Low Risk

get_session_events

Return the raw events for a given session ID. JSONL for file-based agents (Claude/Codex/Gemini/OpenClaw); Hermes messages are serialized as one JSON object per line. Use after list_recent_sessions to drill into a session.

How to control get_session_events ↓

What get_session_events does on AgentWatch

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

Low Risk

Why get_session_events needs a policy

This is a Read operation—it retrieves session event data without side effects. Severity is medium rather than low because session events may contain sensitive information (tokens, queries, user actions, costs), so misuse could expose confidential data; however, it is not destructive, financial, or executable code.

From the tool's definition Tool performs data retrieval: 'Return the raw events for a given session ID' with queries returning JSONL/JSON objects. No modification, deletion, or execution occurs.

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

How to control get_session_events

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_session_events": {}
  }
}

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

  1. Create a free account and register AgentWatch — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about get_session_events

What does the get_session_events tool do? +

Return the raw events for a given session ID. JSONL for file-based agents (Claude/Codex/Gemini/OpenClaw); Hermes messages are serialized as one JSON object per line. Use after list_recent_sessions to drill into a session. It is categorised as a Read tool in the AgentWatch MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_session_events? +

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

What risk level is get_session_events? +

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

Can I rate-limit get_session_events? +

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

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

get_session_events is provided by the AgentWatch MCP server (mishanefedov/agentwatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AgentWatch tool call.

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

Free to start. No card required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.