Wren Pre-sign Check

io.github.claudeisgodPublished by GitHub account claudeisgodv1.4.0Updated Oct 29, 2026

Check a tx, EIP-712 payload, text or Base token before your agent signs. Paid per call over x402.

The publisher's own server: check.tattoo: tattoo size and placement guide

VerifiedStreamable HTTPWeb executableFinanceSecurity & Monitoring

Overview

AI-generated overview

Remote MCP server that checks transactions, EIP-712 payloads, untrusted text and Base tokens before an agent signs or acts, paid per call in USDC.

What you can do
  • Check a transaction or EIP-712 typed-data payload before signing, returning block, review or allow with the decoded call and findings such as unlimited approvals, permits, Permit2 and setApprovalForAll
  • Screen untrusted text (replies, DMs, web pages, tool output, memory) for prompt-injection patterns after decoding base64, hex, Morse, leetspeak, ROT13, reversed and hidden Unicode, optionally flagging lookalike addresses
  • Inspect a Base ERC-20 before approving or transferring: code size, EIP-7702 delegation, name, symbol, decimals, supply, proxy and upgrade admin, ownership and privileged functions in the bytecode
  • Run a free fixed demo to see the report shape before paying
When to use it
Useful when an agent handles crypto signing or Base tokens and you want a pre-signing safety check, or when an agent acts on untrusted text and you want injection screening. The free demo lets you judge the output format first.
Requirements
Remote streamable HTTP endpoint; no authentication, environment variables or headers declared. Paid tools are billed per call over x402 in USDC on Base, so a wallet able to pay x402 is needed; presign_demo is free.
Before you install
Three of the four tools cost money per call (presign_check and token_facts $0.01, screen_text $0.003) in USDC on Base, so an agent can spend funds automatically. Verdicts are advisory: block means do not sign, review means ask a human. The server states nothing sent is stored, but payloads and addresses are sent to a third-party endpoint.

Installation

In SourceWeft

  1. Open Wren Pre-sign Check in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.claudeisgod%2Fwren-presign-check/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "wren-pre-sign-check": {
      "type": "http",
      "url": "https://wren-presign-check.wrenonbase.workers.dev/mcp"
    }
  }
}

Tools

4

presign_check

Pre-sign check

Call before your agent signs anything. Send tx fields (to, data, value, chainId), or typedData (an eth_signTypedData_v4 payload), or untrusted text, with an optional wren-guard policy. Returns block, review or allow, the decoded call and every finding: unlimited approvals, permits, Permit2, setApprovalForAll, EIP-7702 delegation, deployments, injected instructions and, with a policy, unknown recipients, caps and lookalike addresses. Static check, not a simulation. Costs $0.01 USDC on Base per call, paid over x402 (MCP transport): an unpaid call returns a PaymentRequired result, and an x402 MCP client retries with the payment in _meta["x402/payment"]. You sign one USDC authorisation for exactly that price to Wren's wallet: no approvals. Bad input is rejected before anything is charged.

ParameterstodatatextvaluepolicychainIdtypedData

screen_text

Prompt-injection screen

Call before your agent acts on untrusted text (a reply, DM, web page, tool output or memory). Returns safe, suspicious or malicious with the matched patterns, after decoding base64, hex, Morse, leetspeak, ROT13, reversed and hidden Unicode. Optional known: your own addresses, to flag poisoned lookalikes. Deterministic rules, no LLM. Costs $0.003 USDC on Base per call, paid over x402 (MCP transport): an unpaid call returns a PaymentRequired result, and an x402 MCP client retries with the payment in _meta["x402/payment"]. You sign one USDC authorisation for exactly that price to Wren's wallet: no approvals. Bad input is rejected before anything is charged.

Parameterstextrequiredknown

token_facts

Base token contract facts

Call before your agent approves, receives or sends a Base ERC-20. Returns code size, EIP-7702 delegation, name, symbol, decimals, supply, proxy and upgrade admin, owner or renounced, and which privileged functions the bytecode has (mint, pause, blocklist, fees, limits, trading switch, upgrade). Facts only: no grades, not investment advice. If Base can't be read, nothing is charged. Costs $0.01 USDC on Base per call, paid over x402 (MCP transport): an unpaid call returns a PaymentRequired result, and an x402 MCP client retries with the payment in _meta["x402/payment"]. You sign one USDC authorisation for exactly that price to Wren's wallet: no approvals. Bad input is rejected before anything is charged.

Parametersaddressrequired

presign_demo

Free pre-sign example

Free. Runs one fixed example (an unlimited approval, setApprovalForAll, a never-expiring permit, an EIP-7702 delegation, an injected memo or a normal x402 payment) through the same checker, so you can see the report shape before paying for presign_check.

Parametersnamerequired

Version history

1
  1. v1.4.0LatestOct 29, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Check integrations