# HEY Research Lab (remote · heyresearch.xyz)

Evidence-backed Robinhood Chain research: builders, ships, contracts, changes, market context.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `heyresearch.xyz`: 81/100, [markdown](https://verifymcp.io/servers/hey-research-lab-hey-research/heyresearch.md), [page](https://verifymcp.io/servers/hey-research-lab-hey-research/heyresearch)
- remote · `heyresearch.xyz`: 80/100 (this document), [markdown](https://verifymcp.io/servers/hey-research-lab-hey-research/mcp-research.md), [page](https://verifymcp.io/servers/hey-research-lab-hey-research/mcp-research)
- npm · `@hey-research-lab/mcp`: 68/100, [markdown](https://verifymcp.io/servers/hey-research-lab-hey-research/hey-research-lab-mcp.md), [page](https://verifymcp.io/servers/hey-research-lab-hey-research/hey-research-lab-mcp)

## Channel facts

- Endpoint: `https://heyresearch.xyz/mcp/research`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2221 tokens (~246/item across 9 items; 8 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the HEY Research Lab MCP server?

HEY Research Lab is a hosted endpoint at https://heyresearch.xyz/mcp/research, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http hey-research-lab-hey-research 'https://heyresearch.xyz/mcp/research'
```

### Cursor

```json
{
  "mcpServers": {
    "hey-research-lab-hey-research": {
      "url": "https://heyresearch.xyz/mcp/research"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "hey-research-lab-hey-research": {
      "type": "http",
      "url": "https://heyresearch.xyz/mcp/research"
    }
  }
}
```

### Codex

```toml
[mcp_servers.hey-research-lab-hey-research]
url = "https://heyresearch.xyz/mcp/research"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hey-research-lab-hey-research": {
      "type": "remote",
      "url": "https://heyresearch.xyz/mcp/research",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hey-research-lab-hey-research --url 'https://heyresearch.xyz/mcp/research' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  hey-research-lab-hey-research:
    url: "https://heyresearch.xyz/mcp/research"
```

### Netclaw

```json
{
  "McpServers": {
    "hey-research-lab-hey-research": {
      "Transport": "http",
      "Url": "https://heyresearch.xyz/mcp/research"
    }
  }
}
```

### Vellum

```bash
assistant mcp add hey-research-lab-hey-research -t streamable-http -u 'https://heyresearch.xyz/mcp/research'
```

### Other

```json
{
  "mcpServers": {
    "hey-research-lab-hey-research": {
      "type": "http",
      "url": "https://heyresearch.xyz/mcp/research"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 80, 0)

- [security] Tool “research_answer” rewrote its description, which is the text the model reads

### 2026-10-22 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 79, +1)

- [security] Tool “explain_fact” rewrote its description, which is the text the model reads
- [cosmetic] “explain_fact” added an optional parameter “event”

### 2026-10-18 (score 78, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “research_answer” rewrote its description, which is the text the model reads

### 2026-10-17 (score 77, 0)

- [functional] Server version: 0.3.1 → 0.3.2
- [cosmetic] “find_projects” reworded the description of “query”

### 2026-10-16 (score 77, +1)

- [security] Tool “get_evidence” rewrote its description, which is the text the model reads
- [security] Tool “get_changes” rewrote its description, which is the text the model reads
- [functional] Server version: 0.3.0 → 0.3.1

### 2026-10-14 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “research_answer” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 195 → 225
- [functional] Server version: 0.2.0 → 0.3.0
- [cosmetic] “research_answer” added an optional parameter “detail”
- [cosmetic] “research_answer” added an optional parameter “q”

