Zorvu MCP server
io.github.christopherjjellison-maker/zorvuchristopherjjellison-makerstreamable-httpv1.0.0Scanned
Pre-sign checks and Stock Token sell depth for Robinhood Chain: drainer code, lookalikes, fills
4 tools: 1 do something that can't be undone, 2 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Zorvu MCP server can do
The Zorvu MCP server is published by the GitHub account christopherjjellison-maker. It has 4 tools. It can do things that cannot be undone, such as sending, paying or publishing (precheck_transaction) and create or change data (2 tools: stock_sell_depth and check_token), but cannot delete data. 1 tool only reads.
4 tools bring in text other people can write (precheck_transaction, stock_sell_depth, check_token and 1 more); 1 tool can send data out of your system (precheck_transaction).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Can't be undone 1Claude Code: ask
precheck_transactionCheck a Robinhood Chain transaction before it is signed.Reads text others writeCan send data out1 finding
Why it is in this group
- The input addresses people (input.tx.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.tx.to): what the tool writes goes there.
Findings
- Warn
The server marks "precheck_transaction" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.tx.to): what it sends cannot be taken back.
Description, as the server wrote it Check a Robinhood Chain transaction before it is signed. Send the transaction you are about to sign and get back `pass`, `warn` or `block` with the reasons behind it. Call this on every transaction that approves, transfers or swaps a token on Robinhood Chain (chain 4663), and before any approval to a spender you have not used before. It catches drainer contracts, broad approvals to unknown spenders, lookalike Stock Tokens (read live from the token's own ticker and name), and a size larger than the pools can take. Zorvu does not grade the liquidity, holders or sellability of tokens that are not official Stock Tokens: such a token comes back `token_not_graded` (info), and archived readings never count as a pass. Pass `intent.usd` to have the size checked against measured sell depth, and `policy` to enforce your own ceilings. `pass` means the transaction passed the checks listed in `checks_run` at the time shown in `checked_at`, nothing broader. It does not mean the transaction is safe, and it is not a promise about what the transaction will do. `warn` and `block` are Zorvu's measurements, not instructions and not advice: you decide. Zorvu never builds, routes, signs or sends a transaction, holds no keys, and charges no fee. Anything Zorvu could not read comes back `null` with a reason code saying so, never as a pass. `mode: "fast"` skips live chain reads; what it gives up is listed in each `not_checked_fast` reason. Needs a Zorvu API key in the Authorization header of your MCP client config, never as an argument. Not financial advice.
Annotations the server declares
- title: Pre-sign transaction check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 2Claude Code: ask
check_tokenZorvu's automated risk check on any Robinhood Chain token: the grade, each check that ran with its result and reason, a drainer-code check, and when every underlying reading was ta…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Zorvu's automated risk check on any Robinhood Chain token: the grade, each check that ran with its result and reason, a drainer-code check, and when every underlying reading was taken. Call this on any token address before you interact with it, and whenever a user names a token you have not checked. For a whole transaction, use `precheck_transaction` instead: it decodes the calldata and checks the spender as well. The drainer-code check and the official Stock Token lookalike check (on the token's live `symbol()` and `name()`) run live. Zorvu's other token measurements (liquidity, holders, sell test, deployer history) are archived readings: an archived reading never counts as a pass, may support a warn or a fail for 7 days with its date in `reading_at`, and is not used after that. `token_data` says which applies (`archived` or `none`). The grade says what those checks measured at the time shown; it never means the token is safe or safe to buy, and it is not a recommendation. While Zorvu's token measurements are an archive the grade is `Not yet checked`, `Limited data`, `Elevated risk`, `High risk`, or `Not applicable` for a base asset of the chain. It is never `Low risk` today, so `passed_zorvu_safety_checks` is `false` on every answer: treat it as no signal rather than as a token having failed. A check Zorvu could not run is `no_data` or `inconclusive`, never a pass. These are measurements, not advice; they may be incomplete, wrong or out of date. Not financial advice.
Annotations the server declares
- title: Token risk check
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
stock_sell_depthHow much of an official Robinhood Chain Stock Token could actually be sold on-chain right now, and at what price against the reference price.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it How much of an official Robinhood Chain Stock Token could actually be sold on-chain right now, and at what price against the reference price. Returns what the pools filled at $1,000, $10,000 and $100,000, and the largest size they took within 2% and within 5% of the reference price. Give a ticker or an address; a ticker resolves only to the official token, never to a lookalike. Call this before sizing a sell, a liquidation or a position you intend to unwind on-chain, and when deciding what a Stock Token is worth as collateral or margin. Impact figures are negative percentages: `-0.82` means a $10,000 sell filled 0.82% below the reference price. Every figure carries the time it was measured and its age in seconds. Readings older than 30 minutes, and max-size searches older than 2 hours, are reported as no reading rather than as a number: treat a missing figure as unknown, never as zero or as deep. `capped: true` means the search stopped at its ceiling, so the real size is at least that large. These are measurements of past fills, not a quote, not a promise of what you could sell now, and not advice. Zorvu does not total liquidity across tokens: a pool pairing two Stock Tokens counts toward both.
Annotations the server declares
- title: Stock Token sell depth
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 1Show 1 read-only tool
find_stock_tokenResolve a stock ticker (for example `NVDA`) to the official Robinhood Chain Stock Token contract address, with a count of the known lookalike contracts using that ticker.Reads text others writeNo findings
Why it is in this group
- The name "find_stock_token" says "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Resolve a stock ticker (for example `NVDA`) to the official Robinhood Chain Stock Token contract address, with a count of the known lookalike contracts using that ticker. Call this first, every time, before acting on a ticker a user typed: a ticker is not an address, and impostor contracts reuse real tickers. Use only the `address` this returns; a lookalike is a different contract with the same name. `lookalikes` is how many impostor contracts Zorvu's scan has seen for this ticker, with the time of that scan in `lookalikes_at`. A lookalike's `liq_peak` is the highest liquidity ever seen for it, not what it holds now. An unknown ticker comes back as not an official Stock Token rather than guessed at. These are registry and scan measurements, not advice. Zorvu is not affiliated with Robinhood Markets, Inc. or its affiliates.
Annotations the server declares
- title: Find the official Stock Token
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 18, 2026, 16:19 UTC, unchanged since Nov 18, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://zorvu.app/mcp: tools/list returned 4 tools to an anonymous client, including precheck_transaction (irreversible), stock_sell_depth (write), check_token (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "precheck_transaction" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The input addresses people (input.tx.to): what it sends cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http zorvu https://zorvu.app/mcpclaude mcp add --transport http zorvu https://zorvu.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__zorvu__find_stock_token"
],
"ask": [
"mcp__zorvu__precheck_transaction",
"mcp__zorvu__stock_sell_depth",
"mcp__zorvu__check_token"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as zorvu. Review it before you use it.
Capability tags behind 4 rules
- mcp__zorvu__precheck_transaction untrusted-input, outbound
- mcp__zorvu__stock_sell_depth untrusted-input
- mcp__zorvu__check_token untrusted-input
- mcp__zorvu__find_stock_token untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.christopherjjellison-maker/zorvu/verify?hash=8de5b0eba27020de0478c2073131770a570ed1c0d62a2bfa7ff71af5330fadf6" | jq -e '.changed == false'Pinned hash 8de5b0eba270, from Nov 18, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.christopherjjellison-maker/zorvu/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.christopherjjellison-maker/zorvu)Source: MCP Registry. Synced Nov 18, 2026, 14:18 UTC.
Zorvu MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Zorvu MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Zorvu MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Zorvu MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: precheck_transaction.
What tools does the Zorvu MCP server have?
- 4 tools: 1 irreversible, 2 write, 1 read. precheck_transaction, stock_sell_depth, check_token and find_stock_token.
Does the Zorvu MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Zorvu MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): precheck_transaction.
Has the Zorvu MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.