// SCAN REPORT

Vectorise

8 tools. 2 can modify or destroy data without limits.

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

Last updated: 2 Jul 2026

2 can modify or destroy data

6 read-only

8 tools total

Community server · catalogue entry verified 02/07/2026

How to control Vectorise ↓

TOOL MAP

What Vectorise exposes to your agents

Read (6) Write / Execute (1) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Vectorise tools

Destructive · High vectorise_delete_project This tool permanently deletes indexed project data (chunks, embeddings, metadata) with no undo capability. Write · Medium vectorise_index_project The tool name strongly implies it creates a new index (project) by ingesting documents into the vector+keyword search store.

2 of Vectorise'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 Vectorise

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

Deny destructive operations

{
  "vectorise_delete_project": {
    "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

{
  "vectorise_index_project": {
    "limits": [
      {
        "counter": "vectorise_index_project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "vectorise_await_index": {
    "limits": [
      {
        "counter": "vectorise_await_index_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 Vectorise — 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 VECTORISE →

Instant setup, no code required.

FULL CATALOGUE

All 8 Vectorise tools

DESTRUCTIVE 1 tools

Destructive vectorise_delete_project Delete a project permanently. Removes all chunks, embeddings, and metadata.

WRITE 1 tools

Write vectorise_index_project vectorise_index_project

READ 6 tools

Read vectorise_await_index vectorise_await_index Read vectorise_index_status vectorise_index_status Read vectorise_list_jobs List indexing jobs from this server session (resets on restart). Read vectorise_list_projects vectorise_list_projects Read vectorise_reindex_project vectorise_reindex_project Read vectorise_search vectorise_search

EXPLORE

Related servers

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

FAQ

Questions about Vectorise

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

Yes. The Vectorise server exposes 1 destructive tools including vectorise_delete_project. 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 Vectorise? +

The Vectorise server has 1 write tools including vectorise_index_project. 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 Vectorise.

How many tools does the Vectorise MCP server expose? +

8 tools across 2 categories: Destructive, Read. 6 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Vectorise? +

Register the Vectorise 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 Vectorise tool call.

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

ENFORCE POLICY ON VECTORISE →

Instant setup, no code required.

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