MCP.Market

Trusty Squire MCP server

by Trusty-Squire·io.github.Trusty-Squire/mcp·v1.0.33·3 stars
No reviews yet

Credential broker that signs your AI agent up to SaaS dev tools, within a signed spending mandate.

B83/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

3 stars2.3k downloads/wk

Reviews

Write one

Nobody has reviewed Trusty Squire yet.

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

Trusty Squire tools (15)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_extract_failure

    Fetch the full DOM (and optionally the screenshot) of one extract-failure snapshot.

  • list_extract_failures

    List recent extract-failure diagnostic snapshots uploaded by the universal signup bot.

  • operate_act

    Take one action in a provisioning session, then return the resulting

  • operate_await_verification

    Read the user's OWN inbox through their signed-in browser session (no IMAP,

  • operate_captcha_gate

    Detect a captcha and drive the in-session captcha gate: returns {found, variant,

  • operate_extract

    Reveal masked keys and extract credentials from the current page: returns

  • operate_finish

    Close a provisioning session and tear down its browser. Always call this

  • operate_finish_task

    Finish an operate task with its OUTCOME, then close the session. kind=

  • operate_observe

    Re-read the current page of a provisioning session. DEFAULT is a COMPACT

  • operate_prepare_login

    Prepare username/password signup fields from the user's OWN email (captured

  • operate_remember

    Save the CURRENT successful operate session as a replayable operator-recipe

  • operate_seal_vault_credential

    For a sign-in page, retrieve a username/password credential only if the

  • operate_start

    Begin an interactive provisioning session: opens a scoped browser on the

  • operate_store_login

    After the service account is created, vault the sealed signup login (the

  • operate_use

    Replay a saved operator-recipe by name: opens a scoped browser at the recipe's

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

1 medium
  • Code scan103 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/bot/browser.js: …obe = await this.page .$eval(selector, (el) => { cons…
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Trusty Squire compares

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

Safety score
83/100
higher than 68% of 4,460 AI and agents servers
Tools
15
the typical AI and agents server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
3
more than 75% of 2,711 AI and agents servers
Downloads a week
2,312
more than 95% of 1,538 AI and agents servers with a package

What its tools let an agent do: 15 read

Install Trusty Squire in Claude Code, Cursor or VS Code

Runs npx -y @trusty-squire/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @trusty-squire/mcp
Add to Cursor

What the publisher says

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

Trusty Squire

Empower agents with auth and payments.

What you can do

Ask your coding agent to:

  • Get an API key. "Sign me up for Pinecone and get an API key." It signs up, verifies the email, creates the key, and stores it in your vault instead of the chat.
  • Sign in anywhere. It uses your Google or GitHub account on any site that offers it.
  • Buy things. "Order one Glow Serum from whitejade.xyz." You approve the purchase once, and your card number never reaches the agent.
  • Call APIs with stored keys. The agent uses a saved key without ever seeing it.
  • Finish setup. OAuth apps, dashboards, and verification steps, end to end.

Install

npx @trusty-squire/mcp connect

Sign in with Google or GitHub, and Trusty Squire adds itself to your coding agent. Restart the agent and ask for what you need.

To pick the agent yourself:

npx @trusty-squire/mcp connect --target=codex

Works with Claude Code, Codex, Cursor, OpenCode, Goose, Cline, Continue, and Hermes.

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

Trusty Squire: common questions

Is Trusty Squire MCP server safe?
Mostly: it is graded B (83/100). Read the Trusty Squire safety report
How do I install Trusty Squire?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Trusty Squire need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Trusty Squire maintained?
The last commit was 41 days ago (2026-09-24). The latest release is v1.0.33.
What can I use instead of Trusty Squire?
Servers from other publishers that do the same job: Attestix MCP server, Emilia Protocol MCP server and three.ws Provenance MCP server.
How does Trusty Squire compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,460 AI and agents servers); tools 15 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Trusty Squire

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

  • Attestix
    AI agent identity, signed credentials, delegated authority and governance evidence.
    A
  • Emilia Protocol
    Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
    B
  • three.ws Provenance
    Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
    More from nirholas →
    B