AgentUtility Wordmint — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Wordmint fixed-price text-task tools: Do task definitions and prices remain explicit without disguising model-generated conclusions as facts?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Pay-per-call named LLM text tasks with x402 USDC settlement from an agent-held wallet.

What we know

AgentUtility cluster exposing many named text/LLM tasks at posted per-call prices. No AgentUtility API key is required; an agent-held Base USDC wallet signs x402 payments.

Maintenance / activity evidence

@agentutility/mcp-wordmint 0.17.5 published 2026-08-09T19:02:54.276Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
LLM-task invocation plus per-call payment authority. Writes: Spend USDC per task call.
EVM private key.
Sensitive access: Wallet key, Prompt/input content

Payment key and prompt confidentiality are the main risks.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do task definitions and prices remain explicit without disguising model-generated conclusions as facts?

The bounded review of the publisher's documented Wordmint fixed-price text-task tools and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Payment key and prompt confidentiality are the main risks.
LLM-task invocation plus per-call payment authority.
EVM private key.
Prompt/input content is processed by AgentUtility/upstream providers.
Reviewed write actions: Spend USDC per task call
Sensitive access: Wallet key, Prompt/input content
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
Every call spends USDC.
Live tool catalog/prices change over time.
Private payment key must be protected locally.
Prompts/data are sent to AgentUtility/upstream models.

Original activity observations

@agentutility/mcp-wordmint 0.17.5 published 2026-08-09T19:02:54.276Z

Technical identity

npm/@agentutility/mcp-wordmint

Exact implementation source: https://www.npmjs.com/package/@agentutility/mcp-wordmint ↗
Reviewed resource type: Gateway
Package identity: npm:@agentutility/mcp-wordmint

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
@agentutility/mcp-wordmint
Recorded package identity, distribution or download evidence.
Evidence source ↗
agentutility.ai/mcp/
Source material retained for this review.
Includes references whose attribution is not established.
Registry source ↗
registry.modelcontextprotocol.io/
Source material retained for this review.
Includes references whose attribution is not established.

Setup · Watchlist

Gateway setup

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Warning

Financial risk: package may sign and pay for calls or buy tokens. Never use production wallet/private key to test. Obtain explicit spending approval.
A private key is not an API key; do not expose it in project files, screenshots, logs, or chat transcripts.
Chargeable by default for tool invocation: per-call USDC/x402 pricing. Tool listing or MCP registration is not a free-use guarantee.
Publisher baseline documentation retained; live recheck unavailable. This update does not establish a fresh publisher-source verification.
Reviewed actionability is baseline documentation only; client compatibility and runtime operation have not been verified.
Literal command/entry path confirmed against official README; does not validate runtime or host compatibility.
Prior reviewed safety note: Do not treat starting the MCP process as consent to transact.
Prior reviewed safety note: Do not invoke any tool merely to confirm connectivity: publisher prices its tools per call in USDC.
Prior reviewed safety note: Do not supply or fund X402_PRIVATE_KEY for initial registration.
Prior reviewed safety note: Do not delete user data or assume this cancels upstream authorizations.
Client removal, software uninstall, persistent-data deletion and credential revocation are separate actions.

Install / connect
Publisher instructions
Publisher-documented install or connect path; prerequisites and any extra host configuration remain required.
publisher install or stdio launch · retained baseline · Publisher instructions
npx -y @agentutility/mcp-wordmint
Configure / authenticate
MCP100 setup guide
Register local stdio MCP JSON with command npx and args ["-y","@agentutility/mcp-wordmint"], env X402_PRIVATE_KEY. Publisher requires funded Base USDC wallet for paid x402 calls; DO NOT substitute an API key or include private key in public config.
Check connection
Suggested check
Confirm MCP registration and tool discovery only. Calling tools can charge USDC; do not call a paid tool for verification.
Remove / uninstall / revoke
MCP100 setup guide
If registered in Claude Code under the name `agentutility-wordmint`, remove the client entry with `claude mcp remove agentutility-wordmint`. For other MCP hosts remove the matching server/connector in that host’s MCP settings. Remove a globally installed software package separately if applicable; this does not delete data or revoke a service credential.
Client removal, software uninstall, persistent-data deletion and credential revocation are separate actions.
Separate credential guidance (provider revocation is not verified): Publisher uses X402_PRIVATE_KEY for x402 USDC payments. Removing this variable or the MCP registration prevents new calls from this host but does not revoke the wallet private key. If exposed, rotate by creating a new wallet and handling any funds with wallet-provider guidance; no invented vendor revoke CLI.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove agentutility-wordmint

Official Documentation & Sources

https://www.npmjs.com/package/@agentutility/mcp-wordmint ↗

What it does

AgentUtility cluster exposing many named text/LLM tasks at posted per-call prices. No AgentUtility API key is required; an agent-held Base USDC wallet signs x402 payments.

Capability: AI & Reasoning
Resource type: Gateway
Best fit: Pay-per-call named LLM text tasks with x402 USDC settlement from an agent-held wallet.

Representative uses

Run named language tasks
Use fixed-priced summarization/extraction/transformation/writing utilities
Discover paid task catalog

Limitations

Every call spends USDC.
Live tool catalog/prices change over time.
Private payment key must be protected locally.
Prompts/data are sent to AgentUtility/upstream models.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: EVM private key.
Permissions: LLM-task invocation plus per-call payment authority.
Data handling: Prompt/input content is processed by AgentUtility/upstream providers.
Cost: pay_per_call_x402
Risk and cautions: Payment key and prompt confidentiality are the main risks.

Access scope and cautions

Write actions: Spend USDC per task call
Sensitive access: Wallet key Prompt/input content
Risk level: high

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Run named language tasks; Use fixed-priced summarization/extraction/transformation/writing utilities; Discover paid task catalog.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @agentutility/mcp-wordmint. Recorded transport: stdio. Recorded environment-variable notes: X402_PRIVATE_KEY. No configuration values are supplied here. Prerequisites: MCP client; funded Base wallet. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Agent-held EVM private key with USDC on Base.

Can it modify data or perform write operations?

Documented write actions include: Spend USDC per task call. Recorded permission boundary: LLM-task invocation plus per-call payment authority.

What data-handling boundary should I consider?

Prompt/input content is processed by AgentUtility/upstream providers. Recorded sensitive-access context: Wallet key; Prompt/input content.

What limitations and risks should I check before use?

Payment key and prompt confidentiality are the main risks. Every call spends USDC. Live tool catalog/prices change over time. Private payment key must be protected locally. Prompts/data are sent to AgentUtility/upstream models. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.

What cost model is recorded?

The reviewed cost model is pay per call x402. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.