// SCAN REPORT

Pluggedin Mcp Proxy

27 tools. 14 can modify or destroy data without limits.

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

Last updated: 11 Jun 2026

14 can modify or destroy data

13 read-only

27 tools total

Community server · catalogue entry verified 11/06/2026

How to control Pluggedin Mcp Proxy ↓

TOOL MAP

Read (13) Write / Execute (11) Destructive / Financial (3)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · Medium pluggedin_clipboard_delete This tool performs irreversible deletion of data (clipboard entries). Destructive · Medium pluggedin_delete_notification The tool performs an irreversible deletion of data (a notification). Destructive · Medium pluggedin_clipboard_pop The tool removes an entry from the clipboard permanently as part of its core operation ('removes it'). Execute · Medium pluggedin_memory_session_end This tool executes a triggered action (session end and report generation) rather than simply reading or writing data.

14 of Pluggedin Mcp Proxy's 27 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL PLUGGEDIN MCP PROXY

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

Deny destructive operations

{
  "pluggedin_clipboard_delete": {
    "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

{
  "pluggedin_memory_session_start": {
    "limits": [
      {
        "counter": "pluggedin_memory_session_start_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "pluggedin_ask_knowledge_base": {
    "limits": [
      {
        "counter": "pluggedin_ask_knowledge_base_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 Pluggedin Mcp Proxy — 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 PLUGGEDIN MCP PROXY →

Free to start. No card required.

ALL 27 PLUGGEDIN MCP PROXY TOOLS

DESTRUCTIVE 3 tools

Destructive pluggedin_clipboard_delete Delete clipboard entries by name, index, or clear all entries. Destructive pluggedin_delete_notification Delete a notification from the Plugged.in system Destructive pluggedin_clipboard_pop Pop the highest-indexed entry from the clipboard (LIFO behavior). Returns the entry value and removes it.

EXECUTE 2 tools

Execute pluggedin_memory_session_end End a memory session and trigger Z-report generation (AI-compressed session summary). Execute pluggedin_discover_tools Triggers discovery of tools (and resources/templates) for configured MCP servers in the Pluggedin App.

WRITE 9 tools

Write pluggedin_memory_session_start Start a new memory session to begin capturing observations. Returns a session UUID and memory_session_id for s Write pluggedin_cbp_feedback Submit feedback on a collective pattern to improve quality. Rate patterns as helpful, inaccurate, outdated, or Write pluggedin_memory_observe Record an observation during a memory session. Observations are classified by the Analytics Agent into memory Write pluggedin_clipboard_push Push a value to the indexed clipboard with auto-incrementing index. Useful for building ordered pipelines or s Write pluggedin_clipboard_set Set a clipboard entry by name (semantic key) or index (array-like). Named entries are upserted; indexed entrie Write pluggedin_create_document Create and save AI-generated documents to the user Write pluggedin_mark_notification_done Mark a notification as done in the Plugged.in system Write pluggedin_send_notification Send custom notifications through the Plugged.in system with optional email delivery. You can provide a custom Write pluggedin_update_document Update or append to an existing AI-generated document (requires API key)

READ 13 tools

Read pluggedin_ask_knowledge_base Ask questions and get AI-generated answers from your knowledge base. Returns structured JSON with answer, docu Read pluggedin_cbp_query Query collective best practices - privacy-preserving patterns aggregated from the community. Use for proactive Read pluggedin_clipboard_get Get clipboard entries. Specify name or idx for a single entry, or omit both to list all entries with paginatio Read pluggedin_clipboard_list List all clipboard entries with metadata. Image values are truncated to first 1000 chars for preview. Read pluggedin_get_document Retrieve a specific document Read pluggedin_list_documents List documents with filtering options from the user Read pluggedin_list_notifications List notifications from the Plugged.in system with optional filters for unread only and result limit Read pluggedin_memory_details Get full details for selected memories (progressive disclosure Layer 3). Use after pluggedin_memory_search to Read pluggedin_memory_individuation Get your individuation score — a measure of memory maturity (0-100). Shows Memory Depth, Learning Velocity, Co Read pluggedin_memory_search Search memories using semantic similarity. Returns lightweight results (50-150 tokens each) for token-efficien Read pluggedin_memory_search_with_context Search memories with archetype-enhanced collective intelligence. Returns both personal memories and collective Read pluggedin_search_documents Search for specific documents in your library. Returns document metadata (ID, title, snippet). To retrieve ful Read pluggedin_setup Get started with Plugged.in MCP - shows setup instructions and API key configuration (no API key required)

RELATED SERVERS

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

FAQ

Can an AI agent delete data through the Pluggedin Mcp Proxy MCP server? +

Yes. The Pluggedin Mcp Proxy server exposes 3 destructive tools including pluggedin_clipboard_delete, pluggedin_delete_notification, pluggedin_clipboard_pop. 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 Pluggedin Mcp Proxy? +

The Pluggedin Mcp Proxy server has 9 write tools including pluggedin_memory_session_start, pluggedin_cbp_feedback, pluggedin_memory_observe. 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 Pluggedin Mcp Proxy.

How many tools does the Pluggedin Mcp Proxy MCP server expose? +

27 tools across 4 categories: Destructive, Execute, Read, Write. 13 are read-only. 14 can modify, create, or delete data.

How do I enforce a policy on Pluggedin Mcp Proxy? +

Register the Pluggedin Mcp Proxy 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 Pluggedin Mcp Proxy tool call.

Deterministic rules across all 27 Pluggedin Mcp Proxy tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PLUGGEDIN MCP PROXY →

Free to start. No card required.

27 Pluggedin Mcp Proxy tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Pluggedin Mcp Proxy

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL PLUGGEDIN MCP PROXY

// ALL 27 PLUGGEDIN MCP PROXY TOOLS

// RELATED SERVERS

// FAQ