MCP.Market

Lore MCP server

by agentkitai·io.github.agentkitai/lore·v1.4.2·8 stars
No reviews yet

Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

8 stars37 downloads/wk

Reviews

Write one

Nobody has reviewed Lore yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Lore tools (46, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_conversation

    Accept raw conversation and extract memories.

  • as_prompt

    Export memories formatted for LLM context injection. Set verbatim=true for raw original content.

  • check_freshness

    Check memory freshness against git history.

  • classify

    Classify text without storing it.

  • conflicts

    List recent conflicts.

  • consolidate

    Trigger memory consolidation.

  • consolidate_memorieswrite action

    Create a new memory + supersede sources atomically. Returns JSON.

  • demote_memory

    Unshare a memory (make it private again).

  • downvote_memory

    Downvote a memory to lower its ranking.

  • enrich

    Enrich memories with LLM-extracted metadata.

  • entity_map

    List entities in the knowledge graph.

  • export

    Export memories and knowledge graph.

  • extract_facts

    Extract facts from text, return formatted list.

  • fact_supersession_chain

    Audit trail for a fact's supersessions.

  • facts_at_time

    Subject–predicate–object facts about ``entity`` valid at ``at``.

  • forgetwrite action

    Delete a memory from Lore.

  • get_memories

    Fetch full StoredMemory payloads by id.

  • github_sync

    Sync GitHub repo data into Lore memories.

  • graph_query

    Traverse the knowledge graph from a given entity.

  • ingest

    Ingest content with source tracking.

  • list_at_time

    Memories valid (non-superseded) at a given timestamp.

  • list_facts

    List active facts.

  • list_memories

    List memories in Lore.

  • on_this_day

    Retrieve memories from this month+day across all years.

  • promote_memory

    Share a private memory with the team.

  • provenance

    Full provenance for a memory.

  • recall

    Search Lore memory for relevant memories. Set verbatim=true for raw original content.

  • recent_activity

    Get recent memory activity grouped by project.

  • related

    Find related memories and entities by memory ID or entity name.

  • remember

    Store a memory in Lore.

  • remember_observation

    Save a structured observation. Returns a confirmation with the memory ID.

  • review_connection

    Approve or reject a pending connection.

  • review_digest

    Get pending connections for conversational review.

  • save_snapshot

    Save a session snapshot to preserve important context before it is lost.

  • search

    Return a compact JSON index of relevant memories.

  • snapshotwrite action

    Create a quick snapshot backup.

  • snapshot_list

    List available snapshots.

  • stats

    Return memory statistics.

  • suggest

    Get proactive memory suggestions based on current session context.

  • supersede

    Record a supersession event.

  • supersede_fact

    Supersede-not-delete a fact edge.

  • supersession_chain

    Audit trail for a memory's supersessions.

  • timeline

    Fetch chronologically adjacent events around an anchor.

  • topic_detail

    Get everything Lore knows about a topic — linked memories, related entities, timeline.

  • topics

    List auto-detected topics — recurring concepts across multiple memories.

  • upvote_memory

    Upvote a memory to boost its ranking.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan277 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 7 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Lore compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
Tools
46
the typical AI and agents server has 6
Tools that change things
7%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
8
more than 82% of 2,711 AI and agents servers
Downloads a week
37
more than 28% of 1,538 AI and agents servers with a package

What its tools let an agent do: 41 read · 2 create · 3 change

Install Lore in Claude Code, Cursor or VS Code

claude mcp add lore -- uvx lore-sdk
Add to Cursor

What the publisher says

From the Lore repository's README, as published. We do not edit it. Read it on GitHub

Lore — Universal AI Memory Layer

<!-- mcp-name: io.github.agentkitai/lore -->

Your AI agents remember everything. Automatically.

Lore is a cross-agent memory system that stores, connects, and retrieves knowledge across any AI agent — without code changes. Install a hook, and relevant memories appear in every prompt. No agent cooperation needed.

User: "What API rate limits should I use?"

── Lore hook fires (20ms) ──────────────────────────────
🧠 Relevant memories from Lore:
- [0.82] Stripe API returns 429 after 100 req/min — use exponential backoff
- [0.71] Our internal API rate limit is 500 req/min per API key
────────────────────────────────────────────────────────

Agent sees memories + prompt → responds with full context

Features

Universal Memory

remember · recall · forget · list_memories · stats

Store and retrieve memories across any AI agent via MCP tools, REST API, or Python/TypeScript SDK. Semantic search with tier-based TTL, temporal decay, and automatic PII redaction.

Knowledge Graph

graphquery · entitymap · related · extractfacts · listfacts · conflicts

Entities and relationships auto-extracted from memories. Hop-by-hop graph traversal surfaces connected knowledge that pure vector search misses. Atomic fact extraction with automatic conflict detection.

Bi-Temporal Facts & Supersession

supersede · listattime · factsattime · timeline · provenance · supersessionchain · consolidatememories

History without deletion. Memories and facts are corrected by superseding them, never deleting — every change appends to an auditable trail. Lore tracks two independent time axes (bi-temporal): valid-time (when a fact was true in the world) and system-time (when Lore learned it), so you can ask "what was canonical — or true about X — as of date Y?". listattime / factsattime answer as-of queries, timeline walks chronologically adjacent events, and provenance / supersession_chain expose the full correction lineage for a memory or fact.

Graph Visualization

Web UI at /ui/

Interactive D3 force-directed graph of your knowledge base. Entity detail panels, topic clusters, search, and filtering. Runs in the browser — no install required.

Session Continuity

Auto-snapshot + auto-inject — zero agent cooperation

The Session Accumulator automatically captures conversation context and injects relevant session history into every prompt. Deterministic (no LLM needed). Works via hooks — the agent never knows Lore exists.

Recent Activity

recent_activity

Session-aware summary of what happened recently across all projects. Gives agents continuity between conversations without manual context-passing.

Topic Notes

topics · topic_detail

Auto-generated concept hubs that cluster related memories, entities, and facts around recurring themes. See everything Lore knows about a topic in one view.

Export & Snapshot

export · snapshot · snapshotlist · savesnapshot

Full data export in JSON and Markdown formats. Obsidian-compatible output for browsing your knowledge graph in a PKM tool. Snapshots for backup and migration.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Lore: common questions

Is Lore MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Lore safety report
How do I install Lore?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Lore need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Lore maintained?
The last commit was 45 days ago (2026-09-20). The latest release is v1.4.2.
What can I use instead of Lore?
Servers from other publishers that do the same job: Total Agent Memory MCP server, Agent Comms MCP server and Basic Memory MCP server. Compare all Lore alternatives.
How does Lore compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 46 (the typical AI and agents server has 6); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Lore

Same job from other publishers: the closest match first, then the best rated.

All Lore alternatives →
  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • Agent Comms
    Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Mnemoverse Memory
    Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
    A

More from agentkitai →