// SCAN REPORT

Nesift

8 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 2 Jul 2026

3 can modify or destroy data

5 read-only

8 tools total

Community server · catalogue entry verified 02/07/2026

How to control Nesift ↓

TOOL MAP

What Nesift exposes to your agents

Read (5) Write / Execute (2) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Nesift tools

Destructive · High clear This tool permanently removes all indexed pages without opportunity for recovery within the session context. Write · Medium add_batch This tool adds new data (web pages) to the system's index. Write · Medium add_page The tool fetches and processes external content, then stores it in the semantic search index.

3 of Nesift's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Nesift

PolicyLayer is an MCP gateway — it sits between your AI agents and Nesift, 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_batch": {
    "limits": [
      {
        "counter": "add_batch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "answer": {
    "limits": [
      {
        "counter": "answer_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 Nesift — 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 NESIFT →

Instant setup, no code required.

FULL CATALOGUE

All 8 Nesift tools

DESTRUCTIVE 1 tools

Destructive clear Drop all indexed pages from the active session.

WRITE 2 tools

Write add_batch Ingest multiple URLs in parallel. Write add_page Fetch a URL, extract clean text, chunk by heading, and index it into

READ 5 tools

Read answer Synthesize an extractive answer with [N] citations. Read list_pages Show indexed URLs with title, chunk count, and triage summary. Read query Hybrid BM25 + embedding semantic search over indexed pages. Read score_snippets Rank text snippets by semantic relevance to a query, without fetching Read search One-shot SearXNG bridge: search → score → fetch top results → ingest → answer.

EXPLORE

Related servers

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

FAQ

Questions about Nesift

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

Yes. The Nesift server exposes 1 destructive tools including clear. 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 Nesift? +

The Nesift server has 2 write tools including add_batch, add_page. 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 Nesift.

How many tools does the Nesift MCP server expose? +

8 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Nesift? +

Register the Nesift 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 Nesift tool call.

Deterministic rules across all 8 Nesift tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON NESIFT →

Instant setup, no code required.

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