meridian: Skill for Claude Code

.claude/skills/meridian-mcp/SKILL.md

meridian-mcp is a skill for Claude Code from Meridiona/meridian. It costs 30 tokens per session (984 once invoked), scanned A, original, MIT.

A TypeScript MCP server that reads Meridian's local SQLite session database and makes session, focus-time, and activity information available to AI tools. MCP is a standard way for AI applications to access external tools and data.

In plain words
What is it for?
Use it to build and run the server, then query completed sessions, daily timelines, productivity statistics, active sessions, and application lists while the Meridian daemon supplies the database.
Why use it?
It lets compatible AI clients query Meridian activity without requiring native Node.js database modules. The database is opened read-only, so the server does not modify session data.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

This is Meridiona/meridian's own configuration. It tells Claude Code how to work on meridian itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything meridian configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node dist/index.js.

Reuse

Borrowing it

Nothing to install: this file belongs to Meridiona/meridian. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Meridiona/meridian/main/.claude/skills/meridian-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Meridiona/meridian

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for meridian-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/meridiona/meridian/meridian-mcp/github.svg)](https://agentmods.dev/skills/meridiona/meridian/meridian-mcp)
Your own site
<a href="https://agentmods.dev/skills/meridiona/meridian/meridian-mcp"><img src="https://agentmods.dev/badge/skills/meridiona/meridian/meridian-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for meridian-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/meridiona/meridian/meridian-mcp"><img src="https://agentmods.dev/badge/skills/meridiona/meridian/meridian-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 984 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 4
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium MCP Rug Pull · line 87
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 103
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium MCP Rug Pull · line 93
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00984
Opus 5 $0.00015 $0.00492
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 12d ago against content hash 223d36be2b99, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meridian-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/meridian-mcp/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meridian MCP Server Skill

What It Is

A TypeScript MCP server (packages/meridian-mcp/) that exposes Meridian's structured session database to any MCP-compatible AI tool (Claude Code, Claude Desktop, Cursor, etc.).

It opens ~/.meridian/meridian.db read-only using sql.js (pure WebAssembly SQLite — no native Node.js modules, works with any Node.js version) and provides tools for querying app sessions, focus time, and activity history.

Build & Run

cd packages/meridian-mcp

# Install dependencies
npm install

# Build TypeScript → dist/
npm run build

# Start server (stdio transport)
node dist/index.js

Prerequisite: The Meridian daemon must be running and have produced at least one session. The MCP server returns an error message on tool calls (does not crash) if the DB is missing.

Available Tools

Tool Description
get-sessions List completed app sessions for a date (default: today)
get-timeline Full day timeline including idle and sleep gaps
get-stats Daily productivity stats — focus/idle/away time, top apps
get-active-session Currently in-progress session (if daemon is running)
get-apps All-time app usage stats
search-sessions Search sessions by window title, OCR text, or audio
get-session-detail Full OCR, elements, and signals for a session ID (audio excluded — stored in DB but not sent to LLMs)
health-check ETL run status, cursor position, and total session count

Configuration

# Override DB path (default: ~/.meridian/meridian.db)
MERIDIAN_DB=/path/to/custom.db node dist/index.js

Add to Claude Desktop / Claude Code

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "meridian": {
      "command": "node",
      "args": ["/path/to/meridian/packages/meridian-mcp/dist/index.js"]
    }
  }
}

Replace /path/to/meridian with the actual repo path.

Debugging

MCP server errors on startup

# Check if DB exists
ls -lh ~/.meridian/meridian.db

# Check if daemon is running
pgrep meridian

# Run daemon first, then start MCP server
./target/release/meridian &
node packages/meridian-mcp/dist/index.js

Read the full file on GitHub · 128 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 128 lines · 30 tokens per session scan A 223d36be2b99

Subscribe to this mod's changes

meridian-mcp is a skill published in the GitHub repository Meridiona/meridian (336 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 984 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

vscode-doctor

Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor…

majiayu000/spellbook · 75 tokens

review-agent-harness

Review whether a repository's coding-agent harness can reliably carry work from intent through controlled execution, verification, delivery, and learning. Use when asked to assess agent readiness, repeated agent failures, Rules/Skills/Hooks/Memory effectiveness, missing validation or recovery loops, or whether a…

majiayu000/spellbook · 90 tokens

codebase-audit

A read-only method for auditing an entire codebase across contracts, data integrity, errors, security, architecture, technical debt, configuration, and caching. It produces prioritized findings and a repair roadmap.

majiayu000/spellbook · 176 tokens

codex-log-guard

Diagnose excessive Codex local SQLite diagnostic log writes with read-only evidence by default. Use when a user mentions logs2.sqlite, logs2.sqlite-wal, blockloginserts, SSD/TBW wear, or explicitly asks to protect, clean up, verify, or restore Codex diagnostic logging.

majiayu000/spellbook · 68 tokens

harmonyos-app

HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities. Covers HarmonyOS NEXT (API 12+) best practices.

majiayu000/spellbook · 43 tokens

codex-agent

Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.

majiayu000/spellbook · 45 tokens