Pinecone for AI agents

Pinecone is a managed vector database used to store embeddings and power fast similarity search for AI applications. Developers use it to give AI features long-term memory and retrieval. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

AI and modelsOAuth 2.0MCP + RESTpinecone.io
AUDIT LOG · PINECONEPOLICY: acme-support
09:41:07 · claude · u_8f2read
pinecone.list_files
List Files✓ allowed · 212ms
09:41:08 · claude · u_8f2read
pinecone.get_model
Get Model Information✓ allowed · 164ms
09:41:09 · claude · u_8f2write
pinecone.create_index
Create Index✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
pinecone.delete_file
Delete File✕ blocked · policy: deny
EVERY PINECONE CALL, ON THE RECORD
01 · USE CASES

What agents do in Pinecone.

01

Query an index for similar vectors

Fetch the nearest matches to a query embedding from a namespace for a retrieval task.

02

Check index stats read-only

Look up an index's vector count and stats before deciding whether to expand capacity.

03

Delete vectors with approval

Remove a batch of vectors from a namespace only after confirming they are no longer needed.

02 · ACTIONS

48 Pinecone actions, graded by risk.

Every Pinecone action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

24

Look things up. Allowed by default.

  • pinecone.get_model
    Get Model Information
  • pinecone.list_files
    List Files
  • pinecone.list_models
    List Available Models
  • pinecone.list_indexes
    List Indexes
  • pinecone.list_vectors
    List Vectors
  • pinecone.get_assistant
    Get Assistant Status
  • pinecone.query_vectors
    Query Vectors
  • pinecone.list_assistants
    List Assistants
  • pinecone.list_collections
    List Collections
  • pinecone.list_bulk_imports
    List Bulk Imports
  • pinecone.list_restore_jobs
    List Restore Jobs
  • pinecone.list_index_backups
    List Index Backups
  • pinecone.list_project_backups
    List Project Backups
  • pinecone.search_records_namespace
    Search Records in Namespace
  • pinecone.list_namespaces_operation
    List Namespaces
  • pinecone.describe_file
    Describe File
+ 8 MORE

write

17

Create and change things. Allow, or ask the user first.

  • pinecone.create_index
    Create Index
  • pinecone.create_backup
    Create Backup
  • pinecone.update_vector
    Update Vector
  • pinecone.create_assistant
    Create Assistant
  • pinecone.create_namespace
    Create Namespace
  • pinecone.update_assistant
    Update Assistant
  • pinecone.create_index_for_model
    Create Index with Embedding Model
  • pinecone.create_index_from_backup
    Create Index from Backup
  • pinecone.embed
    Generate Embeddings
  • pinecone.rerank
    Rerank Documents
  • pinecone.upload_file
    Upload File to Assistant
  • pinecone.chat_assistant
    Chat with Assistant
  • pinecone.upsert_vectors
    Upsert Vectors
  • pinecone.configure_index
    Configure Index
  • pinecone.start_bulk_import
    Start Bulk Import
  • pinecone.upsert_records_namespace
    Upsert Records to Namespace
+ 1 MORE

destructive

7

Delete, cancel or archive. Ask first, or deny outright.

  • pinecone.delete_file
    Delete File
  • pinecone.delete_index
    Delete Index
  • pinecone.delete_backup
    Delete Backup
  • pinecone.delete_vectors
    Delete Vectors
  • pinecone.delete_assistant
    Delete Assistant
  • pinecone.delete_namespace
    Delete Namespace
  • pinecone.cancel_bulk_import
    Cancel Bulk Import
03 · HOW IT WORKS

Pinecone in three steps.

  1. 01Your users connect PineconeThey sign in to Pinecone on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, writes like “create Index” can wait for the user, and “delete File” can be denied outright.
  3. 03Any agent can actYour agent calls Pinecone through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('pinecone', {
  read: 'allow',
  write: 'ask',        // create_index
  destructive: 'deny',  // delete_file
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Pinecone connects.

Users sign in to Pinecone on Arc0 Connect and approve the scopes you request. Build with Arc0’s Pinecone OAuth app, or bring your own so the Pinecone consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

The same Pinecone connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key · OAuth 2.0
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Pinecone from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Pinecone and Arc0, answered.

Q01

Can I use Pinecone with Claude, ChatGPT or Cursor?

Yes. Connect Pinecone to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Pinecone actions you allow.

Q02

How do users connect Pinecone?

Users sign in to Pinecone on Arc0 Connect and approve the scopes you request. Build with Arc0’s Pinecone OAuth app, or bring your own so the Pinecone consent screen names you. Tokens refresh automatically, and you can export them whenever you want.

Q03

Which Pinecone actions can my agent take?

48 in total: 24 read, 17 write and 7 destructive, such as “create Index”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Pinecone?

Yes. Actions like “delete File” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Pinecone too?

Yes. The same Pinecone connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Pinecone into your agent.

Your users connect Pinecone once, under your brand. Your agent gets 48 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan