add_documents

THE RISK

Medium Risk

Why add_documents needs a policy

The tool creates or modifies data reversibly by adding documents to a collection. This is a Write operation rather than Read (no query), Execute (no arbitrary code execution), Destructive (data is not deleted or overwritten), or Financial (no monetary operations). Severity is medium because adding documents could pollute the search index or consume storage/quota, but effects are reversible via delete_documents.

From the tool's definition Tool description states 'Add documents to a collection' and 'Documents will be automatically embedded', indicating creation of new data entries in the vector database without deletion or irreversible modification.

Documented attack patterns abuse exactly the kind of access add_documents gives an agent:

POLICY

How to control add_documents

PolicyLayer is an MCP gateway — it sits between your AI agents and Qdrant MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_documents:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_documents": {
      "limits": [
        {
          "counter": "add_documents_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_documents stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Qdrant MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Qdrant MCP Server tools

Destructive clear_git_index Delete all indexed git history data for a repository. This is irreversible and will remove Destructive clear_index Delete all indexed data for a codebase. This is irreversible and will remove the entire co Destructive delete_collection Delete a collection and all its documents. Destructive delete_documents Delete specific documents from a collection by their IDs. Write index_new_commits Incrementally index only new commits since the last indexing. Much faster than full re-ind Write index_codebase Index a codebase for semantic code search. Automatically discovers files, chunks code inte Write index_git_history Index a repository Write reindex_changes Incrementally re-index only changed files. Detects added, modified, and deleted files sinc

All 20 Qdrant MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about add_documents

What does the add_documents tool do? +

Add documents to a collection. Documents will be automatically embedded using the configured embedding provider. It is categorised as a Write tool in the Qdrant MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_documents? +

Register the Qdrant MCP Server MCP server in PolicyLayer and add a rule for add_documents: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Qdrant MCP Server. Nothing to install.

What risk level is add_documents? +

add_documents is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_documents? +

Yes. Add a rate_limit block to the add_documents rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block add_documents completely? +

Set action: deny in the PolicyLayer policy for add_documents. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides add_documents? +

add_documents is provided by the Qdrant MCP Server MCP server (mhalder/qdrant-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Qdrant MCP Server tool call.

Start from Qdrant MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →