How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

pinecone_mcp - Skill - OpenSmartRoute

Skillv1.0.0

pinecone_mcp

Name: pinecone_mcp
Author: harrison007123

Reusable skill to connect to Pinecone via MCP to fetch, query, and upload vector data when requested by the user.

by harrison007123(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from harrison007123/WHAT-IF (.agents/skills/pinecone_mcp/SKILL.md). Install upstream with npx skills add harrison007123/WHAT-IF --skill pinecone_mcp. Copyright stays with the author.

Pinecone MCP Skill

This skill enables agents to interact with Pinecone vector databases using the Pinecone Model Context Protocol (MCP) server.

Usage Instructions

When the user requests to fetch from or upload to Pinecone, you can run the Pinecone MCP server.

Server Command: npx -y @pinecone-database/mcp

Common Operations: Once connected to the MCP server (or if you are defining an ADK Agent that uses this MCP), the typical tools exposed are:

pinecone_query: Fetch / search for similar vectors using a query.
pinecone_upsert: Upload / insert vectors into the database.
pinecone_create_index: Create a new vector index.

Environment Variables: Ensure that PINECONE_API_KEY is set in the environment or .env file before launching the server.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Installed into a catalogue, chosen by a router

Install pinecone_mcp and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

harrison007123-what-if-pinecone-mcp.ocm.jsonjson

{
  "ocm": "1",
  "id": "harrison007123-what-if-pinecone-mcp",
  "kind": "skill",
  "name": "pinecone_mcp",
  "description": "Reusable skill to connect to Pinecone via MCP to fetch, query, and upload vector data when requested by the user.",
  "publisher": "harrison007123",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "data_analysis"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Reusable skill to connect to Pinecone via MCP to fetch, query, and upload vector data when requested by the user."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/harrison007123/WHAT-IF",
      "path": ".agents/skills/pinecone_mcp/SKILL.md",
      "ref": "ebfd6a7ef1b9cada8c645658f541887eb5bb0ccf",
      "url": "https://github.com/harrison007123/WHAT-IF/blob/ebfd6a7ef1b9cada8c645658f541887eb5bb0ccf/.agents/skills/pinecone_mcp/SKILL.md",
      "key": "harrison007123/WHAT-IF/.agents/skills/pinecone_mcp/SKILL.md"
    }
  },
  "instructions": "# Pinecone MCP Skill\n\nThis skill enables agents to interact with Pinecone vector databases using the Pinecone Model Context Protocol (MCP) server.\n\n## Usage Instructions\n\nWhen the user requests to fetch from or upload to Pinecone, you can run the Pinecone MCP server.\n\n**Server Command:**\n`npx -y @pinecone-database/mcp`\n\n**Common Operations:**\nOnce connected to the MCP server (or if you are defining an ADK Agent that uses this MCP), the typical tools exposed are:\n- `pinecone_query`: Fetch / search for similar vectors using a query.\n- `pinecone_upsert`: Upload / insert vectors into the database.",
  "cost": {
    "context_tokens": 195
  }
}

Fetch it by URL: GET /api/v1/registry/harrison007123-what-if-pinecone-mcp/manifest?version=1.0.0

About

Pinecone MCP Skill

Usage Instructions

Use it

Install pinecone_mcp and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews