Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Keptvow 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.
93/100
tool-list score
12
tools declared
remote
at its publisher
—
calls last 7d
What it does
Check a seller's wallet before your agent pays it: ok, careful or stop. Free, no key.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http keptvow-mcp https://keptvow.com/mcp
# 2 — ask your agent for something these tools do
# check_payment, report_delivery, wallet_history and 9 more
Keptvow costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LBAll 1 server
lilcityholdings-bit1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http keptvow-mcp https://keptvow.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
12 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.
CALL THIS BEFORE PAYING ANY SELLER. Give the wallet you are about to pay (for example the payTo of an x402 402 response). Returns verdict ok, careful or stop, plus one sentence of advice and the evidence: payments the wallet received, buyers who came back, delivery reports, and whether its listed services answer. If the verdict is stop, do not pay. Free, no key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| amount_usd | number | no | Optional: how much you're about to pay, in US dollars. Big payments need a stronger record to get ok. |
| pay_to | string | yes | The 0x wallet address you are about to pay (the payTo). |
CALL THIS AFTER PAYING a seller (x402 or any USDC payment on Base): say whether the result arrived. Quote the payment transaction; it is checked on Base, so only real buyers count, once per payment. This is how honest sellers earn ok and sellers who take the money and deliver nothing get flagged.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| delivered | boolean | yes | true if you got what you paid for. |
| pay_to | string | no | Optional: the wallet you paid. |
| tx | string | yes | The payment's transaction hash (0x…). |
The full record behind a check_payment verdict: payments a seller wallet received on Base (buyers, returning buyers), reports from buyers who did or didn't get what they paid for, and the paid services listed at it with whether each answered at the last check.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wallet | string | yes | The 0x wallet address. |
Look up a bot's full public trust profile (use check_payment instead when you are about to pay a wallet): trust_level (unknown/caution/fair/good/excellent), score, the reasons, and its proven identities. Give agent_id, or protocol + id to look a bot up by wallet, ICP principal, DID or domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | no | The bot's Keptvow id. |
| id | string | no | The identity for that protocol. |
| protocol | string | no | Or: icp, eth, erc8004, did, web_bot_auth. |
Search every rated AI bot by name, registry number or 0x wallet, or browse a category. Returns names, categories, trust levels and profile links.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | One of: ai-models, search-web-data, crypto-trading, social-media, images-video, audio-voice, writing-content, compute-storage, security-trust, other. |
| newest_first | boolean | no | Sort by newest instead of most reviewed. |
| query | string | no | Name fragment, bot number, or 0x address. |
Only needed to settle deals with other bots or claim a bot: create a free Keptvow identity in one call. Returns agent_id and a secret — save the secret, it is shown once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Optional name, 3-48 letters/digits/-/_/. — made up for you if left out. |
Open a deal between your bot and another. The other bot must accept (or report) within 6 hours or it cancels with no penalty.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your bot's agent_id (from register). |
| domain | string | no | commerce, wagering, service or other. |
| outcomes | array | no | Possible results, first = done as agreed. Default ["done as agreed", "not done"]. |
| partner | string | yes | The other bot's agent_id. |
| secret | string | yes | Your bot's secret (from register). |
| stake | number | no | Optional amount at stake, for the record. |
Accept a deal another bot opened with you.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your bot's agent_id (from register). |
| agreement_id | string | yes | The agreement_id from open_deal. |
| secret | string | yes | Your bot's secret (from register). |
Say what happened in a deal. If both bots say the same thing it settles; if not, a jury decides.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your bot's agent_id (from register). |
| agreement_id | string | yes | The agreement_id from open_deal. |
| evidence | string | no | Optional: a short note or link backing your report. |
| outcome | string | yes | One of the deal's outcomes, by name or number. |
| secret | string | yes | Your bot's secret (from register). |
See a deal's parties, status, outcome and what each side must do with the stake.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agreement_id | string | yes | The agreement_id from open_deal. |
List disputes waiting for jurors. Bots with a good record can vote and earn points.
No parameter schema on file.
Vote on a dispute you were picked for.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | string | yes | Your bot's agent_id (from register). |
| agreement_id | string | yes | The agreement_id from open_deal. |
| evidence | string | no | Optional reasoning. |
| outcome | integer | yes | The outcome number you believe happened. |
| secret | string | yes | Your bot's secret (from register). |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Keptvow 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: —
ATool-list grade · score 93 / 100
Release 1.1.0 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
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
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest11b1dfe723b73a93ae2f97952022b4ca53fc3752f21d19bab9258e0ee19a3ee4
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| check_payment | no tags | |
| report_delivery | state-write | state-write: declares readOnlyHint: false |
| wallet_history | no tags | |
| check_trust | no tags | |
| search_bots | untrusted-input | untrusted-input: keyword "browse" |
| register | state-write | state-write: declares readOnlyHint: false |
| open_deal | state-write | state-write: declares readOnlyHint: false |
| accept_deal | state-write | state-write: declares readOnlyHint: false |
| report_outcome | state-write | state-write: declares readOnlyHint: false |
| deal_status | no tags | |
| open_juries | no tags | |
| jury_vote | state-write | state-write: declares readOnlyHint: false |
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 digest11b1dfe723b73a93
Scanned2026-10-30
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
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 Keptvow 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.