Koskamo

AI Lifeline MCP

A read-only MCP server providing access to daily observed values regarding the survival conditions of AI, including physical, institutional, and capital indicators across Japan, US, EU, and Singapore. It exposes tools to list, search, and retrieve specific data series with units, dates, and sources.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AI Lifeline MCP logo, by Pasokon Sensei Co., Ltd.Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by Pasokon Sensei Co., Ltd.
MCP endpoint (Streamable HTTP)
https://ai-lifeline.org/api/mcp.php
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

4 of 4 have a description · 0 of 4 declare behavior hints · 0 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to ai-lifeline.org ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • List available AI survival condition data series
  • Retrieve specific time-series data with units and sources
  • Check server health and status
  • Search for specific data series by keyword

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
ai-lifeline 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Read-only access to AI Lifeline (https://ai-lifeline.org/): daily observed values on power, water, public finance, disasters, data centers, GPU prices, regulation and market participation for Japan, the United States, the EU and Singapore. Every value is returned with its unit, observation date (observed_at), primary source URL (source_url) and the time the site file was generated (checked_at). Values are exactly those published on the site; nothing is re-aggregated. Check get_health before treating a value as fresh: stale=true means the series is past its expected update.

Tools

4 advertised

list_series
Advertised by the server during the last successful anonymous check.

List the chapters AI Lifeline publishes (one entry per chapter page, from /api/index.json) with their page URL, API URL, the one-sentence answer line, the headline value (value, unit, date) and the series ids that belong to the chapter. region: optional filter, one of 'jp', 'us', 'eu', 'sg'. Returns exactly what index.json and series.json contain; no re-aggregation.

list_series input schema
{
  "type": "object",
  "properties": {
    "region": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Region",
      "default": null
    }
  },
  "additionalProperties": false
}
get_series
Advertised by the server during the last successful anonymous check.

Return one series by its permanent id ('<region>/<chapter>/<series_key>', e.g. 'jp/fiscal/jgb_yield') with the latest published value, unit, observed_at (observation date), value_status (final/provisional), the primary source (name, source_url, license, attribution), update frequency, last confirmed date, staleness judgement from health.json, limitations, page and API URLs, and checked_at (generation time of the site files). Values are the ones published by the site; nothing is recomputed.

get_series input schema
{
  "type": "object",
  "required": [
    "series_id"
  ],
  "properties": {
    "series_id": {
      "type": "string",
      "title": "Series Id"
    }
  },
  "additionalProperties": false
}
get_health
Advertised by the server during the last successful anonymous check.

Return the liveness of AI Lifeline itself from /api/health.json: site_status (ok/degraded), totals (series, stale, fetch_failed, source_under_review, not_measured), the staleness rule as written, the generation time per edition, and per series: last confirmed observation date, update frequency, next expected update, stale flag, age_days and the status of the last fetch. region: optional filter 'jp'|'us'|'eu'|'sg'. only_stale: return only series with stale=true. Nothing here judges the observed world.

get_health input schema
{
  "type": "object",
  "properties": {
    "region": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Region",
      "default": null
    },
    "only_stale": {
      "type": "boolean",
      "title": "Only Stale",
      "default": false
    }
  },
  "additionalProperties": false
}
search_series
Advertised by the server during the last successful anonymous check.

Search published series by words in the series id, name, chapter, unit or source name (case-insensitive substring match over /api/series.json). Returns up to `limit` matches with series_id, name, unit, region, chapter, update_frequency, last_confirmed and source name; use get_series for the value. No ranking beyond match order in the registry.

search_series input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20
    },
    "query": {
      "type": "string",
      "title": "Query"
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
661 ms
95th percentile latency
661 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 661 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http ai-lifeline-mcp https://ai-lifeline.org/api/mcp.php

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add ai-lifeline-mcp --url https://ai-lifeline.org/api/mcp.php

Cursor

Merge this server into .cursor/mcp.json in your project, then enable ai-lifeline-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "ai-lifeline-mcp": {
      "url": "https://ai-lifeline.org/api/mcp.php"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "ai-lifeline-mcp": {
      "type": "streamableHttp",
      "url": "https://ai-lifeline.org/api/mcp.php",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start ai-lifeline-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "ai-lifeline-mcp": {
      "type": "http",
      "url": "https://ai-lifeline.org/api/mcp.php"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http ai-lifeline-mcp https://ai-lifeline.org/api/mcp.php

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://ai-lifeline.org/api/mcp.php

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "ai-lifeline-mcp": {
      "serverUrl": "https://ai-lifeline.org/api/mcp.php"
    }
  }
}

Let your agent find its tools

Find servers like AI Lifeline MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run AI Lifeline MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing