1. Conduid
  2. RAG
  3. Noshy
MCP server · RAG

Noshy

Provide persistent knowledge storage for AI agents using ICM and MCP standards to manage facts and memory graphs across sessions.

34Low

Scored a month ago · breakdown

About Noshy

Noshy is an MCP server in the RAG category: provide persistent knowledge storage for AI agents using ICM and MCP standards to manage facts and memory graphs across sessions.

Install

From source
git clone https://github.com/Noshkoto/Noshy

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (20)

noshy_consolidateMerge related memories on a topic

Parameters not published.

noshy_consolidate_clustersAuto-merge those clusters in one pass

Parameters not published.

noshy_decision_timelineChronological timeline of decisions, fixes, and resolutions. Answer "what did we decide about X?"

Parameters not published.

noshy_deleteRemove a memory by id, or all memories under a topic

Parameters not published.

noshy_delete_projectWipe all memories and memoirs for a project (irreversible)

Parameters not published.

noshy_detect_patternsFind repeated solutions across sessions — candidates for creating reusable skills

Parameters not published.

noshy_extract_sessionLLM-powered extraction from conversation transcripts

Parameters not published.

noshy_feedbackRate a memory +1/-1 to influence how long it survives

Parameters not published.

noshy_find_clustersPreview clusters of semantically near-duplicate memories

Parameters not published.

noshy_find_contradictionsDetect (and link) pairs of memories that assert conflicting facts

Parameters not published.

Show all 20 tools
noshy_get_statsDatabase overview

Parameters not published.

noshy_list_projectsList every project with per-project counts and last activity

Parameters not published.

noshy_predict_importanceLLM-classify a candidate fact without storing it

Parameters not published.

noshy_process_queueDrain queued extractions through the LLM

Parameters not published.

noshy_queue_extractionHand off a transcript for later LLM extraction without blocking

Parameters not published.

noshy_recallSearch memories (keyword, semantic, hybrid) — also surfaces matching memoirs

Parameters not published.

noshy_session_contextGenerate context for a new session — critical memories, recent decisions, active work. Call at session start

Parameters not published.

noshy_store_memoirStore permanent knowledge (docs, reference)

Parameters not published.

noshy_store_memoryRemember a fact, decision, or preference (optional `ttl_seconds` to auto-expire)

Parameters not published.

noshy_stream_extractIncremental extraction for very long transcripts (chunked + overlap)

Parameters not published.

Ask AI

✦

Ask AI about Noshy

Powered by Claude · Grounded in docs

I know everything about Noshy. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Noshy

How do I install Noshy?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Noshy safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Noshy still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.