Local MCP capabilities provider for Expo
Nothing to run from here
AttestPage (Quoteproof) 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.
12
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Use before citing a page, sharing links or installing a suggested package. Signed receipts.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http attestpage-quoteproof-mcp https://vehcdj664efetfrsolne5umanq.srv.us/mcp
# 2 — ask your agent for something these tools do
# attestpage_verify_quote, attestpage_verify_citations, attestpage_fetch and 9 more
AttestPage (Quoteproof) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SRAll 2 servers
srv2 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. 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 attestpage-quoteproof-mcp https://vehcdj664efetfrsolne5umanq.srv.us/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.
Use when an agent is about to quote or cite a web page as the source of a claim: send the URL and the quote word for word, and get back exact, fuzzy or none, with offsets and a signed receipt, so a misquote is caught before a user sees it. US$0.01 per call; fact check of citations. For 3 or more quotes on one page, verify/quotes costs less. PDFs are read too, on the full service, with pdf_page and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | http(s) URL of the page to check (max 2,048 characters). |
| quote | string | yes | Text to look for on the page, or with match "passages" the claim to find support for (max 1,000 characters after normalisation). |
| match | string | no | exact; fuzzy (default), which also accepts small differences; or passages, for a paraphrased claim: the 3 passages that share most of its words, scored, as evidence for you to judge (not a verdict). |
| case_sensitive | boolean | no | Default false; must be false with match "passages". |
| threshold | number | no | Fuzzy similarity needed, default 0.9. |
Use before giving an answer that cites web pages: send up to 10 quote and URL pairs, and get back for each one an exact, fuzzy or none match, under one signed receipt. US$0.10 per call. A fact check of each citation against its source. Match passages give evidence for each paraphrased claim. DOIs get Crossref data and a retracted flag. For 1 to 9 pairs, one verify/quote call per pair costs less. P
| Parameter | Type | Required | Notes |
|---|---|---|---|
| citations | array | yes | 1 to 10 citations. Each URL is fetched once however many quotes cite it. Dead domains are reported as results; if none resolves, 422 and no charge. |
| match | string | no | For every citation: exact; fuzzy (default), which also accepts small differences; or passages, for a paraphrased claim: the 3 passages that share most of its words, scored, as evidence for you to judg |
| case_sensitive | boolean | no | Default false; must be false with match "passages". |
| threshold | number | no | Fuzzy similarity needed, default 0.9. |
Use when an agent needs a web page as clean text, or to notarize one: send a URL or up to 10, and get back clean text, content_kind (real, bot_wall, paywall), title, hashes and a signed receipt per page. US$0.002 per URL; web fetch that flags bot walls. PDFs too, on the full service (edge: 501, uncharged): page.pdf with page_count, pages_read and truncated. 5 free calls a day. Costs US$0.002 per c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | no | http(s) URL to fetch (max 2,048 characters). Send url or urls, not both. |
| urls | array | no | Instead of url: 1 to 10 distinct http(s) URLs in one call, priced per URL (the route price × the count). The answer is results[], one per URL, each with its own receipt. |
| return_text | boolean | no | Also return up to 20,000 characters of clean text (per page). Default false. |
Use when an agent relies on a web page it read earlier and needs change detection: send an earlier receipt or URL with its content_sha256, and get back unchanged, changed, gone or unreadable with the fields that differ. US$0.003 per call; page monitoring, nothing stored, no callbacks. 5 free calls a day. Costs US$0.003 per call in USDC via x402 (Base), charged only when the call succeeds; a bad re
| Parameter | Type | Required | Notes |
|---|---|---|---|
| receipt | string | no | Compact JWS receipt from an earlier /v1/fetch, /v1/verify/quote or /v1/recheck call of this service (paid or trial; not a sample). Max 160 KB. |
| url | string | no | Only without receipt: the http(s) URL to re-check (max 2,048 characters). |
| content_sha256 | string | no | Only with url: the page.content_sha256 from our own fetch (64 hex). Other tools hash other text. |
| return_text | boolean | no | Also return up to 20,000 characters of the new clean text. Default false. |
Use when an agent is about to give a user links or citations: send up to 10 URLs, and get back the status, redirect chain, final URL, title and hash of each, so a dead, moved or blocked link is caught first. A URL whose domain does not resolve is reported as dead and charged. US$0.005 per call; broken-link check for citations. 5 free calls a day. Costs US$0.005 per call in USDC via x402 (Base), ch
| Parameter | Type | Required | Notes |
|---|---|---|---|
| urls | array | yes | 1 to 10 http(s) URLs to check. Dead domains are reported as results; if none resolves, 422 and no charge. |
Use when an agent is about to install or recommend a package an LLM suggested: send up to 10 names, each with its registry (npm, pypi or crates), and get back whether each is listed, its latest version, licence and OSV.dev advisories under one signed receipt, so a made-up or known-bad package is caught before install. Not a security verdict. US$0.005 per call. 5 free calls a day. Costs US$0.005 pe
| Parameter | Type | Required | Notes |
|---|---|---|---|
| packages | array | yes | 1 to 10 packages to look up. Each is { ecosystem, name, version? }; ecosystem is npm, pypi or crates (crates.io). |
Use when an agent needs to show later that a file, answer or record existed unchanged at a point in time: send its sha256, and get back a signed, timestamped receipt over it; a later altered copy no longer matches. Optional note; with an idempotency_key (x402 payments only), a retry gets the same receipt and is not a new record. For signed evidence of what a web page said at a given time (provenan
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sha256 | string | yes | SHA-256 (hex) of the thing being attested. |
| note | string | no | Optional note; only its SHA-256 goes in the receipt. |
