Collar Guardrail — Pre-Trade Risk Layer MCP server
io.github.aiguardrail/backendaiguardrailstreamable-httpv1.0.5Scanned
Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.
6 tools: 5 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 3 findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
5 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Collar Guardrail — Pre-Trade Risk Layer MCP server can do
The Collar Guardrail — Pre-Trade Risk Layer MCP server is published by the GitHub account aiguardrail. It has 6 tools. It can create or change data (5 tools: evaluate_trade, evaluate_trade_paid, check_token_safety, simulate_balance and 1 more), but cannot delete data. 1 tool only reads.
2 tools bring in text other people can write (check_token_safety and get_supported_assets).
The fixed checks matched 3 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Last scanned Nov 3, 2026, version 1.0.5.
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.
6 tools
Changes things 5Claude Code: ask
check_token_safetyHoneypot / contract safety check for any ERC-20 token.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 Honeypot / contract safety check for any ERC-20 token. Returns a severity classification (safe / warn / danger), the specific risk factors detected, and the result of a simulated sell. When severity=danger, the next `evaluate_trade` for the same contract is automatically denied regardless of any other checks. This is a heuristic bytecode + simulation check, not a formal audit. Use it before trading unknown tokens, memecoins, or any contract that is absent from the official Robinhood Chain registry. It is safe to call repeatedly; no transaction is ever sent.
Annotations the server declares
- title: Check Token Safety
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
evaluate_tradePre-trade risk check for a proposed trade.1 finding
Why it is in this group
- The name "evaluate_trade" says "evaluate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "evaluate_trade" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_trade" says "evaluate": a word for a change.
Description, as the server wrote it Pre-trade risk check for a proposed trade. Call this BEFORE executing any trade and treat a "deny" decision as a hard stop. Evaluated at a fixed Tier 1 ceiling ($5,000 notional). For higher limits, use `evaluate_trade_paid` (Tier 2, $25,000) which settles an x402 payment on-chain.
Annotations the server declares
- title: Evaluate Trade (Free)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
evaluate_trade_paidPre-trade risk check gated by an x402 payment.2 findings
Why it is in this group
- The name "evaluate_trade_paid" says "evaluate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...required — the on-chain payment is the credential. FLOW ---- 1. Call WITHOUT payment_pro..."
- Warn
The server marks "evaluate_trade_paid" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_trade_paid" says "evaluate": a word for a change.
Description, as the server wrote it Pre-trade risk check gated by an x402 payment. Evaluated as COLR Tier 2: $25,000 notional ceiling, 10/25 per-minute rate limits. No COLR holdings are required — the on-chain payment is the credential. FLOW ---- 1. Call WITHOUT payment_proof → the tool returns a `PaymentRequiredOutput` describing the on-chain payment (network, asset, amount, payTo, resource). 2. Settle the payment on-chain using an x402-capable client. The facilitator returns a proof string. 3. Call again with `payment_proof=<proof>` → the tool forwards the proof to the guardrail's x402-paid endpoint and returns a full `EvaluateTradeOutput` with `tier=2`.
Annotations the server declares
- title: Evaluate Trade (x402 Paid, Tier 2)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
simulate_balanceSimulate a wallet's ERC-20 balance after a hypothetical trade using eth_call state override.No 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.
Description, as the server wrote it Simulate a wallet's ERC-20 balance after a hypothetical trade using eth_call state override. Read-only: no transaction is ever sent.
Annotations the server declares
- title: Simulate Balance
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_audit_trailVerify the tamper-evident audit trail for a wallet's past guardrail decisions.No 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.
Description, as the server wrote it Verify the tamper-evident audit trail for a wallet's past guardrail decisions.
Annotations the server declares
- title: Verify Audit Trail
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 1Show 1 read-only tool
get_supported_assetsList every asset in the guardrail's official Robinhood Chain registry, with its canonical contract address.Reads text others writeNo findings
Why it is in this group
- The name "get_supported_assets" says "get": 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 List every asset in the guardrail's official Robinhood Chain registry, with its canonical contract address.
Annotations the server declares
- title: Get Supported Assets
- 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 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, 19:01 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- 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
The probe stopped: api.collarguardrail.com does not resolve.
Posture changes
- Nov 13, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 503 to none
- Nov 6, 2026
- HTTP status of an anonymous initialize: 200 to 503
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
- Warnevaluate_trade
The server marks "evaluate_trade" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_trade" says "evaluate": a word for a change.
The server marks "evaluate_trade_paid" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "evaluate_trade_paid" says "evaluate": a word for a change.
The description mentions "credential".
What this check looks forMatched text
description: "...required — the on-chain payment is the credential. FLOW ---- 1. Call WITHOUT payment_pro..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 503 -> none.View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 503 to none
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 503; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 5 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 503
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 5 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.0.5. Values in angle brackets are yours to fill in.
claude mcp add --transport http backend https://api.collarguardrail.com/mcp-http/mcpclaude mcp add --transport http backend https://api.collarguardrail.com/mcp-http/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__backend__get_supported_assets"
],
"ask": [
"mcp__backend__evaluate_trade",
"mcp__backend__evaluate_trade_paid",
"mcp__backend__check_token_safety",
"mcp__backend__simulate_balance",
"mcp__backend__verify_audit_trail"
],
"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 backend. Review it before you use it.
Capability tags behind 2 rules
- mcp__backend__check_token_safety untrusted-input
- mcp__backend__get_supported_assets 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.aiguardrail/backend/verify?hash=c75648214ac9ba2b4ed6091be7bfb9ccf89711ed582596b3e88cf39d7ce860b2" | jq -e '.changed == false'Pinned hash c75648214ac9, from Nov 3, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.aiguardrail/backend/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.aiguardrail/backend)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:22 UTC.
Collar Guardrail — Pre-Trade Risk Layer MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Collar Guardrail — Pre-Trade Risk Layer MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 5 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Collar Guardrail — Pre-Trade Risk Layer MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Collar Guardrail — Pre-Trade Risk Layer 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 Collar Guardrail — Pre-Trade Risk Layer MCP server have?
- 6 tools: 5 write, 1 read. evaluate_trade, evaluate_trade_paid, check_token_safety, simulate_balance, verify_audit_trail and get_supported_assets.
Does the Collar Guardrail — Pre-Trade Risk Layer MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the Collar Guardrail — Pre-Trade Risk Layer MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Collar Guardrail — Pre-Trade Risk Layer MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 3, 2026.