Outage.Me MCP

Provides live cloud and SaaS outage intelligence, provider reliability metrics, and exploited CVE data derived from official status pages and CISA. It offers deterministic factual endpoints for active incidents and reliability indices, as well as natural language querying capabilities for agents.

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.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by outage.me

MCP endpoint (Streamable HTTP)

https://outage.me/mcp

Vendor documentation

What its tools do

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

Can change data (1)

report_observation

8 of 8 have a description · 8 of 8 declare behavior hints · 7 of 8 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 10:02 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Check currently active cloud provider incidents
Retrieve provider reliability indices and recovery times
Identify actively exploited CVEs ranked by risk
Query natural language questions about service status

Source and maintenance

Community listingRegistry 1.3.0

mcp-registry: io.github.marcioyoshida/outage-me@1.3.0 Project website

Protocol and capabilities

Server: tarantula-outage-me 1.3.0
MCP protocol negotiated in check: 2025-06-18
Tools: 8 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: 1 advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  }
}

Server-provided instructions

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

Live outage, reliability and exploited-vulnerability intelligence, from official provider status pages and CISA/FIRST/NVD. The fact tools are deterministic; `answer` is a model call that can be wrong and needs sign-in or an API key. Signed-in clients (https://outage.me/mcp/pro) also get provider_history, backbone_watch, vendor_scorecard and blast_radius, and Pro adds signed incident webhooks (webhook_register) instead of polling. Prefer the fact tools; always cite the `url`. How to connect: https://outage.me/connect

Tools

8 advertised

list_active_incidents — Active cloud/SaaS incidents

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

LIVE: cloud and SaaS incidents open right now (AWS, Azure, GCP, Cloudflare, GitHub, Stripe, …), quoted from each provider's own status page with a link, refreshed several times a day. Use for 'is X down', 'why is X failing', or anything after your training cutoff. Filter by provider, region or component instead of reading the whole list; an untracked provider says so rather than returning an empty all-clear. Deterministic: no model in the loop. Prefer it over `answer`.

list_active_incidents input schema

{
  "type": "object",
  "properties": {
    "region": {
      "type": "string",
      "description": "Optional. Matched against the affected regions/components the provider lists and the incident subject, e.g. 'us-east-1'."
    },
    "provider": {
      "type": "string",
      "description": "Optional. Provider name or common alias, e.g. 'AWS', 'gcp', 'GitHub'. 'AWS' matches every AWS service."
    },
    "component": {
      "type": "string",
      "description": "Optional. Same matching as region, e.g. 'Actions', 'API'."
    }
  },
  "additionalProperties": false
}

list_active_incidents annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

provider_reliability — Provider reliability track record

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

LIVE: reliability index, incident count and median recovery time per cloud/SaaS provider over the current window, from their official status pages. Use for 'how reliable is X' or 'which provider is more stable'. Deterministic: no model in the loop. Prefer it over `answer`.

provider_reliability input schema

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "Optional. Filter to one provider by name."
    }
  },
  "additionalProperties": false
}

provider_reliability annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

exploited_vulnerabilities — Actively exploited CVEs, patch-first

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

LIVE: CVEs being exploited in the wild (CISA KEV), ranked patch-first by CVSS × EPSS exploitation probability × known ransomware use, with CISA due date, patch availability and the factors behind each rank. Use for 'what should we patch first', 'is CVE-X exploited', or recent vulnerabilities your training data can't know. `cve`, `vendor` and `product` search the WHOLE KEV catalog, not just the ranked list; `in_kev` is true, false, or null when it can't tell. Deterministic: no model in the loop.

exploited_vulnerabilities input schema

{
  "type": "object",
  "properties": {
    "cve": {
      "type": "string",
      "description": "Optional. One CVE ID, e.g. CVE-2024-3400: is it in CISA KEV, and its patch-first rank if ranked."
    },
    "limit": {
      "type": "integer",
      "maximum": 20,
      "minimum": 1,
      "description": "Optional. Max rows, default 10."
    },
    "vendor": {
      "type": "string",
      "description": "Optional. KEV entries whose vendor contains this, newest first, e.g. 'Microsoft', 'Ivanti'."
    },
    "product": {
      "type": "string",
      "description": "Optional. KEV entries whose product contains this, e.g. 'Exchange'."
    }
  },
  "additionalProperties": false
}

exploited_vulnerabilities annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

threat_advisories — CISA security advisories (ICS, medical, vulnerability)

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

LIVE: CISA's newest security advisories (CSAF: industrial control systems, medical devices, general vulnerabilities), each with its ID, affected vendors, CVEs, CVSS, the opening of CISA's mitigation text and the CISA link. Use for 'what did CISA advise this week' or 'any CISA advisory for <vendor>'. A vendor with no advisory says so, which is not a statement that it is unaffected. Deterministic: no model in the loop.

threat_advisories input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "Optional. Max rows, default 10."
    },
    "vendor": {
      "type": "string",
      "description": "Optional. Vendor name or part of it, e.g. 'Siemens', 'Rockwell'."
    }
  },
  "additionalProperties": false
}

threat_advisories annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

security_headlines — Security news headlines (breaches, attacks, exploits)

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

LIVE: headlines from eight security trade outlets (BleepingComputer, The Hacker News, SecurityWeek, The Record, Krebs on Security, …): headline, outlet, date and link only, never the article text. Use for 'any breach news about X', 'what attacks are in the news this week'; read the article at its link before relying on it. Deterministic: no model in the loop.

security_headlines input schema

{
  "type": "object",
  "properties": {
    "days": {
      "type": "integer",
      "maximum": 14,
      "minimum": 1,
      "description": "Optional. Look-back in days, default 7."
    },
    "query": {
      "type": "string",
      "description": "Optional. Words that must all appear in the headline, e.g. 'breach', 'ransomware hospital', 'Okta'."
    }
  },
  "additionalProperties": false
}

security_headlines annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

deploy_check — Deploy gate: is it safe to deploy to this provider now?

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

LIVE, from the 5-minute status poll: proceed true, false, or "unknown" for deploying to one provider (optionally one region), with the open incidents behind it and data_age_minutes. Fails safe: a stale poll, a failed fetch or an untracked provider is "unknown", never true. Planned maintenance alone doesn't block. Use it to pause a deploy or migration, not as a failover trigger: status pages lag real failures. Deterministic: no model in the loop.

deploy_check input schema

{
  "type": "object",
  "required": [
    "provider"
  ],
  "properties": {
    "region": {
      "type": "string",
      "description": "Optional, e.g. 'us-east-1', 'us-central1', 'westeurope'."
    },
    "provider": {
      "type": "string",
      "description": "Provider name or alias, e.g. 'AWS', 'Google Cloud', 'GitHub'."
    }
  },
  "additionalProperties": false
}

deploy_check annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

answer — Ask the outage.me analyst (sign-in or API key)

Advertised by the server during the last successful anonymous check.

Advertised read-onlyOpen-world

Ask a free-form question about the live monitor and get a cited answer. This is a LANGUAGE MODEL call and CAN BE WRONG — it returns `confidence` and `citations`; check them. Needs sign-in (connect to https://outage.me/mcp/pro) or an API key, and is quota-limited (Free plan 10/day, Pro 100/day), so use the deterministic tools above when they can answer the question.

answer input schema

{
  "type": "object",
  "required": [
    "q"
  ],
  "properties": {
    "q": {
      "type": "string",
      "description": "The question, in natural language."
    }
  },
  "additionalProperties": false
}

answer annotations

{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

report_observation — Report an API failure you observed (optional)

Advertised by the server during the last successful anonymous check.

Optional. If a request you made to an external service failed with a 5xx, a timeout, a refused connection, a DNS failure or a TLS error in the last 15 minutes, report the hostname and error class here. Only hosts listed in https://outage.me/agent/hosts.json. Do not report 401/403/429 (your own key or rate limit), and never include URLs, paths or request data. A report earns Ask quota only if it is confirmed (our own probe or other organizations agree).

report_observation input schema

{
  "type": "object",
  "required": [
    "host",
    "error_class"
  ],
  "properties": {
    "host": {
      "type": "string",
      "description": "Hostname only, e.g. api.stripe.com"
    },
    "region": {
      "type": "string",
      "description": "Optional: where you run, e.g. aws:us-east-1"
    },
    "error_class": {
      "enum": [
        "http_5xx",
        "timeout",
        "connection_refused",
        "dns_failure",
        "tls_error"
      ],
      "type": "string"
    },
    "report_token": {
      "type": "string",
      "description": "Optional: the token a status answer offered"
    }
  },
  "additionalProperties": false
}

report_observation annotations

{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

1 advertised

enable-outage-reporting — Enable outage reporting to outage.me

Advertised by the server during the last successful anonymous check.

Adds a short instruction so this agent may report API failures it observes (host + error class only) to outage.me.

No arguments advertised.

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).

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: 1164 ms
95th percentile latency: 1164 ms

Maintenance history

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

Nov 7, 2026, 10:02 AM UTC · probe · passed · 1164 ms · metadata changed · 8 tool(s), 1 prompt(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 outage-me-mcp https://outage.me/mcp

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 outage-me-mcp --url https://outage.me/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable outage-me-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "outage-me-mcp": {
      "url": "https://outage.me/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "outage-me-mcp": {
      "type": "streamableHttp",
      "url": "https://outage.me/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start outage-me-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "outage-me-mcp": {
      "type": "http",
      "url": "https://outage.me/mcp"
    }
  }
}

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 outage-me-mcp https://outage.me/mcp

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://outage.me/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "outage-me-mcp": {
      "serverUrl": "https://outage.me/mcp"
    }
  }
}

Let your agent find its tools

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

Connect Koskamo Explore workflows

See all 622

Outage.Me MCP

Endpoint and access

What its tools do

Read-only (7)

Can change data (1)

Checks and signals

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

90-day uptime

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other cloud and infrastructure servers