Skip to content

WARN Firehose — Labor Market Intelligence MCP server

io.github.sendkamal/warn-firehosesendkamalstreamable-httpv1.1.0Scanned

WARN layoffs, H-1B/LCA visas, SEC 8-K, bankruptcies, DOL claims & JOLTS for all 50 US states.

12 tools: 2 change things and 10 only read.

Tools: 0 delete, 0 irreversible, 2 write, 10 read.
  • Reads private data · 1
  • Reads text others write · 0
  • Can send data out · 0
  • No findings

The remote endpoint did not answer the last look. Remote posture

Anlyon alternative

2 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 WARN Firehose — Labor Market Intelligence MCP server can do

The WARN Firehose — Labor Market Intelligence MCP server is published by the GitHub account sendkamal. It has 12 tools. It can create or change data (2 tools: authenticate and export_records), but cannot delete data. 10 tools only read.

1 tool reads private data (get_stats).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Nov 6, 2026, version 1.1.0.

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.

12 tools

Changes things 2Claude Code: ask
  • authenticateAuthenticate with your LaborCurrent API key.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
    Authenticate with your LaborCurrent API key. Returns your tier and access level. Args: api_key: Your LaborCurrent API key (starts with wf_)
  • export_recordsExport WARN records in bulk.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
    Export WARN records in bulk. Requires Pro tier or higher. Returns up to 500 records with full field details. For CSV/Parquet downloads, use the REST API at /api/export/. Get your API key at laborcurrent.com/account Args: api_key: Your LaborCurrent API key (Pro tier required) state: Optional 2-letter state code filter company: Optional company name filter (partial match) days: Look back this many days (default 90, max 730) limit: Max records to return (default 100, max 500)
Only reads 10Show 10 read-only tools
  • get_company_layoffsGet all WARN Act layoff notices for a specific company.No findings

    Why it is in this group

    • The name "get_company_layoffs" says "get": a word for reading.
    Description, as the server wrote it
    Get all WARN Act layoff notices for a specific company. Args: company: Company name to search for (partial match supported) api_key: Optional API key for higher rate limits
  • get_market_pulseGet a single-call market snapshot across all 6 datasets.No findings

    Why it is in this group

    • The name "get_market_pulse" says "get": a word for reading.
    Description, as the server wrote it
    Get a single-call market snapshot across all 6 datasets. Returns: WARN stats (30d trend), top industries, at-risk companies, LCA/H-1B counts, DOL claims, SEC filings, bankruptcies, JOLTS snapshot. Args: api_key: Optional API key for higher rate limits
  • get_pricingReturn LaborCurrent pricing tiers, included tools, and signup URLs.No findings

    Why it is in this group

    • The name "get_pricing" says "get": a word for reading.
    Description, as the server wrote it
    Return LaborCurrent pricing tiers, included tools, and signup URLs. Use this when the user asks about pricing, hits a rate limit, or wants to upgrade. Returns tier prices, daily call limits, included datasets, and direct signup links so the user can act immediately.
  • get_recent_layoffsGet the most recent WARN Act layoff notices.No findings

    Why it is in this group

    • The name "get_recent_layoffs" says "get": a word for reading.
    Description, as the server wrote it
    Get the most recent WARN Act layoff notices. Args: days: Look back this many days (default 30) state: Optional state filter (2-letter code) limit: Max results (default 25, max 100) api_key: Optional API key for higher rate limits
  • get_risk_signalGet companies ranked by composite distress signal across all datasets.No findings

    Why it is in this group

    • The name "get_risk_signal" says "get": a word for reading.
    Description, as the server wrote it
    Get companies ranked by composite distress signal across all datasets. Combines WARN layoff volume/recency, SEC restructuring filings, bankruptcy filings, and H-1B denial rates into a single risk score. Levels: Critical (7+), Elevated (4-6), Moderate (2-3), Low (1). Requires Starter tier or higher. Get your API key at laborcurrent.com/account Args: state: Optional 2-letter state code to filter min_score: Minimum risk score (default 3) limit: Max results (default 15, max 50) api_key: Your LaborCurrent API key (Starter tier required)
  • get_state_intelligenceGet a unified state profile combining all 6 datasets for a US state.No findings

    Why it is in this group

    • The name "get_state_intelligence" says "get": a word for reading.
    Description, as the server wrote it
    Get a unified state profile combining all 6 datasets for a US state. Returns WARN notices, LCA petitions, H-1B approvals/denials, DOL claims, bankruptcy matches, JOLTS data, and a composite distress score. Requires Pro tier or higher. Get your API key at laborcurrent.com/account Args: state_code: Two-letter state abbreviation (e.g. CA, TX, NY) api_key: Your LaborCurrent API key (Pro tier required)
  • get_state_summaryGet a summary of WARN Act layoff data for a specific US state.No findings

