Back to Browse

Ai Agents MCP Server

Developer ToolsLow Risk10.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Pay-per-call AI agents over x402. Settled in USDC on Base with a per-call spending cap.

About

Pay-per-call AI agents over x402. Settled in USDC on Base with a per-call spending cap.

Security Report

10.0
Low Risk10.0Low Risk

Valid MCP server (3 strong, 4 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.

9 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

env_vars

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Private key of a dedicated, low-balance wallet holding USDC on Base. Signs gasless EIP-3009 payment authorizations. Without it, paid tools return payment instructions instead of paying.Required

Environment variable: AGENT_PRIVATE_KEY

Maximum USDC the client will authorize for a single tool call. Calls priced above it are refused.Optional

Environment variable: MAX_USDC_PER_CALL

Hub API key sent as X-API-KEY. Bypasses payment.Required

Environment variable: AGENTS_API_KEY

Hub base URL (https only; http allowed for localhost).Optional

Environment variable: AGENTS_BASE_URL

core (default: 14 web, document and code-security tools), all, or a comma-separated list of agent or package ids to list as tools.Optional

Environment variable: AGENTS_PROFILE

"all" or a comma-separated list of package ids whose checks are listed as individual tools instead of one tool per package.Optional

Environment variable: AGENTS_PACKAGES

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "ai-agents-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@writerslogic/ai-agents-mcp@0.3.0"
      ],
      "env": {
        "AGENTS_API_KEY": "your-agents-api-key-here",
        "AGENTS_PROFILE": "your-agents-profile-here",
        "AGENTS_BASE_URL": "your-agents-base-url-here",
        "AGENTS_PACKAGES": "your-agents-packages-here",
        "AGENT_PRIVATE_KEY": "your-agent-private-key-here",
        "MAX_USDC_PER_CALL": "your-max-usdc-per-call-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

@writerslogic/ai-agents-mcp

An MCP server that exposes the WritersLogic x402 agent hub as tools. By default it lists a focused set of 11 web, document and code-review tools (web search, page and PDF to markdown, page capture, transcription, PII redaction, company and lead research, pre-merge review, EU CRA readiness). Set AGENTS_PROFILE to list more. Calls are priced in USDC and paid over x402 on Base, with no gas needed from the buyer.

The server is a thin client: it fetches the hub catalog, registers a tool per agent, forwards calls over HTTPS, and signs a payment authorization when the hub asks for one and your spending cap allows it.

Install

Requires Node.js 20 or later. No global install is needed; MCP clients run it with npx, which builds it from this repository on first run.

{
  "mcpServers": {
    "writerslogic-ai-agents": {
      "command": "npx",
      "args": ["-y", "@writerslogic/ai-agents-mcp"],
      "env": {
        "AGENT_PRIVATE_KEY": "0x...",
        "MAX_USDC_PER_CALL": "1.00"
      }
    }
  }
}

Put that block in your client's MCP configuration:

ClientConfig file
Claude Desktopclaude_desktop_config.json (Settings, Developer, Edit Config)
Cursor~/.cursor/mcp.json (or .cursor/mcp.json in a project)
Windsurf~/.codeium/windsurf/mcp_config.json
Clinecline_mcp_settings.json (MCP Servers, Configure MCP Servers)
Claude Codeclaude mcp add writerslogic-ai-agents -e AGENT_PRIVATE_KEY=0x... -- npx -y @writerslogic/ai-agents-mcp

Omit AGENT_PRIVATE_KEY to browse and to see prices: paid tools then return the payment instructions instead of paying.

Configuration

VariableDefaultPurpose
AGENT_PRIVATE_KEYunsetPrivate key of the wallet that pays. Needs USDC on Base, no ETH. Use a dedicated low-balance wallet.
MAX_USDC_PER_CALL1.00Per-call spending cap. A call whose price is above it is refused before anything is signed.
AGENTS_API_KEYunsetSent as X-API-KEY. Bypasses payment.
AGENTS_BASE_URLhttps://agents.writerslogic.comHub URL. Must be https; plain http is accepted for localhost only.
AGENTS_TIMEOUT_MS120000Timeout for tool calls (1000 to 600000). The catalog fetch uses at most 15 s.
AGENTS_PROFILEcoreWhich hub agents become tools: core (the default set above), all (the whole hub, 80+ tools), or a comma-separated list of agent or package ids.
AGENTS_PACKAGESunsetall, or a comma-separated list of package ids, to list those packages' checks as individual tools instead of one tool per package.

