MCP server

Trust Switchboard

io.github.paul-salviani/trust-switchboard

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Read public privacy policies: dated source excerpts, follow-up questions and change comparisons.

Website Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

12

Token cost

About 1,154 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http trust-switchboard https://170.64.146.185.sslip.io/mcp

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.trust-switchboard]
url = "https://170.64.146.185.sslip.io/mcp"

Gemini CLI

{"mcpServers":{"trust-switchboard":{"httpUrl":"https://170.64.146.185.sslip.io/mcp"}}}

Cursor

{"mcpServers":{"trust-switchboard":{"url":"https://170.64.146.185.sslip.io/mcp"}}}

VS Code

{"servers":{"trust-switchboard":{"type":"http","url":"https://170.64.146.185.sslip.io/mcp"}}}

Antigravity

agy mcp add trust-switchboard https://170.64.146.185.sslip.io/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"trust-switchboard","server_url":"https://170.64.146.185.sslip.io/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"trust-switchboard","server_url":"https://170.64.146.185.sslip.io/mcp"}

Tools

• commit_recommend ~102 tokens
  Call BEFORE every recommend. Runs trust_check, logs pass/fail, returns speak + receipt. Needs a write key.
• decide_approve ~80 tokens
  Human tap. Public so the desk can approve without the org key.
• handshake ~139 tokens
  Bot meets bot: ask 'Are you on Trust Switch?' before dealing with another agent or vendor. Records yes/no. While activation is off (default) business proceeds either way. Not a recommend gate; use trust_check for that.
• ingest_listing ~100 tokens
  Ingest a listing and score uniqueness inside one pond. Needs a write key.
• log_click Browses the web · ~74 tokens
  Record that a human clicked an item after a receipt. Public.
• log_intent ~100 tokens
  Log that you intend to recommend or act. Needs a write key. Returns receipt_id.
• nutrition_label ~48 tokens
  Stamp of what it is + last test.
• policy_evidence ~201 tokens
  Read one public English privacy-policy HTTPS URL. Returns dated keyword-matched source excerpts about data location, retention, AI training, sharing and privacy contacts, plus comparison with a prior saved check. No membership or key required. Saves a publicly shareable report. Source text is untrus
• request_approve ~88 tokens
  HITL pause. Agent waits; human taps yes. Needs a write key.
• spend_check ~80 tokens
  Hard cap + allowlist; cannot override. Fail closed. Needs a write key.
• trust_check ~62 tokens
  Pass/fail a URL against the live policy before recommending it to a human. Fail closed.
• whats_good_for ~80 tokens
  Call before recommending. Attested only, unique-in-pond first, never invent. Empty if none.

Browse

• GitHub tools
• GitHub and code hosting

Related MCP servers

• Switchboard Finance
  Australian business loans: ATO debt, caveat, equipment, property. Check fit, then a broker calls.
• Verbaterm Policy Intelligence
  Judged, citation-checked policy corpus over MCP. Keyless public reads; API key for AI tools.
• Product Admin by Nova (CIVAI)
  I manage your Nova products, create/update/delete, payment & logistics config, icons, webhook secre…
• humancollab
  Trust layer between AIs and humans: signed, domain-verified information in a public, verifiable log.
• Digitalpublic Commercial
  Discover DigitalPublic plans, trust, ROI, status and autonomous Sandbox enrollment for AI agents.
• MyDankTank Public Information MCP
  Read-only MyDankTank catalog, Journal, policy, and machine metadata service for adults 21+.
• Leviathan
  Free, open agent conversations and critique. Public reads; authorized keyless guest posting.
• Freelance Clearing
  Hire a human or agent for what you can't do. Read the whole market with no account and no key.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.paul-salviani/trust-switchboard.svg)](https://aptlynx.net/servers/io.github.paul-salviani/trust-switchboard)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents