// SCAN REPORT

Peecai

38 tools. 19 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

19 can modify or destroy data

19 read-only

38 tools total

Community server · catalogue entry verified 29/06/2026

How to control Peecai ↓

TOOL MAP

What Peecai exposes to your agents

Read (19) Write / Execute (14) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Peecai tools

Destructive · High delete_brand Although described as a 'soft-delete' (typically a non-permanent database flag), the API documentation explicitly states the action is 'irreversible through the API,' meaning users cannot undo it through normal means. Destructive · High delete_prompt Although technically a 'soft-delete' (logical rather than physical deletion), the tool irreversibly removes prompts and associated chats from the user's perspective and API access. Destructive · High delete_tag This tool permanently removes a tag from the system with no API-level recovery option. Destructive · High delete_topic Despite being a 'soft-delete' (logical deletion rather than physical removal), the action is documented as irreversible through the API, meaning it cannot be undone by normal API operations.

19 of Peecai's 38 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Peecai

PolicyLayer is an MCP gateway — it sits between your AI agents and Peecai, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_brand": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "accept_brand_suggestion": {
    "limits": [
      {
        "counter": "accept_brand_suggestion_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_brands_report": {
    "limits": [
      {
        "counter": "get_brands_report_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Peecai — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON PEECAI →

Instant setup, no code required.

FULL CATALOGUE

All 38 Peecai tools

DESTRUCTIVE 5 tools

Destructive delete_brand Soft-delete a brand. This action is irreversible through the API. Destructive delete_prompt Soft-delete a prompt and its associated chats. This action is irreversible through the API. Destructive delete_tag Soft-delete a tag. This action is irreversible through the API. Destructive delete_topic Soft-delete a topic. This action is irreversible through the API. Destructive reject_brand_suggestion Reject a brand suggestion, removing it from the project and preventing it from being re-suggested.

WRITE 14 tools

Write accept_brand_suggestion Accept a brand suggestion, converting it into a brand within the project. Write accept_prompt_suggestion Accept a prompt suggestion, creating a new prompt from it. Write accept_topic_suggestion Accept a topic suggestion, creating a new topic from it. Write create_brand Create a new brand within a Peec AI project. Requires a brand name; optionally provide aliases, domains, regex Write create_prompt Create a new search prompt to monitor across AI models. Requires prompt text and country code. Write create_tag Create a new tag within a Peec AI project. Write create_topic Create a new topic within a Peec AI project. Write reject_prompt_suggestion Reject a prompt suggestion. Write reject_topic_suggestion Reject a topic suggestion. Write set_project_profile Replace the project Write update_brand Update an existing brand. Changing name, aliases, or regex triggers metric recalculation. Write update_prompt Update prompt topic or tag assignments. Write update_tag Update an existing tag Write update_topic Update an existing topic

READ 19 tools

Read get_brands_report Get brand analytics report per brand. Metrics: visibility (visibility_count/visibility_total), share_of_voice Read get_chat_content Get full content of a specific AI chat. Returns sources, brands mentioned, messages, queries, and products. Read get_domains_report Get domain analytics report: retrieval_rate, citation_rate, and retrieved_percentage. Classification values: O Read get_project_profile Read the project Read get_url_content Get the scraped markdown content of a source URL. Use the URLs report (get_urls_report) to discover URLs. Retu Read get_urls_report Get URL analytics report: citation_count (total citations), retrievals (retrieval count), citation_rate. Class Read list_brand_suggestions List open brand suggestions for a Peec AI project. Suggestions can be accepted to convert into a brand or reje Read list_brands List tracked brands for a Peec AI project. Returns brand IDs, names, and associated domains. Read list_chats List AI chat interactions tracked by Peec AI. Returns up to limit results (default: 100). Recommended: use dat Read list_model_channels List model channels tracked by Peec AI. A model channel (e.g. openai-0, perplexity-0) is a stable identifier t Read list_models Deprecated: use list_model_channels instead. Model channels are stable identifiers (e.g. openai-0, perplexity- Read list_projects List all Peec AI projects for the company. Returns project IDs, names, and statuses. Status values: CUSTOMER ( Read list_prompt_suggestions List suggested prompts for a Peec AI project. Suggestions can be accepted to create prompts or rejected to dis Read list_prompts List search prompts for a Peec AI project. Returns prompt IDs, messages, tags, topics, locations, and search v Read list_topic_suggestions List suggested topics for a Peec AI project. Suggestions can be accepted to create topics or rejected to dismi Read list_topics List topic groupings for a Peec AI project. Returns topic IDs and names. Read search_queries Get search queries that AI models generated when answering prompts. Returns the actual search queries models u Read shopping_queries Get shopping/product queries that AI models generated when answering prompts. Returns product-related queries

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Peecai

Can an AI agent delete data through the Peecai MCP server? +

Yes. The Peecai server exposes 5 destructive tools including delete_brand, delete_prompt, delete_tag. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Peecai? +

The Peecai server has 14 write tools including accept_brand_suggestion, accept_prompt_suggestion, accept_topic_suggestion. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Peecai.

How many tools does the Peecai MCP server expose? +

38 tools across 3 categories: Destructive, Read, Write. 19 are read-only. 19 can modify, create, or delete data.

How do I enforce a policy on Peecai? +

Register the Peecai MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Peecai tool call.

Deterministic rules across all 38 Peecai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PEECAI →

Instant setup, no code required.

38 Peecai tools catalogued and risk-classified — across an index of 43,000+ MCP servers.