Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tboome33/obsidian-mcp-router/plugin install obsidian-routerWrote 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.
[](https://agentmods.dev/commands/tboome33/obsidian-mcp-router/meta-status)<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/meta-status"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/meta-status/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.
<a href="https://agentmods.dev/commands/tboome33/obsidian-mcp-router/meta-status"><img src="https://agentmods.dev/badge/commands/tboome33/obsidian-mcp-router/meta-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.02096 |
| Opus 5 | $0.00019 | $0.01048 |
| Sonnet 5 | $0.00008 | $0.00419 |
| Haiku 4.5 | $0.00004 | $0.00210 |
Grade A, and why
meta-status 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
meta-status
Produces a one-shot diagnostic of the multi-vault Obsidian router. Run it when the user wants to know what's working, what isn't, and how to fix it.
Steps
-
Call the router's
list_vaultstool (no arguments). The router will ping each configured vault in parallel and return a structure like:{ "defaultVault": "tradingview", "configPath": "/Users/.../.claude/obsidian-mcp-router/config.json", "vaults": [ { "name": "tradingview", "type": "local", "baseUrl": "https://127.0.0.1:27125", "online": true, "latencyMs": 4, "missingApiKey": false, "isDefault": true }, { "name": "qnap", "type": "remote", "baseUrl": "https://qnap.tailnet.local:27125", "online": false, "latencyMs": 5012, "error": "[qnap] timed out after 5000ms calling /", "missingApiKey": false } ] } -
Render the result as a compact summary:
- First line:
<n> vault(s) configured · <m> online · default: <name> - Then a markdown table with columns: name | type | status | latency | path/baseUrl
- Use ✅ for online, ❌ for offline, ⚠️ for missingApiKey or any partial issue
- First line:
-
For each vault that is NOT fully healthy, add a short diagnostic block explaining the likely cause and the fix:
| Symptom | Likely cause | Fix to suggest |
|---|---|---|
online: false AND type: local |
Obsidian not running on this vault, or a different vault is open | Open Obsidian and load the vault at the path shown |
online: false AND type: remote AND error includes "unreachable" |
Remote host not reachable | Check that the remote machine is online, the tunnel is up (Tailscale / Cloudflare), and that no firewall changed |
online: false AND error includes "timed out" |
Network path is alive but slow, or the remote vault is busy | Bump timeoutMs for that vault to 15000-20000 |
online: false AND error includes "401" |
API key is wrong or expired | For local: re-run setup-vault.mjs to regenerate. For remote: re-fetch the key from the host's data.json |
online: false AND error includes "cf_access" or "cloudflareaccess.com" |
Cloudflare Access policy is blocking the request | Verify extraHeaders has the right CF-Access-Client-Id + CF-Access-Client-Secret and that the service token is attached to a "Service Auth" policy on the Access app |
missingApiKey: true AND type: local |
Local REST API plugin never enabled for this vault, so no data.json to read |
Open Obsidian on this vault, enable Local REST API plugin, then re-run setup-vault.mjs |
online: true AND latencyMs > 500 AND type: remote |
Functional but slow; might cause timeouts on large operations | Note it as a soft warning; consider Tailscale Funnel for a closer relay or moving to a Cloudflare Tunnel |
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.
- 8d ago Changed · +53 lines 164f1cabef6c
- 11d ago First seen · 81 lines · 39 tokens per session scan A 48d66b4f0499
meta-status is a command published in the GitHub repository tboome33/obsidian-mcp-router (1 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 2,096 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 2026-08-31.
Other commands, from other repositories
lint
Run health check on a project — orphans, contradictions, stale claims, gaps, suggested cross-links. Usage: /mb:lint [-p ] [project-id].
doctor
A diagnostic command for checking and, when requested, repairing an llm-brain installation. It also offers read-only profiles for demo, private use, or preparing a shareable setup.
lint
Run comprehensive wiki health check — orphans, broken links, contradictions, stale pages, index sync, MOC coverage, v2/v4/v5 frontmatter coverage, Core Context freshness, and cross-vault link integrity (mainVaultRelated/mainVaultCmds).
reconnect
Diagnose the ga-mcp-full MCP connection and walk through reconnect options. Use when GA tool calls stop responding, return auth errors, or /plugin shows a red error for ga-mcp-full.
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
wiki-query
Ask questions against the wiki. Synthesizes answers from wiki pages with cross-reference citations.