memory_import_claude

Import Claude Code auto-memory files into AgentDB with ONNX vector embeddings. Reads ~/.claude/projects/*/memory/*.md files, parses YAML frontmatter, splits into sections, and stores with 384-dim embeddings for semantic search. Use allProjects=true to import from ALL Claude projects. Pass project...

Server Claude Flow claude-flow
Category Write
Risk class Medium
Parameters 00 required

What memory_import_claude does on Claude Flow

AI agents use memory_import_claude to create or update resources in Claude Flow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.

Why memory_import_claude needs a policy

This tool creates new database records (stores embeddings in AgentDB) from source files, which is a reversible modification of data. While it reads source files, its primary purpose is to persist transformed data (vector embeddings) into persistent storage. This is Write rather than Read.

From the tool's definition Reads ~/.claude/projects/*/memory/*.md files, parses YAML frontmatter, splits into sections, and stores with 384-dim embeddings; the action is 'Import...into AgentDB', creating new records in a database with derived data (embeddings).

Questions about memory_import_claude

What does the memory_import_claude tool do? +

Import Claude Code auto-memory files into AgentDB with ONNX vector embeddings. Reads ~/.claude/projects/*/memory/*.md files, parses YAML frontmatter, splits into sections, and stores with 384-dim embeddings for semantic search. Use allProjects=true to import from ALL Claude projects. Pass projectPath to override cwd-based detection (#1883 — required when Ruflo runs in WSL but Claude Code is on Windows). Pass excludeFilePatterns (glob list) or excludeFiles (absolute path list) to skip voice-load-bearing, PII, or persona-restricted files (#1937). Use when native Read/Write is wrong because you need (a) cross-session retrieval by semantic similarity (vector embeddings) not by file path, (b) namespacing across projects without managing directory layout, or (c) the .swarm/memory.db audit trail. For one-shot file I/O, native Read/Write is fine. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on memory_import_claude? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for memory_import_claude: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Flow. Nothing to install.

What risk level is memory_import_claude? +

memory_import_claude is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit memory_import_claude? +

Yes. Add a rate_limit block to the memory_import_claude rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block memory_import_claude completely? +

Set action: deny in the PolicyLayer policy for memory_import_claude. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides memory_import_claude? +

memory_import_claude is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.