Wren Pre-sign Check
Server Details
Check a tx, EIP-712 payload, text or Base token before your agent signs. Paid per call over x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool targets a distinct artifact: a transaction/typed-data payload (presign_check), a free fixed sample (presign_demo), an untrusted text string (screen_text) and a Base ERC-20 address (token_facts). The one real boundary blur is text: presign_check accepts 'untrusted text' and reports injected instructions, which overlaps with screen_text's purpose, so an agent could reasonably pick either. The 'call before signing' vs 'call before acting on text' framing mostly resolves it.
All names are snake_case with clear two-word structure, and the presign_ prefix neatly groups the paired check/demo tools. It is not a single consistent verb_noun scheme, however: presign_check and screen_text are verb-led while token_facts is noun-led. Minor deviation, still highly readable.
Four tools is lean but each maps to a real pre-action safety need, so nothing feels padded out for its own sake. The one questionable inclusion is presign_demo, a free documentation/sample endpoint rather than a genuine capability, though it does earn a modest place by showing the report shape before a paid call. No obvious missing companion tool at this scope.
The safety-check surface is well covered for its stated domain: payload decoding and findings, text injection screening with decoding layers, and token bytecode/privilege facts. Minor gaps remain, e.g. no way to inspect the spender/recipient address itself (contract vs EOA, verification status, reputation) beyond lookalike flagging against a caller-supplied known list. Coverage is otherwise coherent for a pre-sign gate.
Available Tools
4 toolspresign_checkPre-sign checkARead-onlyIdempotentInspect
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.
Inputs: to, data, text, value, +3 more.
presign_demoFree pre-sign exampleARead-onlyIdempotentInspect
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.
Inputs: name (required).
screen_textPrompt-injection screenARead-onlyIdempotentInspect
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.
Inputs: text (required), known.
token_factsBase token contract factsARead-onlyIdempotentInspect
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.
Inputs: address (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Check a Base contract, transaction or web page before you act. Free pricing, paid per call in USDC.
Checks before an agent acts: prompt-injection scan, honeypot check, x402 preflight. 3 free calls.
Use before signing an EVM tx or EIP-712 message: risk flags + verdict. Informational, no simulation
Paid x402 pre-checks for agents: phishing links, Base tokens, EIP-712 permits, calldata, DNS.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to run pre-sign risk checks on transactions, approvals, EIP-712 signatures, token addresses, wallet approvals, sanctions screening, and prompt-injection texts, returning green/orange/red verdicts with machine-readable reason codes before signing.1AGPL 3.0
- AlicenseAqualityCmaintenanceEnables agents to run pre-signature security checks: identifying who can replace a Solana program's code or control an EVM contract's upgrades, surfacing dependency advisories for lockfiles, scanning public repos before release, and setting 30-day signed-webhook alerts on changes. Calls are paid per use in USDC over x402 from a wallet with per-call caps and a session budget.853 npmMIT
- AlicenseNot gradedqualityCmaintenanceChecks token contract safety for honeypot, tax, proxy, blacklist, ownership risks, and returns a risk score, enabling rug-pull protection for agents via pay-per-call x402 micropayments.MIT
- FlicenseAqualityCmaintenanceAgent-Level Transaction Safety Oracle. Before an AI agent signs a blockchain transaction, it returns a SAFE/UNSAFE verdict with a SENTINEL Score (AAA-D) and risk flags. Pay-per-call $0.005 USDC via x402 on Base.1-
Glama MCP Gateway
Add one secure layer between your agents and this server.