// MCP TOOL REFERENCE

HMEM — HUMANLIKE MEMORY FOR AI AGENTS TOOLS

23 tools from the hmem — Humanlike Memory for AI Agents MCP Server, categorised by risk level.

View the hmem — Humanlike Memory for AI Agents policy →
// ALL 23 HMEM — HUMANLIKE MEMORY FOR AI AGENTS TOOLS
READ 7 tools
Read find_related Find entries related to the given entry. Read list_projects List all projects (P-entries) with their IDs and titles. Minimal output for checkpoint agents. Read load_project Load a project and activate it. Returns L2 content + L3 titles — the perfect project briefing. Read memory_stats Shows budget status of your memory: total entries by prefix, nodes, favorites, pinned, most-accessed, oldes... Read read_memory Read from your hierarchical long-term memory (.hmem). Read read_project Read a project Read search_memory Searches the collective memory: agent memories (lessons learned, evaluations),
WRITE 14 tools
Write append_memory Append new child nodes to an existing memory entry or node (your own personal memory). Write create_project Create a new project with the standard R0009 schema. Automatically creates:\n Write export_memory Export your memory, excluding secret entries and secret sub-nodes. Write flush_context Store a conversation chunk as linear context history (O-prefix). Write import_memory Import entries from a .hmem file into your memory. Write memory_health Audit report for your memory: broken links (links pointing to deleted entries), Write move_memory Move a sub-node (and its entire subtree) to a different parent, updating all ID references. Write move_nodes Move session (L2), batch (L3), or exchange (L4) nodes between O-entries. Handles ID rewriting, tag migratio... Write rename_id Atomically rename an entry ID and update ALL references across the database. Write set_active_device Set the active device for this machine. Call this once after identifying which machine you are on. Write tag_rename Rename a hashtag across all entries and nodes. Write update_many Batch-update multiple memory entries at once. Applies the same flag(s) to all listed IDs. Write update_memory Update the text of an existing memory entry or sub-node (your own personal memory). Write write_memory Write a new memory entry to your hierarchical long-term memory (.hmem).
DESTRUCTIVE 2 tools
Destructive reset_memory_cache Clear the session cache of the hmem server so all entries are treated as unseen again. Destructive tag_bulk Apply tag changes (add and/or remove) to all entries matching a filter.
// RUNNING THIS SERVER

The managed route: connect hmem — Humanlike Memory for AI Agents through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y hmem-mcp
// FAQ
How many tools does the hmem — Humanlike Memory for AI Agents MCP server have? +

The hmem — Humanlike Memory for AI Agents MCP server exposes 23 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on hmem — Humanlike Memory for AI Agents tools? +

Route the hmem — Humanlike Memory for AI Agents server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do hmem — Humanlike Memory for AI Agents tools fall into? +

hmem — Humanlike Memory for AI Agents tools are categorised as Read (7), Write (14), Destructive (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.