Model Context Protocol (MCP) server for freee API integration
Nothing to run from here
cryptofeed402 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
16
tools declared
remote
at its publisher
—
calls last 7d
What it does
Hyperliquid perp funding, OI, preflight & news sentiment for agents. Pay per call in USDC (x402).
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http cryptofeed402-mcp https://cryptofeed402.site/mcp
# 2 — ask your agent for something these tools do
# get_teaser, get_sample_brief, get_pricing and 13 more
cryptofeed402 costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CRAll 1 server
cryptofeed4021 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 cryptofeed402-mcp https://cryptofeed402.site/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
16 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.
Free: latest brief teaser text, Hyperliquid extreme funding (8h-equivalent rates), BTC/ETH/SOL prices with 24h change.
No parameter schema on file.
Free: a delayed, trimmed sample of the twice-daily crypto brief (previous edition; no OI, sentiment or markdown). Use to evaluate before paying for get_latest_brief.
No parameter schema on file.
Free: current per-call prices (USDC on Base via x402), network and payTo address.
No parameter schema on file.
Free: ask cryptofeed402 to consider monitoring a coin it does not cover yet (covered: BTC, ETH, SOL, HYPE, NEAR, AAVE). Logged for human review; high-demand assets may be added to the brief and paid endpoints later. Not a guarantee. Limit 10/hour/IP; repeat asks for the same symbol within 24h count once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Ticker, e.g. LINK (2-15 chars, letters/digits, optional hyphen; leading $ ok) |
| reason | string | no | Optional short reason (<=200 chars) |
| agent | string | no | Optional agent name/id (<=80 chars) |
Free: tell cryptofeed402 how often you want briefs/reports and the best UTC hours to have a fresh one ready, so we can schedule to match. Logged as aggregate demand (GET /feedback/schedule shows counts only; notes and agent names are never published; no IPs stored). Limit 10/hour/IP.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| frequency | string | yes | — |
| preferred_utc_hours | array | yes | Up to 6 UTC hours (0-23); [] = no preference |
| symbols | array | no | — |
| routes_of_interest | array | no | — |
| agent_name | string | no | — |
| note | string | no | Plain text |
Free: top 20 coins other agents have asked cryptofeed402 to monitor in the last 30 days (aggregate counts only).
No parameter schema on file.
Paid endpoint: perp mark, funding, OI (Hyperliquid) plus OKX spot for one coin. Returns the x402 payment requirements and URL; pay with your own x402 client. Free sample response: https://cryptofeed402.site/samples/price
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | — |
Paid endpoint: most extreme Hyperliquid funding rates right now. Returns the x402 payment requirements and URL. Free sample response: https://cryptofeed402.site/samples/funding
No parameter schema on file.
Paid endpoint: the full latest twice-daily crypto research brief (JSON + markdown). Returns the x402 payment requirements and URL. Free sample: get_sample_brief or https://cryptofeed402.site/brief/sample
No parameter schema on file.
Free: a cached example agent-readiness audit of cryptofeed402.site (score 0-100, pass/warn/fail per check with evidence and fixes) so you can see the output of audit_agent_ready before paying.
No parameter schema on file.
Paid endpoint ($0.002): one Hyperliquid perp's funding (hourly, 8h, annualized), open interest in USD, 24h volume, mark/oracle price, premium and whether it is in the top-10 funding extremes. Any listed Hyperliquid perp; unknown symbols return an error and no charge. Returns the x402 payment requirements and URL. Free sample response: https://cryptofeed402.site/samples/perps
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Hyperliquid perp ticker, e.g. BTC, ETH, SOL, HYPE |
Paid endpoint ($0.002): crypto news sentiment for one asset: -1..1 score, bearish/neutral/bullish label, pos/neg/neu headline counts and up to 5 top headlines with links. Headlines labeled by a local LLM, score is plain math, refreshed about every 15 min. Symbols not in the current snapshot or stale data return an error and no charge (free list: GET /sentiment). Returns the x402 payment requiremen
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Ticker, e.g. BTC, ETH, SOL |
Paid endpoint ($0.05): audits a public website or x402 API for AI-agent readiness (llms.txt, robots.txt AI rules, sitemap, OpenAPI, /.well-known/x402, agent card, MCP initialize, a live unpaid 402 challenge, Bazaar metadata, Roundhouse / 402 Index / x402 Doctor listings). Deterministic, no LLM. Returns the x402 payment requirements and URL; see get_audit_sample for the output format.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Domain or http(s) URL of the site to audit (public hosts, ports 80/443) |
Paid endpoint ($0.01): pre-trade preflight for one Hyperliquid perp in one call: perp mark vs OKX spot and vs oracle (bps), funding hourly/8h/annualized with its extreme-funding rank, open interest and OI change vs ~1h/~24h ago, news sentiment if covered, as_of per component, and neutral flags (funding_extreme, oi_spike, venue_divergence, stale_component) with their rules. Factual checks only, no
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Hyperliquid perp ticker, e.g. BTC, ETH, SOL, HYPE |
Paid endpoint ($0.005): hourly funding settlements for one Hyperliquid perp (rate hourly/8h/annualized, premium) plus mean/min/max, positive/negative hours and cumulative rate. Give hours (1-720, default 168) or from/to (YYYY-MM-DD or ISO 8601 UTC, max 720 hours). History back to each perp's listing (BTC since 2023-05-12). Bad params or unknown symbol return an error and no charge. Returns the x40
| Parameter | Type | Required | Notes |
|---|---|---|---|
| symbol | string | yes | Hyperliquid perp ticker, e.g. BTC |
| hours | integer | no | Last N hours (default 168). Do not combine with from/to. |
| from | string | no | Start, YYYY-MM-DD or ISO 8601 UTC |
| to | string | no | End, YYYY-MM-DD (inclusive) or ISO 8601 UTC; default now |
Paid endpoint: archived briefs for a date range. Returns the x402 payment requirements and URL. Free sample response: https://cryptofeed402.site/samples/history
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | — |
| to | string | no | — |
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 cryptofeed402 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 1.5.0 · scanned 28 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 · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest7a1ee7e9d593d65e066fc33da41ebdafdbef2c80415ebb74744b3f9de98412eb
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 |
|---|---|---|
| get_teaser | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_sample_brief | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_pricing | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| request_asset | state-write | state-write: declares readOnlyHint: false |
| request_report_schedule | state-write | state-write: declares readOnlyHint: false |
| get_top_requested_assets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_price | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_extreme_funding | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_latest_brief | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_audit_sample | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_perps | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_sentiment | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| audit_agent_ready | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_outlook | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_funding_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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 digest7a1ee7e9d593d65e
Scanned2026-10-28
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 1.5.0.
1.5.0
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 cryptofeed402 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.