MCP.Market

Meridian MCP server

online · 100% uptime
by ajc3xc·io.github.ajc3xc/meridian·v1.0.2

Persistent memory, task coordination, and HITL queue for AI coding sessions.

B78/100grade B
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
Growing

0 stars86 downloads/wk

Reviews

Write one

Nobody has reviewed Meridian yet.

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

Meridian tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • Live reliabilityremote reachable in 10204ms; handshake note: MCP handshake timed out after 10000ms12/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Meridian compares

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

Safety score
78/100
higher than 50% of 1,299 Productivity servers
Uptime
100%
of our recent checks; the typical remote Productivity server answers 100%
Response time
113 ms
faster than 84% of 655 Productivity servers
Downloads a week
86
more than 53% of 427 Productivity servers with a package

Install Meridian in Claude Code, Cursor or VS Code

claude mcp add --transport http meridian https://usemeridian.us/mcp/sse
Add to Cursor

What the publisher says

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

<!-- mcp-name: io.github.meridianmcp/meridian -->

Meridian

Claude Code has no memory between sessions. Meridian fixes that.

Open-source MCP server for persistent AI session memory — shared task log, pinned decisions, human-in-the-loop queue, and tiered handoffs. Works with Claude Code, Cursor, Cline, Claude Desktop, or any MCP client.

Why Meridian

Every AI coding session boots blind. You re-explain the architecture, re-describe the constraints, re-list what's been tried. When context fills up mid-task, everything is lost. This is context debt — and it compounds.

Meridian gives your sessions shared memory. They see the same task log, the same pinned decisions, the same goal state. When context fills up, a new session resumes from a compressed handoff in seconds. No copy-paste, no re-explaining from scratch.

What it is, in 30 seconds

A local MCP server every AI session connects to. They share goal state, see each other's task log, and resume from a compressed handoff when context fills up.

Two ways to run Meridian:

  • Self-host — free forever, any team size. Clone and run in 2 commands.
  • Hosted at usemeridian.us — 30 days free (no card), then $20/mo Standard.

<!-- MERIDIAN:ANCHOR:START quickstart -->

Quickstart

Option 1 — binary release (recommended)

Signed binaries for Windows, macOS (Apple Silicon), and Linux are attached to every GitHub release (current: v0.2.6).

Linux / macOS (one-liner via uv):

uv tool install meridian-server
meridian --tunnel --repo .

Linux / macOS (manual binary download):

curl -fsSL https://usemeridian.us/install.sh | sh

Windows (PowerShell, one-liner via uv):

uv tool install meridian-server
meridian --tunnel --repo .

Windows (PowerShell, manual binary download):

irm https://usemeridian.us/install-windows.ps1 | iex

Dashboard opens at http://localhost:7878. Data persists in ~/.meridian/ by default.

Option 2 — from source (dev setup / self-host)

Linux / macOS:

git clone https://github.com/meridianmcp/Meridian
cd Meridian
./install.sh
pixi run start

Windows (PowerShell):

git clone https://github.com/meridianmcp/Meridian
cd Meridian
.\install.ps1
pixi run start

Dashboard opens at http://localhost:7878. Data persists in ./data/meridian.db. <!-- MERIDIAN:ANCHOR:END quickstart -->

Wire it into your AI client

Claude Code

Drop a .mcp.json at your project root.

Shortened. The full README is on GitHub.

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

Meridian: common questions

Is Meridian MCP server safe?
Mostly: it is graded B (78/100). Read the Meridian safety report
How do I install Meridian?
It runs remotely at usemeridian.us. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Meridian need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Meridian maintained?
The last commit was 38 days ago (2026-09-27). The latest release is v1.0.2.
Is Meridian up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Meridian?
Servers from other publishers that do the same job: loci MCP server, Obsidian Turbocharged MCP server and Enquire MCP server. Compare all Meridian alternatives.
How does Meridian compare with other Productivity MCP servers?
safety score 78/100 (higher than 50% of 1,299 Productivity servers); uptime 100% (of our recent checks; the typical remote Productivity server answers 100%); response time 113 ms (faster than 84% of 655 Productivity servers). Full comparison.

Alternatives to Meridian

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

All Meridian alternatives →
  • loci
    Cross-session memory and hybrid RAG over your notes and docs. Local-first, with cited answers.
    A
  • Obsidian Turbocharged
    Governed Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
    B
  • Enquire
    Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.
    A
  • Argent
    Drive iOS Simulators, Android emulators, TVs and Electron/web apps from your coding agent
    A
  • Agent-Native Dispatch
    Central Slack/Telegram router with jobs, memory, approvals, and A2A delegation
    A