Skip to main content
Glama
Sign In

Locul Cloud Memory

by ai.locul
OverviewDiscussionsAdmin

Server Details

Recall memories, entity profiles and source notes from your Locul cloud brain in any AI chat.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 9 tools

Disambiguation3/5

Three tools overlap heavily on retrieval: search, search_notes, and recall_memories all return saved memories, and the search/search_notes boundary is genuinely unclear (search_notes is described as searching memories, not notes). Similarly get_brain_index and memory_stats both report counts of memories, people, projects and topics. Descriptions attempt to differentiate (exact words vs. topical questions vs. overview), but an agent could easily misselect among them.

Naming Consistency3/5

Mostly verb_noun forms (create_memory, get_brain_index, get_entity_profile, get_memory_source, recall_memories), but bare verbs (fetch, search) and a noun phrase (memory_stats) break the pattern. The mixed styles are still readable but not predictable.

Tool Count4/5

Nine tools is a reasonable, well-scoped number for a memory store. A couple of the read tools (search/search_notes, get_brain_index/memory_stats) feel partially redundant, which slightly inflates the count, but it is not excessive.

Completeness3/5

The surface covers create and several read/retrieval paths plus source and entity views, but there is no update or delete tool. An agent that saves an inaccurate memory has no way to correct or remove it, which is a notable lifecycle gap for a personal memory store.

Publisher details

Operator
Locul · Publisher source
Operator website
https://locul.ai · Publisher source
Vendor relationship
First-party · Publisher source
Documentation
https://locul.ai/mcp/cloud/ · Publisher source
Trust center
Not available
Restrictions
Requires a Locul Cloud account. · Publisher source

Available Tools

9 tools
create_memorySave a memoryAInspect

Save one new memory to the user's Locul account. Use only when the user asks to remember or save something. Creates a new record; it does not change or delete existing memories. If the same fact is already saved, nothing is added. Never save secrets such as passwords or keys. Keep fact concrete and standalone so it still makes sense read alone months later, and list every person, company, product, project, tool or topic it is about in entities so it is linked to them.

Inputs: fact (required), kind, entities, confidence, +2 more.

fetchFetchA
Read-only
Inspect

Get the full text of one saved memory by the id returned by search. Read-only.

Inputs: id (required).

get_brain_indexGet brain indexB
Read-only
Inspect

Overview of the user's Locul account: how many memories are saved and the people, projects and topics that come up most. Read-only.

Inputs: no named parameters.

get_entity_profileGet entity profileB
Read-only
Inspect

Show what is saved about one person, company, product, project, tool or topic: its key memories, related items and other names. Match by name or key. Read-only.

Inputs: key (required).

get_memory_sourceGet memory sourceA
Read-only
Inspect

Show which note a memory came from, by memory id: the memory plus the note's title and path. Read-only.

Inputs: id (required).

memory_statsMemory statsB
Read-only
Inspect

Count the memories, people, projects, topics and source notes saved in the user's account. Read-only.

Inputs: no named parameters.

recall_memoriesRecall memoriesA
Read-only
Inspect

Find the user's saved memories that relate to a question or topic. Optionally limit to one person, company, project or topic with entity. Read-only.

Inputs: query (required), limit, entity.

searchSearchB
Read-only
Inspect

Search the user's saved memories and return matching results. Use fetch to get the full text of any result by its id. Read-only.

Inputs: query (required).

search_notesSearch notesA
Read-only
Inspect

Keyword search over the user's saved memories. Use when the user gives exact words or names. Read-only.

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • MyChatArchive MCP Server

      1ch1n
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables semantic search across your local AI conversation history (ChatGPT, Claude, etc.) and provides tools to retrieve context, capture thoughts, and get profile summaries.
      72
      AGPL 3.0
    • MyAITwin MCP

      MyAITwin MCPofficial

      LutoLabs
      F
      license
      Not graded
      quality
      C
      maintenance
      Personal RAG database and semantic search built from inside your AI chat. Store knowledge, voice, and skills; Claude and ChatGPT create work that sounds like you.
      -

    • Memento

      scrypster
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides persistent memory for AI tools by building a local knowledge graph from conversations, enabling cross-session recall and context awareness without cloud dependencies.
      9
      MIT

    • Inkstone

      jairodriguez
      A
      license
      Not graded
      quality
      D
      maintenance
      Automatically extracts and indexes knowledge from AI sessions and files using local LLMs, enabling semantic search and memory management.
      19 npm
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources