ingest_claude_code_sessions

SERVERNodebench SOURCEnodebench-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/ingest-claude-code-sessions.md

WHAT IT DOES

What ingest_claude_code_sessions does on Nodebench

AI agents call ingest_claude_code_sessions to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why ingest_claude_code_sessions is rated Low

The tool scans existing transcript files and aggregates metadata (turn counts, token usage, timestamps, working directories) for analysis. This is a retrieval operation with no side effects on the scanned data or system state. While the data read may be sensitive (founder activity history), the risk category is determined by the action performed (read), not the sensitivity of the data.

From the tool's definition Tool 'ingest_claude_code_sessions' performs read-only operations: 'Scan Claude Code JSONL transcripts', 'Returns session summaries' — it retrieves and queries data without modification, deletion, or execution of commands.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ingest_claude_code_sessions safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ingest_claude_code_sessions, this is the rule to start with:

ingest_claude_code_sessions Allowed

ingest_claude_code_sessions is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every ingest_claude_code_sessions call is checked against it from then on.

FAQ

Questions about ingest_claude_code_sessions

What does the ingest_claude_code_sessions tool do? +

Scan Claude Code JSONL transcripts from ~/.claude/projects/. Returns session summaries with turn counts, token usage, timestamps, and working directories. Use to understand what the founder has been working on across Claude Code sessions. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ingest_claude_code_sessions? +

Register the Nodebench MCP server in PolicyLayer and add a rule for ingest_claude_code_sessions: 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 Nodebench. Nothing to install.

What risk level is ingest_claude_code_sessions? +

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

Can I rate-limit ingest_claude_code_sessions? +

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

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

ingest_claude_code_sessions is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Nodebench, and thousands of servers like it.

This server

All 824 Nodebench tools →

Across the catalogue

claude_git_status on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →