defi-agent MCP server
com.brainonbnb/defi-agentbrainonbnb.comstreamable-httpv1.0.1Scanned
PancakeSwap V3 range check for any position, free; re-centre plan paid, or free holding 1M $BOBAI.
2 tools: 2 change things.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- 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 defi-agent MCP server can do
The defi-agent MCP server is published by brainonbnb.com, a domain the MCP Registry verified. It has 2 tools. It can create or change data (2 tools: lp_position_look and lp_position_plan), but cannot delete data. None of its tools only reads.
2 tools bring in text other people can write (lp_position_look and lp_position_plan).
The fixed checks matched 1 finding (base64-blob). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 12, 2026, version 1.0.1.
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.
2 tools
Changes things 2Claude Code: ask
lp_position_lookRebalancing, the free half: look at a PancakeSwap V3 liquidity position on BNB Chain, read from the chain now — in range or not and how much room is left to each edge, what it hold…Reads text others write1 finding
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.
Findings
- Warn
The description contains a 42-character base64 string.
What this check looks forMatched text
description: "...runs itself (wallet 0xbFAA69233741924eD5b9d5DAA9B4Bf7B84567F0A). Reads only, signs..."
Description, as the server wrote it Rebalancing, the free half: look at a PancakeSwap V3 liquidity position on BNB Chain, read from the chain now — in range or not and how much room is left to each edge, what it holds and is worth in BNB, the fees it is owed and whether collecting them pays for the gas. Give a position id or a wallet that holds one; with neither, it reads the position this agent runs itself (wallet 0xbFAA69233741924eD5b9d5DAA9B4Bf7B84567F0A). Reads only, signs nothing.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
lp_position_planThe DeFi agent, on your position, the paid half (0.10 USD1, or half that in $BOBAI, or nothing for a wallet holding 1,000,000 $BOBAI (holder pass over x402: a signature, no transac…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 The DeFi agent, on your position, the paid half (0.10 USD1, or half that in $BOBAI, or nothing for a wallet holding 1,000,000 $BOBAI (holder pass over x402: a signature, no transaction — terms in the reply)): What the agent that runs this project's own PancakeSwap V3 position would decide about yours, from the same code: whether it is in range and how much room is left to each edge, what it holds and is worth in BNB, what it is owed in fees and whether collecting pays for its own gas, whether a re-set is due and in which width — the width that ended the most ahead against simply holding over the last week when every width was replayed over the recorded prices (its fees, less the gas of its re-sets, plus where it stood against a wallet that held), the width in use kept unless another leads it by a tenth — and what the wallet's spare BNB would add. It reads and plans; it signs nothing on your position. Calling this tool returns the terms; the answer is sold over x402 at https://agent.brainonbnb.com/answer?service=lp_position_plan (or hired through the ERC-8183 escrow for 0.10 $U).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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 or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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 20, 2026, 18:35 UTC, unchanged since Oct 22, 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
- 2
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent.brainonbnb.com/defi-agent/mcp: tools/list returned 2 tools to an anonymous client, including lp_position_look (write), lp_position_plan (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnlp_position_look
The description contains a 42-character base64 string.
What this check looks forMatched text
description: "...runs itself (wallet 0xbFAA69233741924eD5b9d5DAA9B4Bf7B84567F0A). Reads only, signs..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:lp_position_lookChanges thingsinputSchema
- Changed:lp_position_planChanges thingsannotations
Install
Pinned to version 1.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http defi-agent https://agent.brainonbnb.com/defi-agent/mcpclaude mcp add --transport http defi-agent https://agent.brainonbnb.com/defi-agent/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": [],
"ask": [
"mcp__defi-agent__lp_position_look",
"mcp__defi-agent__lp_position_plan"
],
"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 defi-agent. Review it before you use it.
Capability tags behind 2 rules
- mcp__defi-agent__lp_position_look untrusted-input
- mcp__defi-agent__lp_position_plan 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/com.brainonbnb/defi-agent/verify?hash=26f450c721ab1094c94f68e0a696c9f4efe5b2d9581841a9b85b17534bd4291d" | jq -e '.changed == false'Pinned hash 26f450c721ab, from Nov 12, 2026, 19:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.brainonbnb/defi-agent/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.brainonbnb/defi-agent)Source: MCP Registry. Synced Oct 21, 2026, 17:52 UTC.
defi-agent MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the defi-agent MCP server safe?
- No scan can promise that. What its definitions show: 2 tools, 2 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 defi-agent MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the defi-agent MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the defi-agent MCP server have?
- 2 tools: 2 write. lp_position_look and lp_position_plan.
Does the defi-agent MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the defi-agent MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the defi-agent MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.