Skip to main content
Glama
NORTHTEKDevs

GENOME MCP Server

by NORTHTEKDevs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GENOME_MCP_DBNoOverride the default database path (~/.genome/memories.db) for persistent memory storage.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
rememberA

Store a fact or note in long-term memory.

Fully local -- embeds the text with a local model and writes it to a local
SQLite file. No LLM call, no network. Use this whenever the user tells you
something worth remembering across sessions (preferences, facts, decisions).

Args:
    content: The text to remember (a fact, preference, or note).
    user_id: Namespace to store under (default "default"). Use per-end-user.
recallA

Search long-term memory for information relevant to a query.

Read-only, fully local semantic search. Call this before answering when the
user refers to past context, preferences, or previously-shared facts.

Args:
    query: What to look for (a question or topic).
    limit: Max memories to return (1-50, default 5).
    user_id: Namespace to search (default "default").
forgetA

Delete the single memory most relevant to query, if it is relevant enough.

Destructive. Finds the best-matching memory and removes it only when its
relevance (cosine similarity, -1..1) reaches `min_score`. Below the floor
nothing is deleted and the best candidate is reported so the query can be
sharpened. Without the floor, any query against a non-empty memory deletes
its nearest neighbour, however unrelated.

Args:
    query: Describes the memory to remove.
    user_id: Namespace to delete from (default "default").
    min_score: Relevance floor (default 0.5). Lower it only when the
        reported candidate is confirmed to be the memory meant.
reset_memoriesA

Delete ALL memories for a user. Destructive and irreversible.

Args:
    user_id: Namespace to clear (default "default"). This never clears other
        users' namespaces.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
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

TDQS

A4.6/5.0

Scored across 4 tools

Disambiguation5/5

Each tool maps to a distinct memory operation: remember for storing, recall for searching, forget for deleting a single memory, and reset_memories for clearing an entire namespace. The overlap between forget and reset_memories is clearly scoped by singleness versus all-memories, so there is no real ambiguity.

Naming Consistency4/5

Three tools use simple lowercase verb forms (remember, recall, forget) and one uses verb_noun snake_case (reset_memories). The pattern is mostly consistent and intuitive, with only reset_memories deviating by including an object.

Tool Count5/5

Four tools is a well-scoped count for a memory server. Each tool covers a necessary operation without redundancy or bloat, making the set easy to navigate.

Completeness5/5

The core memory lifecycle is covered: store, read/search, delete one, and delete all. There is no explicit update operation, but for a semantic memory store treating memories as immutable facts this is not a meaningful gap.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources