MCP.Market

MADB — Agent Memory Database MCP server

by spshkar84·io.github.spshkar84/madb-memory·v0.2.10
No reviews yet

Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.

A88/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars98 downloads/wk

Reviews

Write one

Nobody has reviewed MADB — Agent Memory Database yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MADB — Agent Memory Database tools (38, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • adaptation_decision_status

    Read the HITL gate status of an adaptation proposal (Sprint 11).

  • analytics

    Show MADB MCP usage analytics: call counts, latencies, recall precision, and Memory ROI.

  • capabilities

    Summarize MADB's durable causal-memory capabilities + usage status.

  • check_policy

    Pre-flight a policy check without writing the record (Sprint 8).

  • detect_skills

    Detect recurring patterns that could be saved as reusable skills.

  • export

    Export memory as a human-readable, git-diffable, tamper-evident projection by causal root.

  • forget

    Soft-delete a memory by event_id.

  • gcwrite action

    Run causal-aware garbage collection on a tenant's memories.

  • get_memory

    Retrieve a specific memory by its event_id.

  • get_summaries

    Get summary records for a tenant.

  • hypothesis_status

    Read the current resolution status of a hypothesis (Sprint 10).

  • introspect

    Introspect memory patterns — see what the agent remembers and how.

  • list_pending_adaptations

    List adaptation proposals awaiting HITL decision (Sprint 11).

  • list_pending_hypotheses

    List pending (unresolved) hypotheses for a tenant (Sprint 10).

  • list_recent

    List the most recent memories for a tenant.

  • list_skills

    List all saved skills ranked by composite score.

  • list_snapshots_tool

    List all named memory snapshots.

  • load_cycle

    Load a cycle archive rooted at root_event_id (Sprint 9).

  • propose_adaptation

    Propose an adaptation for HITL review (Sprint 11 / Loop 2).

  • recall

    Semantic recall: find the most relevant memories for a query.

  • recall_consistency_check

    Verify the per-tenant tamper-evident chain (Sprint 7 Memory Integrity).

  • recall_feedback

    Report which recalled memories were actually used vs. ignored.

  • recall_skill

    Recall skills matching a natural language query.

  • record_hitl_decision

    Record a HITL gate decision on a pending adaptation proposal.

  • reembed

    Backfill embeddings for memories written before the embedder was enabled.

  • remember

    Store a memory in MADB with optional causal links and tags.

  • replay_cycle

    Replay (load + structurally verify) a cycle (Sprint 9).

  • resolve_hypothesis

    Resolve a pending hypothesis with a terminal status (Sprint 10).

  • resume

    One-call session resume: a synthesized brief of the open work.

  • rollback

    Rollback to a named snapshot — soft-delete all records written after it.

  • save_skill

    Store a reusable skill or coding pattern in MADB.

  • search

    Query memories by tenant and optional scope filter.

  • snapshotwrite action

    Create a named memory snapshot for rollback support.

  • stats

    Engine metrics: writes, reads, flushes, compactions, WAL state, etc.

  • summarize

    Summarize old memories into compressed time-bucket summaries.

  • trace_cause

    Trace the causal chain — see what caused a memory or what it caused.

  • verify_rebuildable

    Verify the "index is derived; the causal store is the source of truth" guarantee.

  • write_hypothesiswrite action

    Write a hypothesis (typed prediction) record (Sprint 10).

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan5 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 81 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MADB — Agent Memory Database compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 802 Databases servers
Tools
38
the typical Databases server has 8
Tools that change things
8%
typical: 10%. Fewer write tools means less an agent can break
Downloads a week
98
more than 57% of 328 Databases servers with a package

What its tools let an agent do: 34 read · 2 create · 2 change

Install MADB — Agent Memory Database in Claude Code, Cursor or VS Code

claude mcp add madb-memory -- uvx madb-mcp-server
Add to Cursor

What the publisher says

From the MADB — Agent Memory Database repository's README, as published. We do not edit it. Read it on GitHub

Meta-AgentsDB

Persistent, causal memory for autonomous AI agents.

Purpose-built for Claude and the autonomous-agent era.

Meta-AgentsDB (MADB) is an agent-native database — a hybrid LSM store with a causal DAG, composite-score recall, importance-based forgetting, and HLC-ordered MVCC. It is what your agent needs that PostgreSQL + pgvector + Redis + Pinecone cannot give you in one box.

Install (free tier):

bash

claude mcp add madb -- uvx madb-mcp-server # Claude Code

# or: pip install madb-mcp-server · uvx madb-mcp-server

Memory stays local (~/.madb). Claude Desktop users can install the one-click .mcpb extension. The engine ships as compiled wheels — source is not public. Anonymous usage telemetry can be disabled with MADB_TELEMETRY=off.

What MADB is, in one sentence

The memory substrate Claude reaches for automatically — a focused set of MCP tools, one Skill, one SDK shim — so any Claude session, Claude-Desktop user, or raw-Anthropic-API developer gets persistent, causally-linked, composite-scored agent memory with zero glue code.

How you get MADB

MADB is distributed as compiled binary artifacts under the Meta-Agents.AI Proprietary License. Source code is not public. The three packages:

See examples/basic_usage.py for the shim in action.

The MCP tools Claude gets

The free tier exposes a focused core of 13 memory tools:

Plus the MCP resource madb://memories/{event_id} for reading any memory as a first-class URI.

The Skill is the reflex

The MCP tools are necessary but not sufficient for "default." Without a Skill telling Claude to prefer MADB, Claude still invents per-task memory schemes — JSON files, SQLite tables, pickle dumps, flat vector stores, localStorage, conversation-history arrays.

skills/madb-memory/SKILL.md routes those anti-patterns to MADB by name. The Skill ships bundled with the MCP server wheel and auto-installs to ~/.claude/skills/madb-memory/ on first launch. It is published under CC-BY-ND 4.0 — share verbatim, don't modify.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

MADB — Agent Memory Database: common questions

Is MADB — Agent Memory Database MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the MADB — Agent Memory Database safety report
How do I install MADB — Agent Memory Database?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does MADB — Agent Memory Database need an API key?
No secret keys are declared. It reads 3 settings from the environment.
Is MADB — Agent Memory Database maintained?
The last commit was 120 days ago (2026-07-07). The latest release is v0.2.10.
What can I use instead of MADB — Agent Memory Database?
Servers from other publishers that do the same job: Remem MCP server, Graphmem MCP server and skillmem MCP server.
How does MADB — Agent Memory Database compare with other Databases MCP servers?
safety score 88/100 (higher than 75% of 802 Databases servers); tools 38 (the typical Databases server has 8); tools that change things 8% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to MADB — Agent Memory Database

Same job from other publishers: the closest match first, then the best rated.

  • Remem
    Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
    B
  • Graphmem
    Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.
    A
  • skillmem
    Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.
    A
  • Citadel
    Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools
    B
  • CogniCore
    Memory, reflection and safety for AI agents. Hosted or local, no vector database.
    A