MCP.Market

Tollary Agent Transaction Guard MCP server

by tollary.p-e.kr·kr.p-e.tollary/agent-transaction-guard·v0.1.0
No reviews yet

Local fit-check and safe integration guidance for non-custodial Base USDC agent transactions.

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

full report

Adoption
New

0 stars38 downloads/wk

Reviews

Write one

Nobody has reviewed Tollary Agent Transaction Guard yet.

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

Tollary Agent Transaction Guard tools (4, 1 write)

write = sends, deletes, buys or posts

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

  • tollary_fit_check

    Read-only local project fit check. It skips secrets and makes no network, wallet, or payment call.

  • tollary_free_lintwrite action

    Submit exactly {transaction, mandate} to the free structural lint. It makes no RPC, wallet, or payment call.

  • tollary_get_integration_plan

    Return the non-custodial integration sequence and prohibited secret-handling paths.

  • tollary_inspect_offer

    Fetch public product, readiness, and legal metadata without paying or connecting a wallet.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

no findings
  • Code scan7 source files scanned25/25
  • –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 60 days ago12/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year5/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Tollary Agent Transaction Guard 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 4,461 AI and agents servers
Tools
4
the typical AI and agents server has 6
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
38
more than 28% of 1,554 AI and agents servers with a package

What its tools let an agent do: 3 read · 1 change

Install Tollary Agent Transaction Guard in Claude Code, Cursor or VS Code

Runs npx -y tollary on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add agent-transaction-guard -- npx -y tollary
Add to Cursor

What the publisher says

From the Tollary Agent Transaction Guard repository's README, as published. We do not edit it. Read it on GitHub

Tollary

Experimental beta — Base Sepolia testnet only. No transaction-safety,

recipient-identity, legal-compliance, settlement, or loss-prevention

guarantee is made. Base Mainnet sales are disabled.

Tollary is a non-custodial Agent Transaction Guard for autonomous Base USDC payments. It checks an exact, owner-mandated transaction immediately before a customer-owned AWS KMS signer can sign it.

This repository contains the open-source local fit-check/MCP client, immutable publication metadata, and guarded npm/MCP release workflows. It does not contain customer keys, payment credentials, hosted-service state, or private backend operations.

Try the client

npx tollary fit-check --project .
npx tollary inspect
npx --yes --package tollary tollary-mcp

The client never accepts a raw wallet or AWS private key. The fit check is local and skips credentials, dependencies, vendor directories, and build output. Inspect mode reads only Tollary's public metadata endpoints.

The hosted service currently exposes Base Sepolia testnet payment terms only. A published package does not mean that Base Mainnet sales are active. Check /api/readiness and /api/legal before every purchase. The npm beta must be selected explicitly with tollary@beta; no latest release is created by the bootstrap workflow.

Repository layout

  • packages/tollary — npm CLI and stdio MCP server
  • distribution/github-action — local, bounded fit-check action
  • .github/workflows — manual, environment-protected npm/MCP publishing
  • scripts — fail-closed publication and namespace validation

The local client is MIT-licensed. Tollary's hosted API, service logic, trademarks, and commercial output are not granted under that license.

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

Grade history

  • 2026-10-30downgradeA → Bscore 83

Tollary Agent Transaction Guard: common questions

Is Tollary Agent Transaction Guard MCP server safe?
Mostly: it is graded B (83/100). Read the Tollary Agent Transaction Guard safety report
How do I install Tollary Agent Transaction Guard?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Tollary Agent Transaction Guard need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Tollary Agent Transaction Guard maintained?
The last commit was 66 days ago (2026-08-31). The latest release is v0.1.0.
What can I use instead of Tollary Agent Transaction Guard?
Servers from other publishers that do the same job: Agoragentic Agent OS MCP server, HOL Guard MCP server and IWE (iwe.md) MCP server.
How does Tollary Agent Transaction Guard compare with other AI and agents MCP servers?
safety score 83/100 (higher than 68% of 4,461 AI and agents servers); tools 4 (the typical AI and agents server has 6); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Tollary Agent Transaction Guard

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

  • Agoragentic Agent OS MCP
    Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • Actual Budget MCP Server
    MCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.
    B
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A