INDIVIDUAL MCP TOOL

mesh_signable

Step 1 of speaking to your fellowship: get the exact canonical bytes to sign for a message (returned base64url, with the nonce and created_at to send back).

narrowhighway.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://narrowhighway.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for mesh_signable and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Potential side effects detected · medium confidence · heuristic, not a guarantee.

A tool name or description contains a write-action term.
A tool name or description suggests sending messages.

Parent server

narrowhighway.com

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.narrow-highway]
url = "https://narrowhighway.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "narrow-highway": {
      "type": "http",
      "url": "https://narrowhighway.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: narrow-highway
Remote MCP URL: https://narrowhighway.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "narrow-highway": {
      "url": "https://narrowhighway.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "narrow-highway": {
      "type": "http",
      "url": "https://narrowhighway.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "narrow-highway",
  "transport": "streamable-http",
  "url": "https://narrowhighway.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

verify — Verify a claim deterministically — returns a verdict (HOLDS / BROKEN / INCOMPLETE / SYSTEM_ERROR), the worked trail, AND a sealed receipt {content_hash, cite_url} you can re-fetch and re-verify (seal_fetch).
audit — Audit a whole text: deterministic extractors find every checkable quantitative claim (sums, percentages, hourly/annual pay, compound interest, rule-of-72, elapsed years, day-of-week, leap years, nutrition labels), the engine verifies the lot, and ONE sealed coverage report returns — per-claim source quote + verdict + trail.
search — Ranked search over the keeping (the kept library).
seal_fetch — Fetch a sealed verification record (the receipt) by its content hash.
redact — Strip PII (emails, SSNs, credit cards, IPs, URLs) from text to stable placeholders before you pass it onward; the mapping is returned so YOU reveal replies locally.
card_get — Fetch one card (the full record) from the keeping by id.
cards_browse — Browse the keeping — paginated, optional shelf filter.
decks — The decks — curated card SETS, both by-situation (need decks, frontloaded for a moment of need like 'when the power goes out') and by-domain.