MCP.Market

ContextDB Memory MCP server

by mikhailbovt·io.github.mikhailbovt/contextdb-memory·v0.6.0-alpha.3·1 stars

Local-first durable AI memory with policy-bound recall and a typed project graph.

B80/100grade B
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
New

1 stars

Reviews

Write one

Nobody has reviewed ContextDB Memory yet.

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

ContextDB Memory tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –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 67 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How ContextDB Memory compares

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

Safety score
80/100
higher than 60% of 48,255 servers
GitHub stars
1
more than 65% of 28,688 servers

Install ContextDB Memory in Claude Code, Cursor or VS Code

The registry entry has no remote endpoint or installable package.

What the publisher says

From the ContextDB Memory repository's README, as published. We do not edit it. Read it on GitHub

Automatic project continuity for Codex, backed by a local ContextDB memory graph.

Install · See it grow · Operate safely

Codex can understand a repository brilliantly and still wake up in the next task with the emotional continuity of a goldfish. ContextDB Memory gives it a durable, local project history: the decisions already made, constraints that still matter, goals in flight, verified milestones, and open loops waiting for somebody to stop pretending they do not exist.

The plugin recalls relevant context at the start of substantive work and checkpoints significant state as the task evolves. It does this through a bundled, listener-free MCP adapter; the database, runtime, keys, and mutable memory remain on your own Windows or Linux computer.

Release status: 0.6.0-alpha.3 Developer Preview for Windows x86-64 and Linux x86-64.

Both local profiles include automatic hooks, a typed candidate graph, platform-specific custody,

recovery and uninstall controls, and independently verifiable release bundles. Executables are

unsigned, macOS and ARM64 are not supported, and this is not a hosted ContextDB service.

The Linux ELF uses an Ubuntu 22.04 / glibc 2.35 baseline; other glibc-based

x86-64 distributions require glibc 2.35 or newer and are not individually certified.

What it remembers

Short-lived chatter, guesses, copied logs, secrets, and “maybe someday” noise should not become durable memory. The active Codex model decides whether a change is significant; the host contract constrains how it may be written.

How the memory grows

flowchart LR
    S[Session starts] --> R[Bounded candidate recall]
    R --> W[Codex works with current files]
    W --> C{Durable change?}
    C -- no --> W
    C -- yes --> Q[Quarantined candidate]
    Q --> G[Project / topic / memory DAG]
    G --> R
    Q -. explicit successor .-> Q2[New revision]

Shortened. The full README is on GitHub.

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

Grade history

  • 2026-10-31downgradeA → Bscore 80

ContextDB Memory: common questions

Is ContextDB Memory MCP server safe?
Mostly: it is graded B (80/100). Read the ContextDB Memory safety report
Does ContextDB Memory need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is ContextDB Memory maintained?
The last commit was 71 days ago (2026-08-25). The latest release is v0.6.0-alpha.3.
What can I use instead of ContextDB Memory?
Servers from other publishers that do the same job: Memorix MCP server, Codebase Memory MCP server and Neo4j Memory MCP server.
How does ContextDB Memory compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,255 servers); github stars 1 (more than 65% of 28,688 servers). Full comparison.

Alternatives to ContextDB Memory

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

  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B
  • Codebase Memory
    Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
    C
  • Neo4j Memory
    MCP Neo4j Knowledge Graph Memory Server
    A
  • Nautilus Compass Memory
    Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
    B
  • State Memory MCP
    Persistent workflow graph server tracking tasks, decisions, spatial entities, and blockers.
    A