MCP Tools

These are available to MCP clients through the server.

Core Operations

snap

snap(user_prompt: str, original_response: str, agent_plan: list[str], files_changed: str)

Record every user interaction with automatic file tracking. Handles untracked vs modified files intelligently.

mem_ui

mem_ui(port: int = 38888)

Launch the Web UI at http://localhost:38888 to visually browse history, view diffs, and jump to any snapshot.

mem_history

mem_history(limit: int = 20, commit_hash: str = "")

View memov history with prompts, responses, and file changes.

mem_jump

mem_jump(commit_hash: str)

Jump to a specific snapshot, restoring all tracked files and creating a new branch.

RAG Tools

These tools require [rag] extras installation.

Installation with RAG

Claude Code:

claude mcp add mem-mcp --scope project -- uvx --from "git+https://github.com/memovai/memov.git[rag]" mem-mcp-launcher stdio $(pwd)

VS Code / Cursor: Change the --from argument to:

"git+https://github.com/memovai/memov.git[rag]"

mem_sync

mem_sync()

Sync all pending operations to VectorDB for semantic search capabilities.

validate_commit

validate_commit(commit_hash: str, detailed: bool = True)

Validate a specific commit by comparing prompt/response with actual code changes. Detects context drift and alignment issues.

validate_recent

validate_recent(n: int = 5)

Validate the N most recent commits for alignment patterns. Useful for session reviews and quality assurance.

vibe_debug

vibe_debug(query: str, error_message: str = "", stack_trace: str = "", user_logs: str = "", models: str = "", n_results: int = 5)

Debug issues using RAG search + multi-model LLM comparison. Searches code history for relevant context and queries multiple AI models (GPT-4, Claude, Gemini) in parallel for diverse debugging insights.

vibe_search

vibe_search(query: str, n_results: int = 5, content_type: str = "")

Fast semantic search through code history (prompts, responses, agent plans, code changes) without LLM analysis. Perfect for quick context lookup.

Health Check

GET /health

Returns "OK". Useful for IDE/agent readiness checks.

Architecture