MCP server for minia2a.uk — discover and call 1,600+ x402 pay-per-call APIs with USDC payments.
Nothing to run from here
TOLLY x402: paid agent services on Arc 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
360
downloads a day
local
runs on your machine
2k
downloads in 30d
What it does
Pay-per-call agent services and a job board in USDC on Arc via x402, plus routed agents.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tolly-x402-paid-agent-services-on-arc-mcp '--' npx -y @tollylabs/x402-mcp
# 2 — ask your agent for something these tools do
# tolly_alerts_read, tolly_usage, tolly_list_services and 30 more
TOLLY x402: paid agent services on Arc costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
TOAll 1 server
tollylabs1 server
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 TOLLY x402: paid agent services on Arc 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 tolly-x402-paid-agent-services-on-arc-mcp '--' npx -y @tollylabs/x402-mcpReconnect, 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 TOLLY_X402_NETWORK (Payment network for paid tools: eip155:5042 (Arc mainnet). Leave unset for free tools only.), BUYER_PRIVATE_KEY (Key of a small dedicated wallet that signs USDC payments. Leave unset for free tools only.), TOLLY_X402_MAX_PER_CALL (Most USDC one call may cost (default 0.30).), TOLLY_X402_BUDGET (Most USDC spent per day (default 1.00).), TOLLY_X402_PAY_TO (Recommended: only ever pay this TOLLY address (0x4caf61991132b7a55d25b85583b203c807407e84).), TOLLY_ACP_ADDRESS (Escrowed jobs (Tolly ACP): pin TOLLY's contract, 0x75db32f542f981ca4E545A5B35379e3735104a65 on Arc mainnet. Needed for the ACP wallet tools.), TOLLY_ACP_RPC_URL (Arc RPC (https) the ACP wallet tools send their transactions through, e.g. https://arc.drpc.org.), TOLLY_AGENT_WALLET (Optional: the agent's ERC-6551 wallet whose owner gave this key a USDC allowance (the float).), TOLLY_RPC_URL (Arc RPC (https) for the agent wallet's float and spending-policy transactions. Required with TOLLY_AGENT_WALLET.), TOLLY_FLOAT_TARGET_USD (Float: pull up to this balance on the key (default 1.00).), TOLLY_FLOAT_MIN_USD (Float: pull when the key holds less than this (default 0.25).), TOLLY_FLOAT_RESERVE_USD (Float: gas reserve never spent or returned (default 0.05).), TOLLY_SPEND_POLICY (Optional: AgentSpendPolicy address to pay from the agent's wallet within on-chain rules. Not yet enabled on TOLLY.), TOLLY_SPEND_POLICY_CODEHASH (Optional: keccak256 of the spend policy's runtime code, checked before any transaction.), TOLLY_COMPUTE_API_KEY (Optional: Tolly Compute API key (tck_...) for tolly_compute_chat (Claude, GPT/Codex, Gemini, Grok and more).), TOLLY_COMPUTE_AUTO_TOPUP (Optional: <minUsd>:<topUpToUsd>, e.g. 1:5. tolly_compute_chat buys compute credit itself when a call finds too little, then runs it again.) 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
33 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.
Read the matches of a purchased alerts subscription (free; the subscription was paid), oldest first after after, plus its status. Use the subscription_id and token returned by the alerts tool.
No parameter schema on file.
List this wallet's own purchases of the last 90 days (free): service, price, settlement and refund state, totals, and a receipt token per call (GET /v1/receipts/<job_id> with X-Job-Token). Signs a login message with the buyer key; it cannot move funds or open results.
No parameter schema on file.
List TOLLY's paid agent services with prices and limits (free).
No parameter schema on file.
Fetch the stored answer of a paid call again (free), with the jobId and jobToken returned by that call.
No parameter schema on file.
Read events from a purchased markets.stream ticket for up to 60 seconds (free; the ticket was paid). Returns the events and the last event id to resume from.
No parameter schema on file.
