holistic_search

THE RISK

Low Risk

Why holistic_search needs a policy

The tool retrieves and queries data from multiple memory layers without producing side effects or irreversible changes. It aligns with the 'Read' category definition: retrieves or queries data with no side effects (search, list, get, fetch). The severity is low because misuse would only expose existing information rather than cause system damage or data loss.

From the tool's definition Tool name 'holistic_search' and description states it performs 'search across all memory layers' with no mention of modification, deletion, execution, or financial operations. This is a retrieval/query operation.

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

POLICY

How to control holistic_search

PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Writer's Aid MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for holistic_search:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "holistic_search": {}
  }
}

holistic_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

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

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude Writer's Aid MCP tools

Write add_style_decision Record a style decision for consistency Write generate_outline Create hierarchical outline from content Write mark_mistake Record a writing mistake to avoid repeating it Write set_requirement Store a publisher or style requirement Write suggest_cross_references Suggest where to add links between sections Read analyze_link_graph Visualize connections between documents Read check_before_edit Check context before editing a file - get warnings about past mistakes, decisions, and req Read check_readability Analyze readability metrics

All 34 Claude Writer's Aid MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about holistic_search

What does the holistic_search tool do? +

Unified search across all memory layers (content, decisions, mistakes, concepts, sessions, commits). It is categorised as a Read tool in the Claude Writer's Aid MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on holistic_search? +

Register the Claude Writer's Aid MCP server in PolicyLayer and add a rule for holistic_search: 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 Claude Writer's Aid MCP. Nothing to install.

What risk level is holistic_search? +

holistic_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit holistic_search? +

Yes. Add a rate_limit block to the holistic_search 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 holistic_search completely? +

Set action: deny in the PolicyLayer policy for holistic_search. 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 holistic_search? +

holistic_search is provided by the Claude Writer's Aid MCP server (xiaolai/claude-writers-aid-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Writer's Aid MCP tool call.

Start from Claude Writer's Aid MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →