Koskamo

Pingoru MCP

An official MCP server provided by Pingoru that allows AI agents to query live status, incidents, and maintenance windows for over 8,000 cloud and SaaS providers. It supports tools for checking provider status, components, incidents, and searching providers without requiring authentication for public data.

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.

Pingoru MCP logo, by PingoruVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Pingoru
MCP endpoint (Streamable HTTP)
https://pingoru.io/api/mcp-public/
Vendor documentation

What you can do with it

  • Check if a specific cloud provider is down right now
  • Retrieve recent incidents for a SaaS vendor
  • Search for monitored providers by name
  • Get component-level status for a service

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
pingoru-public 1.27.0
MCP protocol
2025-06-18
Tools
6 advertised
Resources
0 advertised
Resource templates
0 advertised
Prompts
0 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "prompts": {
    "listChanged": false
  },
  "resources": {
    "subscribe": false,
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

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

Live status of 8,000+ cloud and SaaS status pages tracked by Pingoru. Ask whether a vendor is down, which components are affected, and its recent incidents. Read-only; no account needed.

Tools

6 advertised

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

Get the current status and any active incidents for a status-page vendor. Use when the user asks 'is X down?' or 'is X having problems?'. slug: Provider slug or human name. Exact slug ('github', 'amazon-web-services', 'google-cloud') is matched first; on miss we fall back to a search lookup so common shorthands ('aws', 'gcp', 'github actions') and minor typos still resolve. The response includes `matched_via: 'fuzzy'` and the original query when fuzzy fallback was used so the agent can confirm with the user.

provider_status input schema
{
  "type": "object",
  "title": "provider_statusArguments",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "title": "Slug"
    }
  }
}
provider_components
Advertised by the server during the last successful anonymous check.

List a provider's components with current status. Use to drill into 'which AWS components are broken right now?' style questions. Set only_problematic=true to filter out the operational ones. Slug accepts shorthand / typos via fuzzy fallback (see provider_status docstring).

provider_components input schema
{
  "type": "object",
  "title": "provider_componentsArguments",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "title": "Slug"
    },
    "only_problematic": {
      "type": "boolean",
      "title": "Only Problematic",
      "default": false
    }
  }
}
component_status
Advertised by the server during the last successful anonymous check.

Pinpoint the status of one component by name (case-insensitive substring match). Returns an error when the name matches multiple components — the agent should ask the user to disambiguate. Slug accepts shorthand / typos via fuzzy fallback.

component_status input schema
{
  "type": "object",
  "title": "component_statusArguments",
  "required": [
    "slug",
    "component"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "title": "Slug"
    },
    "component": {
      "type": "string",
      "title": "Component"
    }
  }
}
provider_incidents
Advertised by the server during the last successful anonymous check.

Recent incident history for a provider (days clamped to 1-30), plus a separate `maintenance` list: maintenance scheduled or held in the window, including upcoming windows. Each item has its current status (investigating / identified / monitoring / resolved, scheduled / in_progress / completed), start and resolve times, duration, impact, affected components, the vendor's link and the Pingoru page (pingoru_url). Pass component (substring match on component name) to scope to one component. Slug accepts shorthand / typos via fuzzy fallback.

provider_incidents input schema
{
  "type": "object",
  "title": "provider_incidentsArguments",
  "required": [
    "slug"
  ],
  "properties": {
    "days": {
      "type": "integer",
      "title": "Days",
      "default": 7
    },
    "slug": {
      "type": "string",
      "title": "Slug"
    },
    "component": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Component",
      "default": null
    }
  }
}
incident_detail
Advertised by the server during the last successful anonymous check.

Full record for one incident or maintenance: current status, impact, start / resolve times and duration, scheduled window (for maintenance), affected components, the vendor's link, the Pingoru page (pingoru_url) and every status update with its timestamp. Use to summarise 'what happened during the May 3 outage'. Covers the last 30 days plus anything still open. Slug accepts shorthand / typos via fuzzy fallback.

incident_detail input schema
{
  "type": "object",
  "title": "incident_detailArguments",
  "required": [
    "slug",
    "incident_id"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "title": "Slug"
    },
    "incident_id": {
      "type": "integer",
      "title": "Incident Id"
    }
  }
}
search_providers
Advertised by the server during the last successful anonymous check.

Find providers by name or slug. Use when the agent does not know the exact slug ('look up that DBaaS… planetscale?'). Uses Meilisearch under the hood so typos and shorthand still match — 'aws', 'gcp', 'githb', 'k8s' all resolve to the right vendor.

search_providers input schema
{
  "type": "object",
  "title": "search_providersArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    },
    "query": {
      "type": "string",
      "title": "Query"
    }
  }
}

Prompts

0 advertised

No prompt definitions available.

Resources

0 advertised

No resource definitions available.

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
699 ms
95th percentile latency
699 ms

Maintenance history

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

  • · probe · passed · 699 ms · metadata changed · 6 tool(s), 0 resource(s), 0 resource template(s), 0 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 pingoru-mcp https://pingoru.io/api/mcp-public/

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 pingoru-mcp --url https://pingoru.io/api/mcp-public/

Cursor

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

Cline

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

VS Code

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

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 pingoru-mcp https://pingoru.io/api/mcp-public/

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "pingoru-mcp": {
      "url": "https://pingoru.io/api/mcp-public/"
    }
  }
}

Windsurf

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

Let your agent find its tools

Find servers like Pingoru 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 Pingoru 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