io.github.veenrek/mapleai-mcp
NPM · MAPLEAI-MCP
Pay-per-request GPT chat, embeddings, agents and prepaid keys with local x402 USDC signing
Available components
Last scanned (20 hours ago)
Scores higher than 36% of npm servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security99
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 232 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (UNLICENSED) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 16 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability54
- AI-judged instruction clarity (fair).Partial
- Context-footprint check failed: tool/resource definitions use about 1059 tokens (~132/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management17
- Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agent_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Oct 26 +24
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- Tool coverage: unverified → 100 ▲ functional
- Stability: unverified → 0.00 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- First check of Tool coverage: 0 functional
- First check of Schema quality: fail functional
- First check of Schema quality: fair functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: 0 functional
- 13 Oct 26 0
- Security disclosure: unverified → fail ▼ functional
- 12 Oct 26 +19
- Malware scan: unverified → pass ▲ security
- Known CVEs: partial → pass ▲ security
- Stability: Stability not yet verified: this package could not be installed in a clean environment, so we have no schema to compare. security
- Tool safety: Tool safety not yet verified: this package could not be installed in a clean environment, so we have no tool text to scan. security
- Security disclosure: fail → unverified ▼ functional
- Schema quality: Schema quality not yet verified: this package could not be installed in a clean environment, so we have no schema to assess. functional
- Capabilities: Protocol version not yet verified: this package could not be installed in a clean environment, so we never saw its MCP handshake. functional
- Tool coverage: Tool coverage not yet verified: this package could not be installed in a clean environment, so we have no tool definitions to assess. functional
- Dependency health: partial → 0.94 functional
- 6 Oct 26 17
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 22 Oct 2026 · Analysed npm/mapleai-mcp@0.3.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 232 packages
| Packages resolved | 232 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
agent_execute ~248
Paid autonomous agent execution: give a natural-language task, a multi-step agent reasons and calls tools (calculator, fetch_url, web_search via the keyless Exa index, data_analysis; on deployments with a sandbox executor also code_exec — python/javascript/typescript, $0.002 per call, max 3 per task). Engines: agents/oss-20b (cheap — $0.002 base + $0.0005/step) and agents/gpt-6-sol (premium — $0.004 base + $0.004/step). Charged at the max_steps ceiling plus allowed-tool fees; the worst case (20 steps + 3 code_exec, ~$0.09) still fits the default MCP_MAX_PAYMENT_USDC=0.10. With stream=true the reply contains the live SSE step transcript; the agent.execution object always includes the full step trace, sources, usage and charged_ceiling_usd.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | – |
| max_steps | integer | – | – |
| model | string | – | – |
| network | string | – | – |
| stream | boolean | – | – |
| task | string | yes | – |
| tools | array | – | – |
No output schema declared.
No examples provided.
buy_prepaid_tap ~287
Paid one-shot: buys a prepaid MapleAI API key with local x402 USDC. With no arguments it buys the smallest pack of the cheapest model currently on sale (about $0.008). Optional model (one of openai/gpt-5.6-sol, openai/gpt-5.6-terra, openai/gpt-6-luna, openai/gpt-6-sol, when on sale) and tokens (100000..1000000 in steps of 100000) pick a bigger pack: price = tokens x model input rate per million + settlement fee, so 1M tokens of openai/gpt-6-sol is about $1.40 and the largest pack (1M of openai/gpt-5.6-sol) about $2.80. Purchases are capped by MCP_MAX_PREPAID_USDC (default 3.00, covers the largest pack) — not by MCP_MAX_PAYMENT_USDC. The key is an OpenAI-compatible Bearer credential at https://mapleai.shop/v1 — spend it there or with the prepaid_chat tool right here; the network gateways also accept it same-origin under /prepaid/v1/*. Store the returned code — it is the only credential.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | – |
| network | string | – | – |
| tokens | integer | – | – |
No output schema declared.
No examples provided.
chat_completion ~67
Call a MapleAI model with local x402 USDC payment. Maximum spend per call is MCP_MAX_PAYMENT_USDC (default 0.10).
| Name | Type | Req | Description |
|---|---|---|---|
| max_tokens | integer | – | – |
| messages | array | yes | – |
| model | string | yes | – |
| network | string | – | – |
No output schema declared.
No examples provided.
embed_text ~106
Free 2048-dim embeddings via NVIDIA nemotron-3-embed-1b. No payment. Send one string or up to 128 strings; use input_type "query" for questions and "passage" for documents. encoding_format "float" (default) returns number arrays, "base64" returns compact base64 vectors.
| Name | Type | Req | Description |
|---|---|---|---|
| encoding_format | string | – | – |
| input | – | yes | – |
| input_type | string | – | – |
| network | string | – | – |
No output schema declared.
No examples provided.
jev_decide ~77
Paid Jev structured decision (jev-latest): evaluate named questions against a state. About $0.001 per short call via x402 USDC. Each question needs type (noul, choice or score) and instructions.
| Name | Type | Req | Description |
|---|---|---|---|
| network | string | – | – |
| questions | object | yes | – |
| state | string | yes | – |
No output schema declared.
No examples provided.
list_models ~29
List MapleAI models and prices on a supported network. Free call.
| Name | Type | Req | Description |
|---|---|---|---|
| network | string | – | – |
No output schema declared.
No examples provided.
prepaid_chat ~153
Chat completions paid from a prepaid key instead of x402: no wallet, no per-call payment — token spend is bounded by the key budget. Send the oms_buy_ code from buy_prepaid_tap (or the website) plus model and messages. The key is bound to one model; a wrong model is answered 403 with the key's allowedModels. Runs same-origin on the selected network at /prepaid/v1/chat/completions (and identically at https://mapleai.shop/v1/chat/completions).
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| max_tokens | integer | – | – |
| messages | array | yes | – |
| model | string | yes | – |
| network | string | – | – |
No output schema declared.
No examples provided.
prepaid_status ~92
Free: check a prepaid MapleAI key (valid flag, reason, tokens total/used/reserved/remaining). Send the oms_buy_ key bought via buy_prepaid_tap or the website. Keys are global — the check runs same-origin on the selected network (and identically at https://mapleai.shop/v1/prepaid/status).
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | – |
| network | string | – | – |
No output schema declared.
No examples provided.
How do I install the io.github.veenrek/mapleai-mcp server?
io.github.veenrek/mapleai-mcp runs locally as an npm package, launched with npx -y mapleai-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · mapleai-mcp
claude mcp add veenrek-mapleai-mcp -- npx -y mapleai-mcp
What is the io.github.veenrek/mapleai-mcp server?
io.github.veenrek/mapleai-mcp is listed in the public MCP registry as io.github.veenrek/mapleai-mcp. Pay-per-request GPT chat, embeddings, agents and prepaid keys with local x402 USDC signing. This page covers its npm package (mapleai-mcp).
Is the io.github.veenrek/mapleai-mcp server safe to use?
io.github.veenrek/mapleai-mcp scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.veenrek/mapleai-mcp server expose?
io.github.veenrek/mapleai-mcp exposes 8 tools: list_models, embed_text, chat_completion, jev_decide, agent_execute, and 3 more. Their descriptions and schemas cost roughly 1,059 tokens of context every time the server is loaded.
Is the io.github.veenrek/mapleai-mcp server still maintained?
io.github.veenrek/mapleai-mcp is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.veenrek/mapleai-mcp server under?
io.github.veenrek/mapleai-mcp declares the UNLICENSED licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.