    Why it is in this group

    • The name "get_state_summary" says "get": a word for reading.
    Description, as the server wrote it
    Get a summary of WARN Act layoff data for a specific US state. Args: state: Two-letter state code (e.g. CA, TX, NY, FL) api_key: Optional API key for higher rate limits
  • get_statsGet overall statistics about the LaborCurrent database.Reads private dataNo findings

    Why it is in this group

    • The name "get_stats" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "database": it reads databases.
    Description, as the server wrote it
    Get overall statistics about the LaborCurrent database.
  • get_talent_pipelineFind available talent from recent layoffs, cross-referenced with LCA visa roles.No findings

    Why it is in this group

    • The name "get_talent_pipeline" says "get": a word for reading.
    Description, as the server wrote it
    Find available talent from recent layoffs, cross-referenced with LCA visa roles. Shows what occupations/skills each laid-off company was hiring for. Useful for recruiters targeting skilled workers from recently laid-off companies. Requires Starter tier or higher. Get your API key at laborcurrent.com/account Args: state: Optional 2-letter state code days: Look back this many days (default 90) limit: Max results (default 15, max 50) api_key: Your LaborCurrent API key (Starter tier required)
  • search_layoffsSearch WARN Act layoff notices by company name, city, or keyword.No findings

    Why it is in this group

    • The name "search_layoffs" says "search": a word for reading.
    Description, as the server wrote it
    Search WARN Act layoff notices by company name, city, or keyword. Args: query: Search term (company name, city, etc.) state: Optional 2-letter state code to filter (e.g. CA, TX, NY) limit: Max results to return (default 20, max 100) api_key: Optional API key for higher rate limits

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 untrusted-input or outbound.

Reads private data1
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.

The remote endpoint did not answer the last look

Looked at Nov 20, 2026, 19:10 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: The server redirected a POST to a different request.

Posture changes

  1. Nov 13, 2026
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

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.

  1. PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
    • Reachable: yes to no
    • HTTP status of an anonymous initialize: 200 to none
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 2 to 0
    • Protocol version: 2025-06-18 to none

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http warn-firehose https://warnfirehose.com/mcp/
claude mcp add --transport http warn-firehose https://warnfirehose.com/mcp/

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__warn-firehose__get_pricing",
      "mcp__warn-firehose__search_layoffs",
      "mcp__warn-firehose__get_state_summary",
      "mcp__warn-firehose__get_recent_layoffs",
      "mcp__warn-firehose__get_stats",
      "mcp__warn-firehose__get_company_layoffs",
      "mcp__warn-firehose__get_talent_pipeline",
      "mcp__warn-firehose__get_risk_signal",
      "mcp__warn-firehose__get_market_pulse",
      "mcp__warn-firehose__get_state_intelligence"
    ],
    "ask": [
      "mcp__warn-firehose__authenticate",
      "mcp__warn-firehose__export_records"
    ],
    "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 warn-firehose. Review it before you use it.

Capability tags behind 1 rule
  • mcp__warn-firehose__get_stats private-data

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.sendkamal/warn-firehose/verify?hash=646f5040b460e270ca797d14f45908d21f78d0ba8f261b89e606eda60db0943a" | jq -e '.changed == false'

Pinned hash 646f5040b460, from Nov 6, 2026, 11:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.sendkamal/warn-firehose/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.sendkamal/warn-firehose
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.sendkamal/warn-firehose.svg)](https://radar.anlyon.com/servers/io.github.sendkamal/warn-firehose)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:49 UTC.

WARN Firehose — Labor Market Intelligence MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the WARN Firehose — Labor Market Intelligence MCP server safe?

No scan can promise that. What its definitions show: 12 tools, 2 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 WARN Firehose — Labor Market Intelligence MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the WARN Firehose — Labor Market Intelligence 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 WARN Firehose — Labor Market Intelligence MCP server have?

12 tools: 2 write, 10 read. authenticate, export_records, get_pricing, search_layoffs, get_state_summary, get_recent_layoffs, get_stats, get_company_layoffs and 4 more.

Does the WARN Firehose — Labor Market Intelligence MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the WARN Firehose — Labor Market Intelligence MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the WARN Firehose — Labor Market Intelligence MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 6, 2026.