// MCP TOOL REFERENCE

LORE TOOLS

8 tools from the Lore MCP Server, categorised by risk level.

// ALL 8 LORE TOOLS

READ 7 tools

Read find_relevant Like search_memory, but ranked by relevance blended with recency (a fresh memory outranks Read get_context Return the neighbor messages around an anchor message_id, in order, with the anchor Read get_message Fetch a single message by message_id. Use full=true to retrieve the complete stored text Read get_session Return one logical session as a single chronological timeline, folding the primary thread Read list_sessions List sessions as rollups (message count, first/last activity, project), most-recent first. Read search_memory Keyword search across all indexed agent session transcripts, ranked by relevance (bm25). Read timeline Bucketed message activity over time (by day or hour), in chronological order. Filterable

WRITE 1 tools

Write push Ingest a batch of already-normalized records directly into the store — the universal

// FAQ

How many tools does the Lore MCP server have? +

The Lore MCP server exposes 8 tools across 2 categories: Read, Write.

How do I enforce policies on Lore tools? +

Route the Lore 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 Lore tools fall into? +

Lore tools are categorised as Read (7), Write (1). Each category has a recommended default policy.

Enforce policy on every Lore tool call.

Start from Lore, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.