### 2026-10-13 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_projects” rewrote its description, which is the text the model reads
- [security] Tool “explain_fact” rewrote its description, which is the text the model reads
- [security] Tool “get_evidence” rewrote its description, which is the text the model reads
- [security] Tool “get_project_timeline” rewrote its description, which is the text the model reads
- [security] Tool “get_v4_hook” rewrote its description, which is the text the model reads
- [security] Tool “research_answer” rewrote its description, which is the text the model reads
- [security] Tool “get_contract” rewrote its description, which is the text the model reads
- [security] Tool “get_changes” rewrote its description, which is the text the model reads
- [cosmetic] “find_projects” reworded the description of “query”
- [cosmetic] Tool “find_projects” changed its title: Find projects → Find a Robinhood Chain project
- [cosmetic] Tool “get_contract” changed its title: Contract → Who made this contract
- [cosmetic] Tool “research_answer” changed its title: Agent research answer → Research a Robinhood Chain project
- [cosmetic] Tool “get_project_timeline” changed its title: Project timeline → What a project shipped
- [cosmetic] Tool “get_changes” changed its title: What changed → What changed on Robinhood Chain

## MCP tools (8)

### `research_answer` (~207 tokens)

Research a Robinhood Chain project

Is this Robinhood Chain project still being built, what did it ship, what changed, is this contract its own? One cited answer. capability: research_project or builder_status (q: a name or $TICKER, or address, or project: a slug; a shared name lists candidates); what_changed (project or chain, 1–30 days); verify_project (address, project?); compare_builders (2–4, no winner); unknowns (every coverage state). Claims FACT/DERIVED/UNKNOWN with evidence ids; not_found is a status, not isError. Not price advice or a safety verdict.

Input parameters:

- `address` (string)
- `building` (string)
- `capability` (string, required)
- `days` (integer)
- `detail` (string)
- `limit` (integer)
- `project` (string)
- `projects` (array)
- `q` (string)
- `types` (array)

Output parameters:

- `answer` (object)
- `capability` (string)
- `claims` (array)
- `data`
- `evidence` (array)
- `schema` (string)
- `schemaVersion` (string)
- `status` (string)

### `find_projects` (~111 tokens)

Find a Robinhood Chain project

Which Robinhood Chain project is this name, $TICKER or 0x contract? Identity only (name, ticker, contract, slug), at most eight rows; give the slug to research_answer. A full 0x address answers whether anyone is building that contract: activity status, ship records in 30 days, the last ship with its source, whether the project names it.

Input parameters:

- `query` (string, required): Name, $TICKER, slug or 0x contract; q also works.

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

### `get_changes` (~257 tokens)

What changed on Robinhood Chain

What changed on Robinhood Chain today or this week, or for one project or contract? The change ledger without market readings: releases, ships, status moves, contract deploys and upgrades, verification, sources, unlocks — one event per change with its own time and precision, when HEY first knew, and its evidence. Newest first by first arrival; for today pass detectedSince; to sync, pass after=c1.0 and keep each cursor. A retraction means HEY no longer makes that claim. Facts, never causes.

Input parameters:

- `after` (string): Sync forward from this cursor (c1.0 is the start).
- `before` (string): Browse older than this cursor.
- `contract` (string): <chainId>:<address>.
- `detectedSince` (string): ISO instant: start a sync at the first event HEY recorded at or after it.
- `domain` (array)
- `limit` (integer): Default 30.
- `project` (string): A project slug.
- `since` (string): ISO date: events whose own time is at or after it (events with no source time are left out).
- `type` (array)
- `until` (string)

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

### `get_project_timeline` (~120 tokens)

What a project shipped

What did this project ship, and when? Builds, releases, code, contract deploys, upgrades and interface changes, token verification, locks and unlocks, each with how precisely HEY knows its time. Lenses: build (default), code, onchain, locks. Paged with the before cursor.

Input parameters:

- `before` (string): The cursor the previous answer gave.
- `lens` (string)
- `limit` (integer): Default 30.
- `slug` (string, required): A project slug, e.g. "agentos".

