Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
HEY Research Lab 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.
96/100
trust score
9
downloads a day
local
or remote
773
downloads in 30d
What it does
Evidence-backed Robinhood Chain research: builders, ships, contracts, changes, market context.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user hey-research-lab-mcp '--' npx -y @hey-research-lab/mcp
# 2 — ask your agent for something these tools do
# find_projects, lookup_token, get_project_snapshot and 14 more
HEY Research Lab costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HRAll 1 server
hey-research-lab1 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 can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
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 hey-research-lab-mcp '--' npx -y @hey-research-lab/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://heyresearch.xyz/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http hey-research-lab-mcp https://heyresearch.xyz/mcpFree 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 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
17 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.
Find Robinhood Chain projects by name, ticker or contract, or browse one of HEY's surfaces. A full 0x address is answered as lookup_token would. Surfaces: building-with-token: verified shipping, active or resumed, with a token whose market is live. still-building: verified activity continuing through a market drawdown HEY tracked. under-the-radar: eligible under HEY's Under the Radar rule (status
No parameter schema on file.
One project by its contract address — use this whenever the user pastes a contract. It answers HEY's one question about that address: is anyone building it. The activity status in HEY's words, ship records in 30 days, the last ship with its source, and whether the project names this contract. An address HEY publishes no page for answers "unknown" with a scan link: an answer, not an error. No risk
No parameter schema on file.
Everything important about one project in one read: identity and when HEY first recorded it, build status and Build Momentum, market context with its kind or why it is withheld, on-chain use, product usage over 7 days (calls, active contracts, distinct caller addresses per day — addresses, not people), verification and sources, HoodLock locks, the latest changes, freshness and what HEY does not kn
No parameter schema on file.
The canonical change ledger: what changed on Robinhood Chain or on one project — releases, ships, status moves, contract deployments, implementation and interface changes, verification, publication, sources, scheduled unlocks — one event per change, with its own time and precision, when HEY first knew, and its evidence. Use this for "what changed", "what happened since", "anything new on X". Brows
No parameter schema on file.
One project's research timeline: builds, releases, code, contract deploys, upgrades and interface changes, token verification, locks and scheduled unlocks, each with how precisely HEY knows its time. Lenses: everything, build, code, onchain, market, locks. Paged with the before cursor each answer gives.
No parameter schema on file.
What HEY knows and does not about one project, per dimension — builder evidence, repositories, releases, current and historical market, contracts and their verified source and interface, distribution, locks, market integrity, protocol economics, timeline, official docs, API description, official source changes, repository metadata, published packages and package advisories — as states (MEASURED, N
No parameter schema on file.
Why HEY publishes a fact about one project: the value, whether it is FACT, DERIVED or UNKNOWN, the canonical rule and its version, the winning source and why, the inputs, the lineage from source to public value, and the evidence ids. Omit fact to list what can be explained. source.counted takes a source id.
No parameter schema on file.
Open one published record by its typed id — ship:, signal:, abi:, impl:, lock:, source:, claim:, state:, method:, sourcechange:, security: — as a receipt: what it claims, its source URL, when it happened at what precision, when HEY knew, how it is backed. Ids come from get_changes, get_project_timeline, explain_fact and the snapshot. A withdrawn record says so.
No parameter schema on file.
One token's market from HEY's own daily index: the current reading with its valuation kind and provider, price, liquidity, volume and trades by day, the lifecycle (deploy, the launchpad's claim, stage, first indexed trade), pools and depth, a supply-concentration summary (shares only, no addresses), contract checks and events by day. include=["moves"] adds each day-on-day valuation move with the b
No parameter schema on file.
A contract as a research entity: creation, deployer (the only account ever named, with a count of other tracked projects' tokens it deployed), factory, verified source and compiler, how the explorer verified it and whose code it is (a launchpad template, a bytecode match, or source published for the address), Sourcify's answer, proxy kind, implementation history or the contract it is a minimal clo
No parameter schema on file.
What changed for one project between two dates (YYYY-MM-DD, at most 400 days apart): releases and meaningful ships, status and Build Momentum then and now, valuation and liquidity then and now, and the changes recorded — each value from the nearest persisted point with its date and basis; none HEY did not persist. Never a cause.
No parameter schema on file.
Two to four Robinhood Chain projects side by side: activity status, last ship, Build Momentum, velocity, cadence, verification and market context — each line FACT, DERIVED or UNKNOWN. No winner and no recommendation.
No parameter schema on file.
