Get started

BrainGraph for AI agents

BrainGraph builds a searchable knowledge graph from documents, recordings, and web pages that teams use to ground AI answers in their own source material. 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.

Connect BrainGraphSee the 10 actions ↓
AI and modelsAPI keyMCP + RESTbraingraph.ai
AUDIT LOG · BRAINGRAPHPOLICY: acme-support
09:41:07 · claude · u_8f2read
braingraph.list_brains
List Brains✓ allowed · 212ms
09:41:08 · claude · u_8f2read
braingraph.search_brain
Search Brain✓ allowed · 164ms
09:41:09 · claude · u_8f2write
braingraph.ingest_web_page
Ingest Web Page✓ approved · approved by user
EVERY BRAINGRAPH CALL, ON THE RECORD
01 · USE CASES

What agents do in BrainGraph.

01

Search the knowledge graph

Run a read-only search across a brain's ingested documents and graph patterns to answer a question.

02

Ingest a new source document

Upload a document or ingest a web page or video into a brain after the user approves the source.

03

Check ingestion progress

Look up a document's ingestion progress before relying on it as the basis for a search.

02 · ACTIONS

10 BrainGraph actions, graded by risk.

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

read

6

Look things up. Allowed by default.

  • braingraph.list_brains
    List Brains
  • braingraph.search_brain
    Search Brain
  • braingraph.list_patterns
    List Graph Patterns
  • braingraph.list_documents
    List Documents
  • braingraph.get_document_progress
    Get Document Progress
  • braingraph.resolve_entity
    Resolve Entity

write

4

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

  • braingraph.ingest_web_page
    Ingest Web Page
  • braingraph.upload_document
    Upload Document
  • braingraph.transcribe_audio
    Transcribe Audio
  • braingraph.ingest_youtube_video
    Ingest YouTube Video

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

BrainGraph in three steps.

  1. 01Your users connect BrainGraphThey add their BrainGraph api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “ingest Web Page” can wait for the user to approve.
  3. 03Any agent can actYour agent calls BrainGraph 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('braingraph', {
  read: 'allow',
  write: 'ask',        // ingest_web_page
  destructive: 'deny',  
})

# 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 BrainGraph connects.

Users add their BrainGraph api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same BrainGraph 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
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use BrainGraph from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

BrainGraph and Arc0, answered.

Q01

Can I use BrainGraph with Claude, ChatGPT or Cursor?

Yes. Connect BrainGraph 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 BrainGraph actions you allow.

Q02

How do users connect BrainGraph?

Users add their BrainGraph api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which BrainGraph actions can my agent take?

10 in total: 6 read, 4 write and 0 destructive, such as “ingest Web Page”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in BrainGraph?

Yes. Allow read actions and deny writes in the BrainGraph policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call BrainGraph too?

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

Get started

Plug BrainGraph into your agent.

Your users connect BrainGraph once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect BrainGraphBrowse all apps →

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