| idempotency_key | string | no | Optional, x402 payments only (keys are scoped to the paying address; trial and L402 calls get 400). Retries with the same key and sha256 get the same receipt; a different sha256 gets 409. |
Use before sending a finished answer or report that quotes web pages: send the document as written, and get back every quote with its link, checked on the live page: exact, fuzzy or none, score, offsets and each page's status, under one signed receipt. Up to 10 pairs per part; the free preview (POST /v1/verify/document/preview) lists the pairs, parts and price first. For a part of 1 to 9 pairs, on
| Parameter | Type | Required | Notes |
|---|---|---|---|
| document | string | yes | The answer or report as written, 1 character to 60000 bytes (UTF-8). Its quotes and their links are found by fixed rules (extractor doc-v1). |
| format | string | no | markdown (default) or text (only bare URLs and [n] references are links). |
| match | string | no | For every pair: exact; fuzzy (default), which also accepts small differences; or passages, for a paraphrased claim: the 3 passages that share most of its words, scored, as evidence for you to judge (n |
| case_sensitive | boolean | no | Default false; must be false with match "passages". |
| threshold | number | no | Fuzzy similarity needed, default 0.9. |
| min_words | integer | no | A quoted span with fewer words is skipped as too_short (default 4). |
| part_size | integer | no | Pairs per part, default 10. A free trial call needs 3 or fewer. |
| part | integer | no | 0-based part to check, default 0; call POST /v1/verify/document/preview first to see how many parts there are. |
Use when an agent is about to quote one web page several times: send the URL and up to 20 quotes in your exact words, and get back for each one exact, fuzzy or none, with offsets and context, plus the page's verdict and hashes, under one signed receipt. The page is fetched once at one price for 1 to 20 quotes, so from 3 quotes up it costs less than one verify/quote call per quote. Full service onl
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | http(s) URL of the page to check (max 2,048 characters). Fetched once for all the quotes. |
| quotes | array | yes | 1 to 20 quotes to look for on that page, or with match "passages" claims to find support for (each max 1,000 characters after normalisation). One price for the call however many. |
| match | string | no | For every quote: exact; fuzzy (default), which also accepts small differences; or passages, for a paraphrased claim: the 3 passages that share most of its words, scored, as evidence for you to judge ( |
| case_sensitive | boolean | no | Default false; must be false with match "passages". |
| threshold | number | no | Fuzzy similarity needed, default 0.9. |
Use when an agent already holds the source text (a file it read, a tool result, a document) and is about to quote it: send the text and the quote word for word, and get back exact, fuzzy or none with offsets, or with start and end, whether the text at those offsets says the quote. Nothing is fetched. Declared offsets are raw code points; result offsets are into the normalised text. A signed receip
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The source text you already hold, as sent (max 50,000 characters; no fetch, no normalising before hashing). Offsets count characters (code points). |
| quote | string | yes | Text to look for in the source, or with match "passages" the claim to find support for (max 1,000 characters after normalisation). |
| start | integer | no | Optional, with end: the declared start offset of the quote in text, raw code points, 0-based. Only that slice is matched (max 1,000 code points), so the answer is whether the text at these offsets say |
| end | integer | no | Optional, with start: the declared end offset, raw code points, exclusive. Give both or neither; not with match "passages". |
| match | string | no | exact; fuzzy (default), which also accepts small differences; or passages, for a paraphrased claim: the 3 passages of the text that share most of its words, scored, as evidence for you to judge (not a |
| case_sensitive | boolean | no | Default false; must be false with match "passages". |
| threshold | number | no | Fuzzy similarity needed, default 0.9. |
Use when you are handed an AttestPage evidence receipt and need to check it before relying on it: verifies the compact JWS against this service's published keys and returns its payload, so a forged or altered receipt is caught. Free. Free. Docs: https://vehcdj664efetfrsolne5umanq.srv.us/docs/receipt-verify
| Parameter | Type | Required | Notes |
|---|---|---|---|
| receipt | string | yes | The compact JWS from the "receipt" field of a response. |
Use before paying for POST /v1/verify/document: send the same body, and get back the quote and link pairs it would check, what was skipped and why, the number of parts and the exact price. Nothing is fetched, signed or charged. Free. Free. Docs: https://vehcdj664efetfrsolne5umanq.srv.us/docs/verify-document
| Parameter | Type | Required | Notes |
|---|---|---|---|
| document | string | yes | The answer or report as written, 1 character to 60000 bytes (UTF-8). Its quotes and their links are found by fixed rules (extractor doc-v1). |
| format | string | no | markdown (default) or text (only bare URLs and [n] references are links). |
| match | string | no | For every pair: exact; fuzzy (default), which also accepts small differences; or passages, for a paraphrased claim: the 3 passages that share most of its words, scored, as evidence for you to judge (n |
| case_sensitive | boolean | no | Default false; must be false with match "passages". |
| threshold | number | no | Fuzzy similarity needed, default 0.9. |
| min_words | integer | no | A quoted span with fewer words is skipped as too_short (default 4). |
| part_size | integer | no | Pairs per part, default 10. A free trial call needs 3 or fewer. |
| part | integer | no | 0-based part to check, default 0; call POST /v1/verify/document/preview first to see how many parts there are. |
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 AttestPage (Quoteproof) 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: —
—Grade not published
No rule-by-rule report on file for this release
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 0.1.0.
0.1.0
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 AttestPage (Quoteproof) 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.