Name: tab
Author: paidwithtab

tab MCP

Agents pay per call over HTTP 402: 8,600+ API routes, owner-signed budgets, signed receipts.

Grade A Local · stdio No auth needed 5 tools v2.4.0 · 23 Oct 2026 MIT

No reviews yet by paidwithtabnpm 1,847 Runs on your machine, nothing hosted

93/100

trust score

312

downloads a day

local

runs on your machine

downloads in 30d

What it does

Agents pay per call over HTTP 402: 8,600+ API routes, owner-signed budgets, signed receipts.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user paidwithtab-tab-mcp '--' npx -y paidwithtab mcp

# 2 — ask your agent for something these tools do
#   tab_limits, tab_search, tab_discover and 2 more

tab costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

paidwithtab1 server

1 category

All 1 server

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 tab 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 Node.js — the current LTS (24) is the safe choice; npx 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 paidwithtab-tab-mcp '--' npx -y paidwithtab 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 asks of you

Nothing is required, but it can take TAB_AGENT (Agent key file. Default ~/.tab/agent.json, which `npx paidwithtab init` creates with a mandate and starter credits.), TAB_MANDATE (Owner-signed mandate file. Default ~/.tab/mandate.json.), TAB_MAX_PER_CALL (Refuse any single call priced above this many dollars, e.g. 0.05.), TAB_CATALOG (Catalog to search. Default https://paidwithtab.com.) if you want to set them.

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

5 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.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

What this agent is allowed to spend: the mandate terms (budget, window, per-call cap, allowed realms, expiry) and the client-side per-call cap.

No parameter schema on file.

Search the tab catalog for paid API routes by keyword. Returns callable URLs with prices, cheapest first. Each result names its currency: USD, or the token a gateway charges in; this agent can only pay in the currency tab_limits reports.

Parameter	Type	Required	Notes
query	string	yes	keywords to search route names and descriptions
max_price	string	no	optional price ceiling in this agent's currency, e.g. "0.01"; routes priced in other currencies are left out
limit	number	no	how many routes to return, best matches first (default 20, at most 100); the result says how many matched in total

Fetch a tab gateway discovery document (/.well-known/tab) listing its realm, rail and priced routes.

Parameter	Type	Required	Notes
origin	string	yes	gateway origin, e.g. https://pay.example.com

Fetch a URL, paying per request over HTTP 402 within the mandate: tab gateways, and x402 sites (USDG on Robinhood Chain, USDC on Base) from the agent's own funded address. Returns status, the payment receipt or x402 settlement (if any) and the body.

Parameter	Type	Required	Notes
url	string	yes	—
method	string	no	HTTP method, default GET
body	string	no	request body for POST/PUT/PATCH

Check the mandate owner's available balance on the gateways the catalog knows about (or on one specific gateway origin).

Parameter	Type	Required	Notes
origin	string	no	optional gateway origin to ask directly
wallet	string	no	optional wallet id; defaults to the mandate owner

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

Nothing here is billable: mcprush charges nothing to install tab or to call it, at any volume.

ATrust score 93 / 100

Release 2.4.0 · scanned 3 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 score93

Findings1 threat · 0 capability

Capabilityhigh

Coveragesource

Verificationrepo

Surface digest67bd2d680b374ce2c1b0b4fb830c48a66b14a33f90d0f640a2063cf3c3f1f42e

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	high	capability blast radius (high) — client exposure if the model is manipulated	−6
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 surfacenot available

Implementation sourceread

Package metadataread

Live transportnot available

No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. high is the level these add up to.

Tool	Capability tags	Why the tag was assigned
No per-tool rows for this release — see the note below.

can execute shell commands or code

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 digest67bd2d680b374ce2

Scanned2026-11-03

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.