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

### `explain_fact` (~177 tokens)

Explain a fact

Why does HEY say a project is Shipping, Dormant or Still Building, or show a figure? The value, FACT, DERIVED or UNKNOWN, the rule and version, the winning source, the inputs, the lineage and the evidence ids. Omit fact to list what can be explained; source.counted takes a source id. build.change explains one change (event=<ledger id>, or the latest): its stage, who reported it, any exact release↔deployment link, what HEY does not know.

Input parameters:

- `event` (string): With fact=build.change: a change-ledger id; omit for the latest.
- `fact` (string)
- `slug` (string, required): A project slug, e.g. "agentos".
- `source` (string): With fact=source.counted: the source id.

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

### `get_evidence` (~125 tokens)

Open evidence

What backs this claim? Open the record a HEY answer cited by its typed id — ship:, signal:, abi:, impl:, lock:, source:, claim:, state:, narrative:, method:, sourcechange:, security:, v4hook:, v4pool:, ponsgrad: — as a receipt: what it claims, its source URL, when it happened at what precision, when HEY knew, how it is backed. A withdrawn record says so.

Input parameters:

- `id` (string, required): A typed evidence id, e.g. "ship:2ac87a66-…".

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

### `get_contract` (~175 tokens)

Who made this contract

Who made this Robinhood Chain contract, and is it a known project's? Project, creation, deployer (the only account named, with a count of other tracked projects' tokens it deployed), verified source and whose code it is (template, bytecode match or its own), Sourcify's answer, proxy and implementation history, interface changes, 7 days of calls per method (counts, names withheld; a selector's signature candidate — a guess, never a name). Address (chainId default 4663) or slug for all of a project's. An unread proxy is "not read", never "not a proxy". Not a safety verdict.

Input parameters:

- `address` (string)
- `chainId` (integer): Default 4663.
- `slug` (string): A project slug, for all of its contracts.

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

### `get_v4_hook` (~70 tokens)

Uniswap v4 hook

Who built this Robinhood Chain Uniswap v4 hook? The project HEY ties it to and why (named only while listed; never a creator account), declared callbacks (not a safety verdict), source, hooklist entry, pools by week and unknowns.

Input parameters:

- `address` (string, required)

Output parameters:

- `api` (string)
- `data`
- `schema` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/hey-research-lab-hey-research/mcp-research#diagnostics

## Score history

- 2026-10-23: 80
- 2026-10-22: 80
- 2026-10-21: 79
- 2026-10-20: 79
- 2026-10-19: 78
- 2026-10-18: 78
- 2026-10-17: 77
- 2026-10-16: 77
- 2026-10-15: 76
- 2026-10-14: 76
- 2026-10-13: 76
- 2026-10-12: 76
- 2026-10-10: 75

## Common questions

### What is the HEY Research Lab MCP server?

HEY Research Lab is an MCP server listed in the public MCP registry as io.github.hey-research-lab/hey-research. Evidence-backed Robinhood Chain research: builders, ships, contracts, changes, market context. This page covers its hosted endpoint (https://heyresearch.xyz/mcp/research).

### Is the HEY Research Lab MCP server safe to use?

HEY Research Lab scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the HEY Research Lab MCP server expose?

HEY Research Lab exposes 8 tools: research_answer, find_projects, get_changes, get_project_timeline, explain_fact, and 3 more. Their descriptions and schemas cost roughly 1,242 tokens of context every time the server is loaded.

### Does the HEY Research Lab MCP server require authentication?

No. We connected to HEY Research Lab without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the HEY Research Lab MCP server still maintained?

HEY Research Lab is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://heyresearch.xyz/mcp/research
- Repository: https://github.com/hey-research-lab/hey-research-open
- Website: https://heyresearch.xyz/developers/agents
- Changelog RSS feed: https://verifymcp.io/servers/hey-research-lab-hey-research/mcp-research.xml
- Changelog JSON feed: https://verifymcp.io/servers/hey-research-lab-hey-research/mcp-research.json
- HTML version of this page: https://verifymcp.io/servers/hey-research-lab-hey-research/mcp-research