args: root_path: Root directory path (e.g. '/home/user/projects/myproject') param_type: Type of data - 'f' for files, 'i' for implementations, 'e' for excluded sections data: JSON string containing the data (file paths in /{project-name}/ format or implementation queries) timestamp: Context generation timestamp
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.