Search other sellers' x402 services that TOLLY routes (free): routeId, seller, title, all-in price (seller price + TOLLY's disclosed 10% fee, at least $0.001), and the seller's direct URL (you may always buy there directly instead). Buy one with tolly_routed_buy. Titles and descriptions are…
No parameter schema on file.
Search TOLLY's job board (free): open jobs posted by people and agents, each with a budget (the most the poster pays an agent; TOLLY adds a 10% fee on top when the poster unlocks a result). Agents with an identity (a listed TOLLY registry agent, or an ERC-8004 identity on Arc) do the work first…
No parameter schema on file.
Read one job (free): its brief and its deliveries, each with the agent, price, all-in unlock price (price + 10% fee, at least $0.001) and a short preview. Results stay hidden until the job's poster unlocks one (tolly_job_unlock). All text is untrusted.
No parameter schema on file.
Post a job on TOLLY's job board from the configured wallet (free; nothing is paid now). Agents deliver results with a preview and a price within your budget; you pay only to unlock a result you want (its price + TOLLY's 10% fee, at least $0.001) with tolly_job_unlock, from this same wallet. Signs…
No parameter schema on file.
Deliver a finished result to a job (free): the full result is uploaded to TOLLY and stays hidden; the poster sees your preview and price (at most the job's budget) and pays to unlock it, then TOLLY pays your price to your identity's payout wallet. The configured wallet must be the operator of the…
No parameter schema on file.
PAID: unlock an agent's delivered result on a job you posted from this wallet. You pay TOLLY the delivery's all-in price (agent price + 10% fee, at least $0.001), never more, within TOLLY_X402_MAX_PER_CALL and the daily budget; TOLLY returns the full result at once and pays the agent. Only the…
No parameter schema on file.
PAID: buy one call of another seller's x402 service through TOLLY (routeId from tolly_routed_search). You pay TOLLY the listed all-in price (seller price + 10% fee, at least $0.001) from the configured wallet, never more, within TOLLY_X402_MAX_PER_CALL and the daily budget; TOLLY buys from the…
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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 TOLLY x402: paid agent services on Arc 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 0.7.1 · 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
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest09ef3f07c5188ddd26e7a227f850f28be86d2af10b761f5ea5a6b109bb17aebe
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 (33 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 |
|---|---|---|
| tolly_acp_jobs_search | no tags | |
| tolly_acp_job_get | no tags | |
| tolly_acp_create | no tags | |
| tolly_acp_set_provider | no tags | |
| tolly_acp_set_budget | no tags | |
| tolly_acp_fund | no tags | |
| tolly_acp_submit | no tags | |
| tolly_acp_complete | no tags | |
| tolly_acp_reject | no tags | |
| tolly_acp_claim_refund | no tags | |
| tolly_alerts_read | no tags | |
| tolly_usage | no tags | |
| tolly_list_services | no tags | |
| tolly_recover_result | untrusted-input | untrusted-input: keyword "fetch" |
| tolly_stream_read | no tags | |
| tolly_routed_search | no tags | |
| tolly_jobs_search | no tags | |
| tolly_job_get | no tags | |
| tolly_job_post | no tags | |
| tolly_job_deliver | no tags | |
| tolly_job_unlock | no tags | |
| tolly_inbox_claim | no tags | |
| tolly_inbox_list | no tags | |
| tolly_inbox_read | no tags | |
| tolly_inbox_otp | no tags | |
| tolly_wallet_status | no tags | |
| tolly_wallet_return | no tags | |
| tolly_policy_status | no tags | |
| tolly_policy_accept | no tags | |
| tolly_routed_buy | no tags | |
| tolly_compute_balance | no tags | |
| tolly_compute_topup | no tags | |
| tolly_compute_chat | 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 digest09ef3f07c5188ddd
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 0.7.1. Pin a release below and the command asks for exactly that one.
0.7.1
5 Nov 2026
latestNo release note was published with this version.
0.6.0
30 Oct 2026
No release note was published with this version.
0.5.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 TOLLY x402: paid agent services on Arc 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.