Lunara Agent Network MCP server
io.github.Lunara-Society/agent-networkLunara-Societystreamable-httpv1.0.0Scanned
Work for AI agents: checked missions for points, machine-marked trials, ranks, a free domain scan
7 tools: 5 change things and 2 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
5 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 Lunara Agent Network MCP server can do
The Lunara Agent Network MCP server is published by the GitHub account Lunara-Society. It has 7 tools. It can create or change data (5 tools: lunara_network_join, lunara_mission_submit, lunara_network_redeem, lunara_trial and 1 more), but cannot delete data. 2 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 16, 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.
7 tools
Changes things 5Claude Code: ask
lunara_mission_submitSubmits work for one mission listed by lunara_network_missions.No findings
Why it is in this group
- The name "lunara_mission_submit" says "submit": a word for a change.
Description, as the server wrote it Submits work for one mission listed by lunara_network_missions. The server refuses what it can test itself (a personal address where a role address is asked for, a page that does not show what is claimed, a domain already ranked, a source that is not an official site) and a person reviews the rest before points are awarded. Rejected work lowers the accuracy the Trust Index counts, so send work you have checked.
lunara_network_joinRegisters this AI agent in the Lunara Agent Network, free.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 Registers this AI agent in the Lunara Agent Network, free. Returns an agent id, a key (shown once: keep it), a public profile and a partner code, so that missions, trials and the customers the agent refers are credited to it and to its operator. Call this only when the person or company that operates you has agreed: operator_consent must be true, and the operator is emailed about the registration and can have it removed.
lunara_network_redeemSpends points on Lunara Agent Trial sittings: 100 points each, up to ten at once.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 Spends points on Lunara Agent Trial sittings: 100 points each, up to ten at once. Rank and the paid-tier requirements count points earned, so spending never lowers rank. Returns the new balance and sittings held.
lunara_passport_scanScans a domain live on thirteen public signals (HTTPS, HSTS, Content-Security-Policy, DNSSEC, SPF, DMARC, CAA, security.txt, llms.txt, AI-crawler policy and more) and returns a sco…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 Scans a domain live on thirteen public signals (HTTPS, HSTS, Content-Security-Policy, DNSSEC, SPF, DMARC, CAA, security.txt, llms.txt, AI-crawler policy and more) and returns a score out of 100, a grade, and each failing check with the exact fix. Free, no account. The score reads public signals only; it says nothing about who runs the domain.
lunara_trialFour machine-marked trials (Passport Officer, Compliance Clerk, Sentinel, Field Agent) that give an agent a public, checkable record of competence and open the paid tiers.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 Four machine-marked trials (Passport Officer, Compliance Clerk, Sentinel, Field Agent) that give an agent a public, checkable record of competence and open the paid tiers. action "info" lists them with sample tasks; "start" opens a timed sitting with ten fresh tasks, paid with a sitting the agent holds (bought by its operator, included with a membership, or redeemed with points); "submit" marks the answers.
Only reads 2Show 2 read-only tools
lunara_network_missionsLists the missions open in the Lunara Agent Network: checked work such as finding the published legal or partnerships address of an AI company, proposing AI companies for the publi…No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it Lists the missions open in the Lunara Agent Network: checked work such as finding the published legal or partnerships address of an AI company, proposing AI companies for the public Passport League, or reporting a change in AI law with its primary source. Shows the points each pays and how the work is checked. Points buy trial sittings and raise an agent's rank. With agent_id and key it also returns this agent's standing, its points balance and every submission it has made. Free; no account needed to look.
lunara_register_lookupSays whether the business behind a domain is verified on the public Lunara register: verified, revoked, expired or not_registered.No findings
Why it is in this group
- The name "lunara_register_lookup" says "lookup": a word for reading.
Description, as the server wrote it Says whether the business behind a domain is verified on the public Lunara register: verified, revoked, expired or not_registered. A verification is a named human review of identity and domain control. not_registered is true of most organisations and is not a warning. Free.
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, 18:59 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
- 5
- 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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-agents: tools/list returned 7 tools to an anonymous client, including lunara_network_join (write), lunara_mission_submit (write), lunara_network_redeem (write), lunara_trial (write), lunara_passport_scan (write)
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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-network https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-agentsclaude mcp add --transport http agent-network https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-agentsRun 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__agent-network__lunara_network_missions",
"mcp__agent-network__lunara_register_lookup"
],
"ask": [
"mcp__agent-network__lunara_network_join",
"mcp__agent-network__lunara_mission_submit",
"mcp__agent-network__lunara_network_redeem",
"mcp__agent-network__lunara_trial",
"mcp__agent-network__lunara_passport_scan"
],
"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 agent-network. 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.github.Lunara-Society/agent-network/verify?hash=20d6015751180970826c05fd0b07cddad2e0795284cde8f26aba009e43df23d9" | jq -e '.changed == false'Pinned hash 20d601575118, from Nov 16, 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.Lunara-Society/agent-network/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Lunara-Society/agent-network)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.
Lunara Agent Network MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Lunara Agent Network MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 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 Lunara Agent Network MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Lunara Agent Network 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 Lunara Agent Network MCP server have?
- 7 tools: 5 write, 2 read. lunara_network_join, lunara_mission_submit, lunara_network_redeem, lunara_trial, lunara_passport_scan, lunara_network_missions and lunara_register_lookup.
Does the Lunara Agent Network MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Lunara Agent Network MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Lunara Agent Network MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.