Sunaiva Gate — Agent Rule Enforcement MCP server
io.sunaivacore/gatesunaivacore.iostreamable-httpv2.0.4Scanned
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
16 tools: 2 can delete or cancel things, 7 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here can delete or cancel 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 Sunaiva Gate — Agent Rule Enforcement MCP server can do
The Sunaiva Gate — Agent Rule Enforcement MCP server is published by sunaivacore.io, a domain the MCP Registry verified. It has 16 tools. It can delete or cancel things (2 tools: reset_rule_mode and delete_custom_rule) and create or change data (7 tools: update_rules, ship_confidence_check, audit_verify, set_rule_mode and 3 more). 7 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 18, 2026, version 2.0.4.
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.
16 tools
Deletes or cancels 2Claude Code: deny
delete_custom_ruleDelete a custom rule.No findings
Why it is in this group
- The name "delete_custom_rule" says "delete": a word for removing or ending something.
Description, as the server wrote it Delete a custom rule. Requires API key (Pro+).
reset_rule_modeRemove a mode override for a rule, reverting it to its default enforcement mode.No findings
Why it is in this group
- The name "reset_rule_mode" says "reset": a word for a change.
- The description's first verb is "remove": a word for removing or ending something.
Description, as the server wrote it Remove a mode override for a rule, reverting it to its default enforcement mode. Requires API key (Pro+).
Changes things 7Claude Code: ask
add_custom_ruleCreate a custom detection rule in the backend.No findings
Why it is in this group
- The name "add_custom_rule" says "add": a word for a change.
Description, as the server wrote it Create a custom detection rule in the backend. Requires API key (Pro+).
apply_presetApply a preset bundle, activating all its included rules.No findings
Why it is in this group
- The name "apply_preset" says "apply": a word for a change.
Description, as the server wrote it Apply a preset bundle, activating all its included rules. Requires API key (Pro+).
audit_verify[Planned — not yet implemented on the remote endpoint, returns NOT_IMPLEMENTED] Forward-linked hash-chain / ed25519 audit-log verification is not yet built in this backend.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.
Description, as the server wrote it [Planned — not yet implemented on the remote endpoint, returns NOT_IMPLEMENTED] Forward-linked hash-chain / ed25519 audit-log verification is not yet built in this backend.
set_rule_modeSet enforcement mode (shadow/advisory/enforce) for a specific rule.No findings
Why it is in this group
- The name "set_rule_mode" says "set": a word for a change.
Description, as the server wrote it Set enforcement mode (shadow/advisory/enforce) for a specific rule. Requires API key (Pro+).
ship_confidence_check[Planned — not yet implemented on the remote endpoint, returns NOT_IMPLEMENTED] Ship Confidence Gate (Rule 42) dual-tier authorization is not yet built in this backend.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.
Description, as the server wrote it [Planned — not yet implemented on the remote endpoint, returns NOT_IMPLEMENTED] Ship Confidence Gate (Rule 42) dual-tier authorization is not yet built in this backend.
update_custom_ruleUpdate an existing custom rule.No findings
Why it is in this group
- The name "update_custom_rule" says "update": a word for a change.
Description, as the server wrote it Update an existing custom rule. Requires API key (Pro+).
update_rules[Planned — not yet implemented on the remote endpoint, returns NOT_IMPLEMENTED] Enable/disable is not backed by any route in this API; use set_rule_mode (shadow/advisory/enforce) i…No findings
Why it is in this group
- The name "update_rules" says "update": a word for a change.
Description, as the server wrote it [Planned — not yet implemented on the remote endpoint, returns NOT_IMPLEMENTED] Enable/disable is not backed by any route in this API; use set_rule_mode (shadow/advisory/enforce) instead, or the local `npx @sunaiva/gate` package.
Only reads 7Show 7 read-only tools
get_audit_logView recent gate decisions — blocks, warnings, passes, and bypasses.No findings
Why it is in this group
- The name "get_audit_log" says "get": a word for reading.
