Peec AI for AI agents

Peec AI analyzes a brand's visibility in AI search results, tracking competitors, citations, and sentiment across topics. Marketing teams use it to understand how AI answers describe their brand. 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.

MarketingOAuth 2.0 (MCP)MCP + RESTpeec.ai
AUDIT LOG · PEEC AIPOLICY: acme-support
09:41:07 · claude · u_8f2read
peec_ai.get_actions
Get actions✓ allowed · 212ms
09:41:09 · claude · u_8f2write
peec_ai.create_tags
Create tags✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
peec_ai.delete_tags
Delete tags✕ blocked · policy: deny
EVERY PEEC AI CALL, ON THE RECORD
01 · USE CASES

What agents do in Peec AI.

01

Check brand sentiment in AI search

Look up how a brand is described in AI search answers across tracked prompts.

02

Create a new tracked prompt

Add a prompt to monitor how AI search engines answer questions about a topic.

03

Delete a topic with approval

Remove a tracked topic only after a marketing lead confirms it is no longer relevant.

02 · ACTIONS

26 Peec AI actions, graded by risk.

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

read

1

Look things up. Allowed by default.

  • peec_ai.get_actions
    Get actions

write

15

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

  • peec_ai.create_tags
    Create tags
  • peec_ai.create_brands
    Create brands
  • peec_ai.create_topics
    Create topics
  • peec_ai.create_prompts
    Create prompts
  • peec_ai.create_products
    Create products
  • peec_ai.create_categories
    Create categories
  • peec_ai.create_global_brand
    Create global brand
  • peec_ai.create_url_classification
    Create url classification
  • peec_ai.create_domain_classification
    Create domain classification
  • peec_ai.generate_topics
    Generate topics
  • peec_ai.assign_url_classification
    Assign url classification
  • peec_ai.finalize_prompt_suggestions
    Finalize prompt suggestions
  • peec_ai.generate_prompt_suggestions
    Generate prompt suggestions
  • peec_ai.assign_domain_classification
    Assign domain classification
  • peec_ai.edit_brand_perception_attribute_clusters
    Edit brand perception attribute clusters

destructive

10

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

  • peec_ai.delete_tags
    Delete tags
  • peec_ai.delete_brands
    Delete brands
  • peec_ai.delete_topics
    Delete topics
  • peec_ai.delete_prompts
    Delete prompts
  • peec_ai.archive_prompts
    Archive prompts
  • peec_ai.delete_products
    Delete products
  • peec_ai.delete_categories
    Delete categories
  • peec_ai.delete_tag_groups
    Delete tag groups
  • peec_ai.delete_url_classification
    Delete url classification
  • peec_ai.delete_domain_classification
    Delete domain classification
03 · HOW IT WORKS

Peec AI in three steps.

  1. 01Your users connect Peec AIThey sign in to Peec AI on Arc0 Connect, under your brand, and approve the access you ask for.
  2. 02You set the rulesReads run, writes like “create tags” can wait for the user, and “delete tags” can be denied outright.
  3. 03Any agent can actYour agent calls Peec AI 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('peec_ai', {
  read: 'allow',
  write: 'ask',        // create_tags
  destructive: 'deny',  // delete_tags
})

# 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 Peec AI connects.

Peec AI runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Peec AI through the same endpoint, policies and audit log as every other app.

The same Peec AI 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
OAuth 2.0 (MCP)
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Peec AI from any agent.

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

Peec AI and Arc0, answered.

Q01

Can I use Peec AI with Claude, ChatGPT or Cursor?

Yes. Connect Peec AI 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 Peec AI actions you allow.

Q02

How do users connect Peec AI?

Peec AI runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Peec AI through the same endpoint, policies and audit log as every other app.

Q03

Which Peec AI actions can my agent take?

26 in total: 1 read, 15 write and 10 destructive, such as “create tags”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Peec AI?

Yes. Actions like “delete tags” 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 Peec AI too?

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

Get started

Plug Peec AI into your agent.

Your users connect Peec AI once, under your brand. Your agent gets 26 actions behind your policies, with every call on the record.

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