Skip to main content
Glama
fredporter

SnackMachine

by fredporter

SnackMachine

Modular snack registry, scheduler, spool, and MCP knowledge conduit.

Install

pip install snackmachine

Or from source:

pip install -e .

Related MCP server: akb

Structure

snackmachine/
├── registry.py         # SnackSpec, SnackPlugin, SnackRegistry
├── base.py             # SnackParam, SnackMeta, BaseSnack
├── scheduler.py        # Cron-like maintenance scheduler
├── spool_reader.py     # Spool feed parser
├── spool_writer.py     # Spool append writer
└── conduit/
    ├── bridge.py       # MCP query/status/chat routes
    ├── library_index.py # FTS5 across all 5 vault layers
    ├── ai_bridge.py    # AI-ranked search with agent boosting
    ├── doclang.py      # Markdown/wiki-link/section parser
    └── knowledge_layer.py # Multi-agent shared memory

Usage

from snackmachine.registry import get_registry
from snackmachine.base import BaseSnack, SnackMeta

class MySnack(BaseSnack):
    meta = SnackMeta(id="my-snack", name="My Snack", category="custom")
    def execute(self, action=None, **kwargs):
        return {"success": True}

# Register
get_registry().register(MySnack())

Data

All mutable data lives in ~/.ucore/:

  • ~/.ucore/indices/library.db — FTS5 search index

  • ~/.ucore/knowledge/shared.db — multi-agent memory

  • ~/.ucore/logs/ — spool files

  • ~/.ucore/config/mcp-manifests/ — MCP server manifests

Set SNACKMACHINE_DATA_DIR to override the data root.

License

MIT

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

No tool schema history has been recorded yet.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    Governed multi-agent memory for AI agents. Hybrid markdown + SQLite store with full-text search, vector retrieval, and LLM reranking. Three transports: MCP stdio, HTTP JSON-RPC, and MCP SSE. One Go binary
    1
    Apache 2.0
  • F
    license
    A
    quality
    A
    maintenance
    MCP-native knowledge base for AI agents — vault-scoped docs, tables, and files, git-versioned, with hybrid search (BM25 + pgvector dense + reranker) and an event stream so external consolidators / gardeners stay decoupled.
    50
    157
    -
  • A
    license
    A
    quality
    A
    maintenance
    Local-first agentic knowledge layer over Obsidian notes, enabling MCP-aware agents to search, retrieve, and compile knowledge with provenance and task contracts.
    37
    27
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    A local-first MCP server for durable agent memory using SQLite and FTS5, enabling knowledge graph storage, search, and recall for AI agents.
    20
    1
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/fredporter/snackmachine'

If you have feedback or need assistance with the MCP directory API, please join our Discord server