A free-text question about one project (English or Malay). HEY matches it to the parts of its record it is about and answers only from that record, every line tagged FACT, DERIVED or UNKNOWN with its source. It records building only and offers no view on price.
No parameter schema on file.
Robinhood Chain as a whole. view: days (default; trades, volume, tokens, transactions, launches, ships per day), this-week (the rollup), weekly-report (an archived ISO week, or the latest), unlocks (scheduled HoodLock unlocks with proof), build-market (Build Momentum beside market attention, a map). Aggregates only; nobody is named.
No parameter schema on file.
For one project: what happened to its tracked token market — liquidity against the level it held, trading, a pool migration — beside its builder activity, and where the two disagree. It describes the token market, never whether development stopped, and never calls a project a rug or safe.
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 HEY Research Lab 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 96 / 100
Release 0.3.0 · scanned 14 Oct 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 score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest5db3e99d1da055af3a3f10579d19fd3959c74a4880b4660ae6b95255d9db98a7
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (17 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>".
1 of the 17 recovered tools are registered only when offered.has("find_projects") && research holds (dist/index.js:3024) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_project_snapshot") holds (dist/index.js:3124) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_changes") holds (dist/index.js:3140) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_project_timeline") holds (dist/index.js:3183) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("explain_fact") holds (dist/index.js:3210) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_evidence") holds (dist/index.js:3239) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_token_market") holds (dist/index.js:3255) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_contract") holds (dist/index.js:3282) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("get_v4_hook") holds (dist/index.js:3312) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("project_diff") holds (dist/index.js:3327) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("ask_hey") holds (dist/index.js:3343) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("chain_overview") holds (dist/index.js:3359) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("research_answer") holds (dist/index.js:3408) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
1 of the 17 recovered tools are registered only when offered.has("market_integrity") holds (dist/index.js:3451) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
3 of the 17 recovered tools are registered only when !research holds (dist/index.js:3467) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes none of the recovered tools.
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.
No tool is registered unconditionally · (1) 1 only when offered.has("find_projects") && research holds (dist/index.js:3024) · (2) 1 only when offered.has("get_project_snapshot") holds (dist/index.js:3124) · (3) 1 only when offered.has("get_changes") holds (dist/index.js:3140) · (4) 1 only when offered.has("get_project_timeline") holds (dist/index.js:3183) · (5) 1 only when offered.has("explain_fact") holds (dist/index.js:3210) · (6) 1 only when offered.has("get_evidence") holds (dist/index.js:3239) · (7) 1 only when offered.has("get_token_market") holds (dist/index.js:3255) · (8) 1 only when offered.has("get_contract") holds (dist/index.js:3282) · (9) 1 only when offered.has("get_v4_hook") holds (dist/index.js:3312) · (10) 1 only when offered.has("project_diff") holds (dist/index.js:3327) · (11) 1 only when offered.has("ask_hey") holds (dist/index.js:3343) · (12) 1 only when offered.has("chain_overview") holds (dist/index.js:3359) · (13) 1 only when offered.has("research_answer") holds (dist/index.js:3408) · (14) 1 only when offered.has("market_integrity") holds (dist/index.js:3451) · (15) 3 only when !research holds (dist/index.js:3467) — typically when a key or option is configured. All 17 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| find_projects conditional (1) | no tags | |
| get_project_snapshot conditional (2) | no tags | |
| get_changes conditional (3) | no tags | |
| get_project_timeline conditional (4) | no tags | |
| explain_fact conditional (5) | no tags | |
| get_evidence conditional (6) | no tags | |
| get_token_market conditional (7) | sensitive-source | sensitive-source: keyword "get_token" |
| get_contract conditional (8) | no tags | |
| get_v4_hook conditional (9) | no tags | |
| project_diff conditional (10) | no tags | |
| ask_hey conditional (11) | no tags | |
| chain_overview conditional (12) | no tags | |
| research_answer conditional (13) | no tags | |
| market_integrity conditional (14) | no tags | |
| lookup_token conditional (15) | no tags | |
| get_project_coverage conditional (15) | no tags | |
| compare_projects conditional (15) | 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 digest5db3e99d1da055af
Scanned2026-10-14
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 0.3.0. Pin a release below and the command asks for exactly that one.
0.3.0
14 Oct 2026
latestNo release note was published with this version.
0.2.0
9 Oct 2026
No release note was published with this version.
0.1.2
2 Oct 2026
No release note was published with this version.
0.1.1
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 HEY Research Lab 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.