mcp-registry/com.ppn-hub/ppn-hub · v1.2.0
As of 2026-10-18 08:40 UTC, the Ppn Hub MCP server is up with a Glimind reliability score of 96/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
One MCP endpoint over 69 public PPN APIs: search_apis to discover, execute_api to call. Free tier.
Claude Code
claude mcp add --transport http ppn-hub-mcp-server https://mcp.ppn-hub.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"ppn-hub-mcp-server": {
"type": "http",
"url": "https://mcp.ppn-hub.com/mcp"
}
}
}
Third-party server, listed as discovered. Review its source before installing.
3 of 3 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
1 tool(s) have parameters with no type (no type/enum/anyOf/$ref).
Give every parameter a "type" (or "enum"/"anyOf"). Untyped parameters make models guess — strings for numbers, objects for arrays. How to fix →
1 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
Handshake + tools/list takes ~1,927 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fcom.ppn-hub%2Fppn-hub/fixes
{
"name": "execute_api",
"description": "Execute a request against any of the 59 registered APIs. Use search_apis first to find the correct api name and operationId. Requires 'Authorization: Bearer ppn_live_*'.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"api",
"operationId"
],
"properties": {
"api": {
"type": "string",
"description": "API name: marketo, atmos, chronomap, hydros, lithos, terra, carbon-credit, cost-compare, demand-forecast, grid-connect, site-matching, storage-optimize, tariff-optimize, transmission-loss, carbonias, planetary, green-path-api, biomassia, gasturbia, geothermia, hydria, reactoria, renewio, solaria, windaria-api, hydrogen, sla-viewer-production, nanobase-api, nanosnap-console, nanosnap-gacha-production, nanosnap-inventory-production, nanosnap-leaderboard-production, nanosnap-mailbox-production, nanosnap-persona-gateway-production, nanosnap-presence-production, nanosnap-replay-production, nanosnap-room-production, nanosnap-save-data-production, nanosnap-spatial-message-production, nanosnap-world-counter-production, nanosnap-world-objects-production, biositia, cryonia, faunaunify, literatia, plantunify, ppn-hub-workers, foodsense, onokoro, sakurahub-address, sakurahub-gateway, sakurahub-web, weathio, biolexia-production, biocolo, nishinoshima-gateway-production, celestora, orbitalio, perks"
},
"body": {
"description": "Request body for POST/PUT/PATCH",
"type": "string"
},
"params": {
"type": "object",
"description": "Query and path parameters as key-value pairs",
"additionalProperties": {}
},
"operationId": {
"type": "string",
"description": "operationId from search_apis results"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "search_apis",
"description": "Search across 484 endpoints in 59 APIs (cultural, earth, energy-calc, green-path, harmonias, hydrogen, internal, nanobase, nanosnap, natura, platform, sakurahub, science, sim, space, stocks). Returns matching endpoints with method, path, summary, parameters, and a ready-to-run example. Use this to discover available API endpoints before calling execute_api. Results carry a \"coverage\" field (e.g. [\"JP\"]) for region-limited APIs; use the \"region\" filter to narrow.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"tag": {
"type": "string",
"description": "Filter by OpenAPI tag"
},
"limit": {
"type": "number",
"maximum": 50,
"minimum": 1,
"description": "Max results (default: 20)"
},
"query": {
"type": "string",
"description": "Search term (matches operationId, summary, description, path, API name, tags; synonyms expanded)"
},
"domain": {
"type": "string",
"description": "Filter by domain: cultural, earth, energy-calc, green-path, harmonias, hydrogen, internal, nanobase, nanosnap, natura, platform, sakurahub, science, sim, space, stocks"
},
"method": {
"enum": [
"GET",
"POST",
"PUT",
"DELETE",
"PATCH"
],
"type": "string",
"description": "Filter by HTTP method"
},
"region": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "Filter by ISO 3166-1 alpha-2 region the API serves data for (e.g. \"JP\"). Returns region-specific + global APIs; excludes APIs limited to other regions."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/com.ppn-hub/ppn-hub"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/com.ppn-hub/ppn-hub"}) over MCP.
execute_api ~463 tokenssearch_apis ~417 tokensenvironment_brief ~189 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fcom.ppn-hub%2Fppn-hub?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fcom.ppn-hub%2Fppn-hub?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.ppn-hub%2Fppn-hub.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.ppn-hub%2Fppn-hub.svg :target: https://glimind.com/server/mcp-registry%2Fcom.ppn-hub%2Fppn-hub?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:ca5b0169524721b2…, first seen 2026-10-17, included at leaf 4794 of 21,098. Version history · verify what your client received.
Compare: most reliable data servers · most reliable code servers · most reliable search servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-18 08:40 UTC, the Ppn Hub MCP server is up with a Glimind reliability score of 96/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Ppn Hub MCP server advertises 3 tools, including environment_brief, execute_api, search_apis.
Point your MCP client at this streamable-http endpoint: https://mcp.ppn-hub.com/mcp
Glimind scanned all 3 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.