Description, as the server wrote it View recent gate decisions — blocks, warnings, passes, and bypasses.
get_rule_modesList all enforcement-mode overrides configured for the authenticated customer.No findings
Why it is in this group
- The name "get_rule_modes" says "get": a word for reading.
Description, as the server wrote it List all enforcement-mode overrides configured for the authenticated customer. Requires an account (Dev+).
get_rulesList active validation rules — the customer's TRUE enforced set (constitutional + recommended-default metadata on dev tier, all 69 premium rules on pro+).No findings
Why it is in this group
- The name "get_rules" says "get": a word for reading.
Description, as the server wrote it List active validation rules — the customer's TRUE enforced set (constitutional + recommended-default metadata on dev tier, all 69 premium rules on pro+). `category`/`preset` filter args are accepted but not applied server-side.
list_custom_rulesList all custom rules for the authenticated customer.No findings
Why it is in this group
- The name "list_custom_rules" says "list": a word for reading.
Description, as the server wrote it List all custom rules for the authenticated customer. Requires API key (Pro+).
list_presetsList available rule preset bundles.No findings
Why it is in this group
- The name "list_presets" says "list": a word for reading.
Description, as the server wrote it List available rule preset bundles. Requires API key (Dev+).
log_bypassRecord an intentional rule bypass with justification.No findings
Why it is in this group
- The name "log_bypass" says "log": a word for reading.
Description, as the server wrote it Record an intentional rule bypass with justification. Cannot bypass constitutional rules.
validate_actionCheck if a proposed action passes all active validation rules.No findings
Why it is in this group
- The name "validate_action" says "validate": a word for reading.
Description, as the server wrote it Check if a proposed action passes all active validation rules. Returns allowed/blocked with rule violations.
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 untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 19:14 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
- 9
- 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 9 tools that change things (2 destructive, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.sunaivacore.io: tools/list returned 16 tools to an anonymous client, including reset_rule_mode (destructive), delete_custom_rule (destructive), update_rules (write), ship_confidence_check (write), audit_verify (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
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 2.0.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http gate https://mcp.sunaivacore.ioclaude mcp add --transport http gate https://mcp.sunaivacore.ioRun 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__gate__validate_action",
"mcp__gate__log_bypass",
"mcp__gate__get_rules",
"mcp__gate__get_audit_log",
"mcp__gate__get_rule_modes",
"mcp__gate__list_custom_rules",
"mcp__gate__list_presets"
],
"ask": [
"mcp__gate__update_rules",
"mcp__gate__ship_confidence_check",
"mcp__gate__audit_verify",
"mcp__gate__set_rule_mode",
"mcp__gate__add_custom_rule",
"mcp__gate__update_custom_rule",
"mcp__gate__apply_preset"
],
"deny": [
"mcp__gate__reset_rule_mode",
"mcp__gate__delete_custom_rule"
]
}
}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 gate. Review it before you use it.
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.sunaivacore/gate/verify?hash=2b07e5b9c0f2b0e9f042c3d37718b6790f654cbffcfb2133751cbeb467c06bdc" | jq -e '.changed == false'Pinned hash 2b07e5b9c0f2, from Nov 18, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.sunaivacore/gate/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.sunaivacore/gate)Source: MCP Registry. Synced Oct 21, 2026, 18:52 UTC.
Sunaiva Gate — Agent Rule Enforcement MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Sunaiva Gate — Agent Rule Enforcement MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 9 of which can change, send or delete something, and 0 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 Sunaiva Gate — Agent Rule Enforcement MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: reset_rule_mode and delete_custom_rule.
Can the Sunaiva Gate — Agent Rule Enforcement 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 Sunaiva Gate — Agent Rule Enforcement MCP server have?
- 16 tools: 2 destructive, 7 write, 7 read. reset_rule_mode, delete_custom_rule, update_rules, ship_confidence_check, audit_verify, set_rule_mode, add_custom_rule, update_custom_rule and 8 more.
Does the Sunaiva Gate — Agent Rule Enforcement MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Sunaiva Gate — Agent Rule Enforcement MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Sunaiva Gate — Agent Rule Enforcement MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.