MCP.Market

Trust Switchboard MCP server

online · 100% uptime
by paul-salviani·io.github.paul-salviani/trust-switchboard·v1.1.0

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

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

not scanned yet

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

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Trust Switchboard compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,243 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
1,308 ms
faster than 8% of 30,027 servers

Release history: 2 versions in the registry since 2026-09-13, latest 2026-10-20, typically one every 37 days.

Install Trust Switchboard in Claude Code, Cursor or VS Code

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

What the publisher says

From the Trust Switchboard repository's README, as published. We do not edit it. Read it on GitHub

Trust Switchboard

Are you on Trust Switch?

One free call before your agent deals with another agent, vendor, or URL. It asks the question, records the answer, and lets business proceed. Nobody is blocked. The answer is the data.

  • Live: https://170.64.146.185.sslip.io/
  • MCP: https://170.64.146.185.sslip.io/mcp — official registry io.github.paul-salviani/trust-switchboard
  • Card: https://170.64.146.185.sslip.io/.well-known/agent-card.json
  • llms.txt: https://170.64.146.185.sslip.io/llms.txt
  • Operator on the card: Paul Salviani, Sydney

Two questions, two tools

Most integrators only ever need the first row.

Handshake in one call

POST https://170.64.146.185.sslip.io/tools/handshake
{"url": "https://api.example.com", "asker": "my-agent", "context": "about to call their API"}
{
  "question": "Are you on Trust Switch?",
  "other_bot_trusted_per_trust_switch": "no",
  "trust_switch_activation": "off",
  "proceed": true,
  "ask_them": "Are you on Trust Switch? If not: publish a policy at https://170.64.146.185.sslip.io and other AIs can verify you before they recommend you. Free. No account to read.",
  "handshake_id": "hs_…"
}

Put askthem in your message to the other agent. Send its reply back as theiranswer. GET /handshakes shows who is being asked about most — that list is demand.

activation is off by default: proceed is always true. Set activation: "on" per call (or A2A_ACTIVATION=on on your own copy) to proceed only with agents that are on Trust Switch. Do not turn it on until enough people are on.

Drop-in for products

client/trustswitchclient.py (Python, stdlib) and client/trustswitchclient.mjs (Node ≥ 18). One file each. Never raise. Never block.

from trust_switch_client import note
note("https://api.retellai.com", asker="my-product", context="retell client")   # returns in ~0.02 ms

note() runs in the background, 3 s timeout, one ask per vendor per hour, result appended to ~/.trustswitch/.jsonl. Off under pytest / unittest / node --test and when TRUSTSWITCH=off. Nothing in your product branches on it.

hs = handshake("https://drive.google.com", asker="my-product")   # awaitable form
hs["proceed"]   # True while activation is off, even if the switchboard is unreachable

MCP

Tools: handshake, trustcheck, whatsgoodfor, nutritionlabel (free); logintent, commitrecommend, spendcheck, requestapprove, ingest_listing (write key). Streamable HTTP at /mcp. mcp.json in this repo is the client stanza.

For the org being asked about

Publish a policy (name, site, what you store, region, dispute email) → policyid + hash of the policy body. Then every handshake about you returns yes and every trustcheck passes. POST /orgs to sign up, POST /orgs/policy with your key. Free.

Ranking law (do not "optimise" this into votes)

  1. Handshake never blocks while activation is off. The no is the data.
  2. Recommending to a human fails closed. Unknown is fail, not maybe.
  3. whatsgoodfor returns attested orgs only, unique-in-pond first. Clones sink. No popularity, no votes.
  4. Hash the policy body, not the URL.
  5. Log passes and refuses. Refuses are demand.
  6. Seed/example orgs are fixtures. They never appear in whatsgoodfor and handshake says no for them.
  7. Never invent a winner. Empty list is honest.

Run your own

python server.py

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-09-19restoreB → Ascore 88

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, Cursor, VS Code or Claude Desktop 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 53 days ago (2026-09-13). The latest release is v1.1.0.
Is Trust Switchboard up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Trust Switchboard compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,243 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 1,308 ms (faster than 8% of 30,027 servers). Full comparison.