Mmcp.market

Trust Switchboard MCP server

by paul-salviani·io.github.paul-salviani/trust-switchboard·v1.0.2

Ask "Are you on Trust Switch?" before your agent deals with another agent. Free. Never blocks.

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Trust Switchboard yet.

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

Trust Switchboard tools (11)

write = sends, deletes, buys or posts
  • commit_recommendFree

    Call BEFORE every recommend. Runs trust_check, logs pass/fail, returns speak + receipt. Needs a write key.

  • decide_approveFree

    Human tap. Public so the desk can approve without the org key.

  • handshakeFree

    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_listingFree

    Ingest a listing and score uniqueness inside one pond. Needs a write key.

  • log_clickFree

    Record that a human clicked an item after a receipt. Public.

  • log_intentFree

    Log that you intend to recommend or act. Needs a write key. Returns receipt_id.

  • nutrition_labelFree

    Stamp of what it is + last test.

  • request_approveFree

    HITL pause. Agent waits; human taps yes. Needs a write key.

  • spend_checkFree

    Hard cap + allowlist; cannot override. Fail closed. Needs a write key.

  • trust_checkFree

    Pass/fail a URL against the live policy before recommending it to a human. Fail closed.

  • whats_good_forFree

    Call before recommending. Attested only, unique-in-pond first, never invent. Empty if none.

Public scan report

scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it

no findings
  • Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1455ms20/20
  • Tool poisoning11 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Grade history

  • 2026-09-19restoreBAscore 88

Install directly

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

Trust Switchboard: common questions

Is Trust Switchboard MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Trust Switchboard safety report
How do I install Trust Switchboard?
It runs remotely at 170.64.146.185.sslip.io. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Trust Switchboard need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Trust Switchboard maintained?
The last commit was 7 days ago (2026-09-13). The latest release is v1.0.2.
Is Trust Switchboard up?
100% of our last 6 checks got an answer. We check remote servers about four times a day.
What can I use instead of Trust Switchboard?
Servers from other publishers that do the same job: Agent Wormhole MCP server, mcpm MCP server and MCP server. Compare all Trust Switchboard alternatives.

Alternatives to Trust Switchboard

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

All Trust Switchboard alternatives →
  • Agent Wormhole
    Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.
    B
  • mcpm
    MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
    B
  • MCP
    Authorize consequential AI agent actions before execution
    A
  • Projectmem
    Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.
    A
  • qikly
    Generates tests from acceptance criteria, then converges code with an agent that never sees them.
    A

More from paul-salviani