list_projects

THE RISK

Low Risk

Why list_projects needs a policy

This tool retrieves and displays information about projects and their conversation history metadata. It performs no modifications, deletions, or external operations—only reads and returns project information. The blast radius of misuse is minimal; an agent listing projects poses no risk to data integrity, financial systems, or system execution. This is a standard Read category operation.

From the tool's definition Tool name 'list_projects' and description 'List all projects that have Claude Code conversation history, with session counts and activity dates' indicate a retrieval operation that queries metadata about existing projects without modifying, deleting, or…

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

POLICY

How to control list_projects

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

policy.json

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

list_projects 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 ClaudeHistoryMCP — 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 ClaudeHistoryMCP tools

Write cloud_sync_push Push local knowledge entries and session summaries to the cloud server. Only pushes entrie Read cloud_sync_pull Pull knowledge entries and session summaries from the cloud server. Merges with local data Read cloud_sync_status Check cloud sync configuration and connection status. Shows whether sync is configured, la Read find_patterns Discover recurring patterns in conversation history: common topics, frequent workflows, re Read find_solutions Search past conversations for solutions to errors or problems. Prioritizes results contain Read get_project_context Get comprehensive context for a project: recent sessions, key topics, common tools, and pa Read get_session_summary Get a structured summary of a conversation session. Provide either a session ID or project Read search_history Search past Claude Code conversations. Supports filter syntax: project:name, before:date,

All 9 ClaudeHistoryMCP 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 list_projects

What does the list_projects tool do? +

List all projects that have Claude Code conversation history, with session counts and activity dates. It is categorised as a Read tool in the ClaudeHistoryMCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_projects? +

Register the ClaudeHistory MCP server in PolicyLayer and add a rule for list_projects: 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 ClaudeHistoryMCP. Nothing to install.

What risk level is list_projects? +

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

Can I rate-limit list_projects? +

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

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

list_projects is provided by the ClaudeHistory MCP server (jhammant/claudehistorymcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ClaudeHistoryMCP tool call.

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

CHECK YOUR STACK →