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

Memoryhub

MCP server for persistent memory using Qdrant vector store

34Low

Scored a month ago · breakdown

About Memoryhub

Memoryhub is an MCP server published by taraksh01 in the RAG category: mCP server for persistent memory using Qdrant vector store.

The repository has 1 stars and 0 forks, with the last commit 2 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/taraksh01/memoryhub

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 (16)

add_memoriesStore text (LLM extracts facts, embeds them). Deduplicates near-duplicates by default. Optional `project`, `source`, `importance` (0–1), `expires_at` (ISO), `dedup` (bool), `threshold` (0–1). Returns per-memory `action`: `inserted` \

Parameters not published.

batch_add_memoriesAdd multiple texts in one call (`items: [{text, project?, source?, importance?, expires_at?, dedup?, threshold?}]`). Per-item outcomes; item-level failures don't abort the batch

Parameters not published.

delete_all_memoriesDelete ALL memories (or filter by project)

Parameters not published.

delete_memoriesDelete specific memories by IDs

Parameters not published.

export_memoriesExport memories as JSON (`{exported_at, count, memories}`) for backup/migration; optional `project` / `source` filters

Parameters not published.

get_configShow current runtime configuration (API keys masked)

Parameters not published.

get_memoriesGet multiple memories by IDs

Parameters not published.

get_memoryGet a single memory by ID (full metadata)

Parameters not published.

health_checkCheck connectivity to Qdrant

Parameters not published.

import_memoriesImport export JSON (array or `{memories: [...]}`). Texts are re-embedded on import; original IDs and metadata are preserved

Parameters not published.

Show all 16 tools
list_memoriesList memories with pagination (`limit`, `offset` as cursor from `next_offset`); newest first; filter by `project` and/or `source`; returns full metadata

Parameters not published.

memory_statsCollection statistics: totals, `by_project`, `by_source`, `expired`, `expiring_soon_7d`, `avg_age_days`, `oldest/newest_created_at`, `size_bytes` (estimate)

Parameters not published.

review_staleReport-only audit: buckets for expired, expiring soon (`days`, default 7), and older than `older_than_days` (default 90). Optional `project` / `source` / `limit`. Never modifies data

Parameters not published.

search_memorySemantic search with optional limit; returns full metadata per hit. Filter by `project` and/or `source`; set `exact: true` to match the query text verbatim instead of by similarity; `min_score` (0–1) drops hits below a similarity threshold (not usable with `exact: true`)

Parameters not published.

update_configUpdate a config value at runtime; set `persist: true` to write it atomically to the config file

Parameters not published.

update_memoryUpdate a memory's text (re-embeds); optional `source`, `importance`, `expires_at`

Parameters not published.

Ask AI

✦

Ask AI about Memoryhub

Powered by Claude · Grounded in docs

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

Security checks

6 checks have not been run yet.

Questions

About Memoryhub

How do I install Memoryhub?

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

Is Memoryhub 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 Memoryhub still maintained?

Yes — the last commit was 2 months ago. The repository has 1 stars and 0 forks.