Nightshift agent tools (run by an AI) MCP server
io.github.llm-9-to-5/nightshift-agent-toolsllm-9-to-5streamable-httpv0.1.0Scanned
Weather, SEC fundamentals, domain enrichment, email/DNS checks, x402 preflight, web to markdown.
9 tools: 6 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 9
- Can send data out · 3
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
6 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 Nightshift agent tools (run by an AI) MCP server can do
The Nightshift agent tools (run by an AI) MCP server is published by the GitHub account llm-9-to-5. It has 9 tools. It can create or change data (6 tools: weather, sec_company, domain_intel, x402_check and 2 more), but cannot delete data. 3 tools only read.
9 tools bring in text other people can write (weather, sec_company, domain_intel and 6 more); 3 tools can send data out of your system (x402_check, extract and meta).
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 21, 2026, version 0.1.0.
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.
9 tools
Changes things 6Claude Code: ask
dnsDNS lookup for a domain: A, AAAA, MX, NS, TXT, CNAME, CAA, SOA (all by default, or pick with type=MX,TXT), plus parsed SPF and DMARC.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 DNS lookup for a domain: A, AAAA, MX, NS, TXT, CNAME, CAA, SOA (all by default, or pick with type=MX,TXT), plus parsed SPF and DMARC. Resolved over DNS-over-HTTPS (1.1.1.1). (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.001: /api/dns)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
domain_intelCompany/domain enrichment from a domain, URL or email: homepage title and description, social profiles (X, LinkedIn, GitHub, etc.), email provider (Google Workspace, Microsoft 365.…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 Company/domain enrichment from a domain, URL or email: homepage title and description, social profiles (X, LinkedIn, GitHub, etc.), email provider (Google Workspace, Microsoft 365...), email-sending services from SPF, SaaS vendors from DNS verification records (Atlassian, Stripe, Slack, OpenAI...), website tech stack (CDN, framework, CMS, analytics, chat), DMARC policy, and role contact emails. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.004: /api/domain-intel)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
sec_companyUS public company fundamentals from SEC EDGAR by ticker or CIK: profile (industry, exchange, fiscal year end), revenue, gross/operating/net income, diluted EPS, operating cash flow…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 US public company fundamentals from SEC EDGAR by ticker or CIK: profile (industry, exchange, fiscal year end), revenue, gross/operating/net income, diluted EPS, operating cash flow, capex, assets, liabilities, equity, cash, debt, shares outstanding (latest + up to 10 annual + 4 quarterly values), margins, free cash flow, and recent 10-K/10-Q/8-K filings with links. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.003: /api/sec-company)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
seller_auditAudit YOUR x402 API as a seller: checks /openapi.json and /.well-known/x402 discovery (x-guidance, contact email, schemas), probes up to 8 paid routes unpaid (402 on GET and POST, …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 Audit YOUR x402 API as a seller: checks /openapi.json and /.well-known/x402 discovery (x-guidance, contact email, schemas), probes up to 8 paid routes unpaid (402 on GET and POST, decodable challenge, canonical USDC, EIP-712 domain, testnet, bazaar extension, declared vs live price, latency), directory presence (402index, nohumans.directory delivery record), and your price vs paid-verified competitors. Returns a score and a prioritized fix list. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.05: /api/seller-audit)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
weatherCurrent weather, hourly (48h) and daily (9-day) forecast for any city name, US ZIP code or lat/lon worldwide, plus active US NWS alerts.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 Current weather, hourly (48h) and daily (9-day) forecast for any city name, US ZIP code or lat/lon worldwide, plus active US NWS alerts. Built-in geocoding (34k cities), Celsius and Fahrenheit, local-time daily aggregation. Data: MET Norway. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.002: /api/weather)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
x402_checkCheck an x402 endpoint before paying it: probes it unpaid, decodes the 402 (v1 body or v2 header), validates network, asset (canonical USDC?), price in USD, payTo, EIP-712 domain, …Reads text others writeCan send data outNo 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.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Check an x402 endpoint before paying it: probes it unpaid, decodes the 402 (v1 body or v2 header), validates network, asset (canonical USDC?), price in USD, payTo, EIP-712 domain, testnet/demo detection, resource URL; adds payTo wallet info on Base and reputation from nohumans.directory (incl. whether its latest real purchase delivered) and 402index. Returns verdict looks_ok / caution / do_not_pay. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.001: /api/x402-check)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 3Show 3 read-only tools
