// SCAN REPORT

Arca MCP

10 tools. 6 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

6 can modify or destroy data

4 read-only

10 tools total

Community server · catalogue entry verified 03/07/2026

How to control Arca MCP ↓

TOOL MAP

What Arca MCP exposes to your agents

Read (4) Write / Execute (4) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Arca MCP tools

Destructive · High clear This tool permanently removes data from the vector memory storage without explicit per-item confirmation. Destructive · High delete The tool performs an irreversible deletion operation on a memory item identified by UUID. Write · Medium add The tool creates or modifies data (vector embeddings/memories) within the semantic storage system. Write · Medium connect This tool creates a new relationship (edge) between existing memory nodes in the graph structure.

6 of Arca MCP's 10 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Arca MCP

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

Deny destructive operations

{
  "clear": {
    "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

{
  "add": {
    "limits": [
      {
        "counter": "add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get": {
    "limits": [
      {
        "counter": "get_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 Arca MCP — 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 ARCA →

Instant setup, no code required.

FULL CATALOGUE

All 10 Arca MCP tools

DESTRUCTIVE 2 tools

Destructive clear Clear all memory items, optionally within a specific bucket. Destructive delete Delete a memory item by its UUID.

WRITE 4 tools

Write add add Write connect Create a directed edge between two memory nodes. Write disconnect Remove one or all directed edges between two memory nodes. Write ingest ingest

READ 4 tools

Read get Retrieve content from memory storage based on a query. Read get_last Retrieve the last N memories ordered by creation time (most recent first). Read list_buckets List all memory buckets. Read traverse traverse

EXPLORE

Related servers

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

FAQ

Questions about Arca MCP

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

Yes. The Arca MCP server exposes 2 destructive tools including clear, delete. 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 Arca MCP? +

The Arca MCP server has 4 write tools including add, connect, disconnect. 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 Arca MCP.

How many tools does the Arca MCP server expose? +

10 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Arca MCP? +

Register the Arca 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 Arca MCP tool call.

Deterministic rules across all 10 Arca MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ARCA →

Instant setup, no code required.

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