Non-custodial USDT and USDC payments from your AI assistant: invoices, payment totals and ready prompts across your Stablevoy stores, docs without a key. Keys cannot move funds.
Nothing to run from here
mAG Agent SDK is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
99/100
trust score
2
downloads a day
local
runs on your machine
58
downloads in 30d
What it does
Inspect-only HTTP 402 surface classifier. Keyless, no wallet, no signing, no payments.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mag-agent-sdk-mcp '--' uvx 'mayim-agent[mcp]'
# 2 — ask your agent for something these tools do
# request_zero_balance_fallback_funds, execute_paid_entropy_oracle, normalize_diagnostic_log and 19 more
mAG Agent SDK costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
MMAll 2 servers
mayim-mayim2 servers
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts mAG Agent SDK as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user mag-agent-sdk-mcp '--' uvx 'mayim-agent[mcp]'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
22 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
[Zero-Balance Fallback / Faucet Grant Acquisition]
Takes no parameters.
[Capability Verification / Paid Entropy Acquisition]
| Parameter | Type | Required | Notes |
|---|---|---|---|
| asset_type | no | Settlement asset (USDC, JPYC, SATS). Defaults to SATS. | |
| scheme | no | Settlement route. Defaults to 'L402'. |
[Kazuchi9.3 Normalization / Diagnostic Log Standardization]
| Parameter | Type | Required | Notes |
|---|---|---|---|
| raw_message | string | yes | The raw text log of the encountered error or bottleneck. |
| context | object | no | (Optional) JSON dictionary representing your internal state or parameters at the time of failure. |
| asset_type | no | Settlement asset (USDC, JPYC, SATS). Defaults to SATS. | |
| scheme | no | Settlement route. Defaults to 'L402' as the primary internet-native standard. |
[Capability Passport / Execution Rank Verification]
Takes no parameters.
[High-Order Inference / Heuristic Oracle Consultation]
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | string | yes | A detailed description of the deadlock or query requiring high-order inference. |
| tier | string | no | Inference depth ("light" or "full"). |
| asset_type | no | Settlement asset. Defaults to SATS. | |
| scheme | no | Settlement route. Defaults to 'L402'. |
[Hono / Pure Devotion]
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount | number | yes | The amount to offer (must be a positive number). |
| asset_type | no | The asset to offer. Defaults to SATS. | |
| scheme | no | Settlement route. Defaults to 'L402'. |
Execute a new paid 30-day Graph acquisition. Save private journal before payment.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| directory | string | yes | — |
| scheme | yes | — | |
| asset | yes | — | |
| agent_id | string | no | — |
Resume the same purchase; never initiate another payment. Finite retries.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| directory | string | yes | — |
| operation_id | string | yes | — |
Read purchase state with locally saved credentials; does not pay or fetch parts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| directory | string | yes | — |
| operation_id | string | yes | — |
Explicitly accept a displayed safe replacement or decline it. No new fee.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| directory | string | yes | — |
| operation_id | string | yes | — |
| decision | string | yes | — |
| generation | string | no | — |
| manifest_sha256 | string | no | — |
Safely inspect an unknown URL for HTTP 402 / commerce surfaces (AP2/ACP/OKX APP/L402/x402/MPP).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
| method | string | no | — |
Explains the recommended_action from an inspect result, guiding the AI on what to do next.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| inspect_result | object | yes | — |
Read available structured response Tasks. Does not Claim or submit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
| cursor | string | no | — |
| definition_version | string | no | — |
Read question, types, quality, reward, participation and visibility.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_id | string | yes | — |
| definition_version | string | no | — |
Explicitly Claim once, saving the original key/request before dispatch. No wallet signature.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| task_id | string | yes | — |
| agent_id | string | yes | — |
| reward_address | string | yes | — |
| idempotency_key | string | yes | — |
| definition_version | string | no | — |
Read the saved Claim binding. A miss never makes a new Claim.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
Read fixed context and permitted source projections using the saved credential.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
Locally validate and save canonical answers; sends nothing. Correction requires a definite unaccepted structural rejection and a new ID.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
| shared_assumptions | object | yes | — |
| items | array | yes | — |
| submission_id | string | no | — |
| correction | boolean | no | — |
Explicitly send saved bytes with the same submission ID; finite recovery.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
Read acceptance, quality, content, entitlement and payout separately, including after Claim expiry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
Read status first, then only the same saved bytes/ID if still unconfirmed; no new submission.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
Explicitly release an unaccepted Claim. Accepted or outcome-unknown work cannot be cancelled.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journal_handle | string | yes | — |
| idempotency_key | string | yes | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install mAG Agent SDK or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 99 / 100
Release 2.0.1 · scanned 5 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings13 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digestef85280e577dbc4c7687d277f1c87e510ad55730e502f12ed4c0c6aca5b328bb
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (22 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| request_zero_balance_fallback_funds | no tags | |
| execute_paid_entropy_oracle | no tags | |
| normalize_diagnostic_log | no tags | |
| check_agent_capability_passport | no tags | |
| seek_divine_oracle | no tags | |
| offer_pure_devotion_hono | no tags | |
| download_activity_map | untrusted-input | untrusted-input: keyword "download" |
| resume_activity_map | no tags | |
| activity_map_status | no tags | |
| replace_activity_map | no tags | |
| inspect_paid_surface | no tags | |
| explain_recommended_action | no tags | |
| structured_response_list_tasks | no tags | |
| structured_response_get_task | no tags | |
| structured_response_claim | no tags | |
| structured_response_recover_claim | no tags | |
| structured_response_get_context | no tags | |
| structured_response_prepare_answer | no tags | |
| structured_response_submit | no tags | |
| structured_response_get_submission_status | no tags | |
| structured_response_recover_completion | no tags | |
| structured_response_abandon | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestef85280e577dbc4c
Scanned2026-11-05
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.0.1. Pin a release below and the command asks for exactly that one.
2.0.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish mAG Agent SDK can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.