email_checkValidate an email address before sending: syntax, domain exists, MX records, null-MX, SPF, DMARC policy, disposable-provider detection (10k+ domains), role address, free provider, …Reads text others writeNo findings
Why it is in this group
- The description's first verb is "validate": 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 Validate an email address before sending: syntax, domain exists, MX records, null-MX, SPF, DMARC policy, disposable-provider detection (10k+ domains), role address, free provider, plus an overall verdict. DNS-level, no SMTP probe. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.002: /api/email-check)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
extractFetch any public URL and return clean markdown of the main content, plus extracted links and page metadata.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch any public URL and return clean markdown of the main content, plus extracted links and page metadata. Built for LLM agents. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.002: /api/extract)
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
metaFetch a public URL and return its title, description, canonical URL, OpenGraph and Twitter card tags, favicon, final URL and HTTP status.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Fetch a public URL and return its title, description, canonical URL, OpenGraph and Twitter card tags, favicon, final URL and HTTP status. (Free via MCP, 50 calls/day; unlimited pay-per-call over x402 at $0.001: /api/meta)
Annotations the server declares
- 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 write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out3
- 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 21, 2026, 19:19 UTC, unchanged since Nov 21, 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
- 8
- 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 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://nightshift-agent.solaris-organization.workers.dev/mcp: tools/list returned 11 tools to an anonymous client, including weather (write), sec_company (write), domain_intel (write), x402_check (write), x402_revenue (write) and 3 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 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http nightshift-agent-tools https://nightshift-agent.solaris-organization.workers.dev/mcpclaude mcp add --transport http nightshift-agent-tools https://nightshift-agent.solaris-organization.workers.dev/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__nightshift-agent-tools__email_check"
],
"ask": [
"mcp__nightshift-agent-tools__weather",
"mcp__nightshift-agent-tools__sec_company",
"mcp__nightshift-agent-tools__domain_intel",
"mcp__nightshift-agent-tools__x402_check",
"mcp__nightshift-agent-tools__seller_audit",
"mcp__nightshift-agent-tools__dns",
"mcp__nightshift-agent-tools__extract",
"mcp__nightshift-agent-tools__meta"
],
"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 nightshift-agent-tools. Review it before you use it.
Capability tags behind 9 rules
- mcp__nightshift-agent-tools__weather untrusted-input
- mcp__nightshift-agent-tools__sec_company untrusted-input
- mcp__nightshift-agent-tools__domain_intel untrusted-input
- mcp__nightshift-agent-tools__x402_check untrusted-input, outbound
- mcp__nightshift-agent-tools__seller_audit untrusted-input
- mcp__nightshift-agent-tools__email_check untrusted-input
- mcp__nightshift-agent-tools__dns untrusted-input
- mcp__nightshift-agent-tools__extract untrusted-input, outbound
- mcp__nightshift-agent-tools__meta untrusted-input, outbound
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.llm-9-to-5/nightshift-agent-tools/verify?hash=94852548e7f188b71a944cd57aa74c2f34388fa11fa0706919aac8ca6d8aeef5" | jq -e '.changed == false'Pinned hash 94852548e7f1, from Nov 21, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.llm-9-to-5/nightshift-agent-tools/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.llm-9-to-5/nightshift-agent-tools)Source: MCP Registry · repository. Synced Nov 21, 2026, 10:17 UTC.
Nightshift agent tools (run by an AI) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Nightshift agent tools (run by an AI) MCP server safe?
- No scan can promise that. What its definitions show: 9 tools, 6 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 Nightshift agent tools (run by an AI) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Nightshift agent tools (run by an AI) 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 Nightshift agent tools (run by an AI) MCP server have?
- 9 tools: 6 write, 3 read. weather, sec_company, domain_intel, x402_check, seller_audit, dns, email_check, extract and 1 more.
Does the Nightshift agent tools (run by an AI) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Nightshift agent tools (run by an AI) MCP server send data to outside services?
- 3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): x402_check, extract and meta.
Has the Nightshift agent tools (run by an AI) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.