Tools

Tools are discovered from the hub catalog (GET /api/v1/catalog?view=tools) and package index (GET /api/v1/packages) when the server starts, and refreshed on tools/list after ten minutes, so the live list is authoritative. Tool names are the agent or package id with every character outside A-Za-z0-9_ replaced by _. Each agent tool takes the agent's own input schema.

Small single-purpose checks ($0.005 each) are grouped into one tool per package, such as money_math_kit, so the tool list stays short. A package tool takes one of:

  • {"describe": true, "check": "<id>"}: free. Returns the check's input schema and an example input, from GET /api/v1/packages/<id>. Without check it lists the package's checks.
  • {"check": "<id>", "input": {...}}: runs one check at its own price.
  • {"calls": [{"check": "<id>", "input": {...}}, ...]}: runs up to 20 checks from the package under one $0.02 payment through /api/v1/micro-batch. Stateful and network checks are rejected before payment.

Arguments are validated locally first, so a check outside the package or a malformed call never reaches the hub. A hub without a package index gets one tool per agent. Agents at the time of writing:

ToolPrice (USDC)Description
search_web0.01Web search: licensed Exa/Brave results with snippets
read_page0.01Page contents: URL to clean Markdown or text
capture_page0.02Page capture: screenshot or PDF of a public URL
convert_document0.02Document to Markdown with per-page hashes and offsets
transcribe_audio0.25Transcribe an audio or video file URL (Whisper, timestamps, SRT, VTT)
redact_text0.05Selective PII redaction with a self-check
lookup_company0.05Company identity: name, domain, LEI, VAT, CIK or ticker to one verified legal entity
enrich_lead0.50Autonomous Lead Enrichment
build_battlecard1.50SaaS Pricing & Competitor Battlecard Spy
review_code_changes0.60Pre-merge Review Pack
check_cra_readiness2.40EU CRA Readiness Check

Also always available, and free:

ToolDescription
verify_provenancePOSTs to /api/v1/verify-provenance to check the _provenance record on a paid result.

A paid result is the hub's JSON response, returned unchanged as text content.

How payment works

  1. The tool POSTs your arguments to the agent endpoint.
  2. If the hub answers 402, it sends a base64 PAYMENT-REQUIRED header (x402 v2) listing an exact scheme requirement: network eip155:8453, USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913, an atomic amount (6 decimals), payTo, and the token's EIP-712 name and version.
  3. If AGENT_PRIVATE_KEY is set and amount is at most MAX_USDC_PER_CALL, the client signs an EIP-3009 TransferWithAuthorization (EIP-712, USDC domain on chain 8453) for exactly that amount to payTo, valid for the requirement's timeout, with a random nonce.
  4. It retries the same request once with the base64 PAYMENT-SIGNATURE header. The hub's facilitator submits the transfer and pays the gas.
  5. The result is returned. If the retry is not accepted, the error is returned and nothing further is sent.

If no key is configured, or the price is over the cap, the tool returns an error that states the price, network, asset and payTo, and no signature is produced.

Provenance

Paid results carry a _provenance record next to data. Pass the whole {data, _provenance} object to verify_provenance to check it against the hub. The request body is forwarded as given.

Security

  • The key stays local. AGENT_PRIVATE_KEY is read once from the environment, used only to sign typed data, and never logged or sent anywhere. Authorizations are signatures; the client never broadcasts a transaction.
  • The cap is per call, not per session. An agent that calls tools in a loop can spend MAX_USDC_PER_CALL each time. Fund the wallet with only what you are willing to lose, and lower the cap to the most expensive tool you actually want to allow.
  • Only USDC on Base is signed for. Challenges naming another network, asset, or transfer method are refused, so a malicious or compromised hub cannot ask for a different token. Base Sepolia (eip155:84532) USDC is also accepted for testing.
  • Catalog entries are untrusted. Endpoints must resolve to the hub's own origin, ids and prices are validated, and redirects are never followed, so credentials and signatures are not sent to other hosts.
  • Bounds. Requests are limited to 1 MiB, responses to 2 MiB, and every request has a timeout.
  • Stdout is the MCP stream. Logs go to stderr only; they include the paying address and each payment amount, never the key.
  • Anyone who holds a signed authorization before it expires could submit it, up to the signed amount and to payTo only.

Development

npm install
npm run build
npm test

Tests run against a local mock hub and verify the EIP-3009 signature by recovering the signer, the cap at limit-1, limit and limit+1, and an end-to-end stdio session against dist/index.js. No network access or funds are involved.

License

Apache-2.0. Copyright 2026 WritersLogic.

Reviews

No reviews yet

Be the first to review this server!