MCP.Market

Mapleai MCP server

by veenrek·io.github.veenrek/mapleai-mcp·v0.3.1
No reviews yet

Pay-per-request GPT chat, embeddings, agents and prepaid keys with local x402 USDC signing

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
Growing

0 stars45 downloads/wk

Reviews

Write one

Nobody has reviewed Mapleai yet.

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

Mapleai tools (8, 2 write)

write = sends, deletes, buys or posts

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

  • agent_executewrite action

    Paid autonomous agent execution: give a natural-language task, a multi-step agent reasons and calls tools

  • buy_prepaid_tapwrite action

    Paid one-shot: buys a prepaid MapleAI API key with local x402 USDC.

  • chat_completion

    Call a MapleAI model with local x402 USDC payment. Maximum spend per call is MCP_MAX_PAYMENT_USDC (default 0.10).

  • embed_text

    Free 2048-dim embeddings via NVIDIA nemotron-3-embed-1b. No payment.

  • jev_decide

    Paid Jev structured decision (jev-latest): evaluate named questions against a state.

  • list_models

    List MapleAI models and prices on a supported network. Free call.

  • prepaid_chat

    Chat completions paid from a prepaid key instead of x402: no wallet, no per-call payment — token spend is

  • prepaid_status

    Free: check a prepaid MapleAI key (valid flag, reason, tokens total/used/reserved/remaining).

Public scan report

scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mapleai compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
80/100
higher than 60% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
45
more than 37% of 12,191 servers with a package

What its tools let an agent do: 6 read · 2 change

Install Mapleai in Claude Code, Cursor or VS Code

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

claude mcp add mapleai-mcp -- npx -y mapleai-mcp
Add to Cursor

What the publisher says

From the Mapleai repository's README, as published. We do not edit it. Read it on GitHub

MapleAI — GPT, Claude and Agent APIs with x402 Pay-Per-Request

OpenAI-compatible GPT and Anthropic-native Claude chat, multi-step agent execution, image, audio, X (Twitter) intel, embeddings and structured-decision APIs behind one endpoint. No accounts, no subscriptions, no API keys for the pay-per-request tier — an agent pays per call in USDC over the x402 protocol. Prepaid API keys are available for clients that prefer a token budget over per-request payments.

Live endpoints

Prepaid key endpoint (shared): https://mapleai.shop/v1

Models and pricing

GPT (per 1M tokens)

A request is quoted as counted input tokens × input rate + requested output tokens × output rate, plus the network settlement fee (about $0.001; the exact amount is always in the 402 challenge). Failed calls (HTTP ≥ 400) are cancelled, not settled.

Claude (per 1M tokens)

Native Anthropic Messages API at POST /v1/messages (system prompt, content blocks, SSE events, required max_tokens; the system prompt is billed as input tokens). Also reachable via the OpenAI-compatible /v1/chat/completions.

Agent execution

POST /v1/agents/execute — multi-step agent loop (reason → call tools → final answer), Cluster Protocol-compatible response. Optional SSE step streaming with "stream": true (step events as tools run, done with the final result). Built-in tools: deterministic calculator, dataanalysis (statistics over up to 500 numbers), keyless websearch (Exa) and fetch_url. Per-step timeout returns partial results instead of a bare 502.

Charged as a ceiling — base + maxsteps × per-step price (+ tool ceilings), like maxtokens for chat; up to 20 steps per task.

Images (per image)

POST /api/v1/images/generations and POST /api/v1/images/image2image (edit a PNG/JPEG/WebP data URI, max 10 MB). On Solana these routes settle upfront (image generation outlives a Solana blockhash) and retry transient upstream failures inside the same paid request.

Audio (per request)

Shortened. The full README is on GitHub.

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

Mapleai: common questions

Is Mapleai MCP server safe?
Mostly: it is graded B (80/100). Read the Mapleai safety report
How do I install Mapleai?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Mapleai need an API key?
Yes. The registry entry asks for EVM_PRIVATE_KEY, SVM_PRIVATE_KEY.
Is Mapleai maintained?
The last commit was 22 days ago (2026-10-13). The latest release is v0.3.1.
How does Mapleai compare with other MCP servers?
safety score 80/100 (higher than 60% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.