AI agents use record_session_start to create or update resources in MCP Pytest Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Pytest Server environment.
This tool writes a new test session entry to track the start of a pytest run. It creates data (a session record) but does not delete anything, execute arbitrary code, or involve financial transactions. The blast radius of misuse is low — at worst it creates spurious session records.
From the tool's definition "Record the start of a test session" — creates/initializes a session record
Documented attack patterns abuse exactly the kind of access record_session_start gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Pytest Server, and nothing reaches the server without passing your rules. This is the rule we recommend for record_session_start:
{
"version": "1",
"default": "deny",
"tools": {
"record_session_start": {
"limits": [
{
"counter": "record_session_start_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}record_session_start 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.
Free to start. No card required.
Record the start of a test session. It is categorised as a Write tool in the MCP Pytest Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Pytest Server MCP server in PolicyLayer and add a rule for record_session_start: 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 MCP Pytest Server. Nothing to install.
record_session_start is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_session_start 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.
Set action: deny in the PolicyLayer policy for record_session_start. 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.
record_session_start is provided by the MCP Pytest Server MCP server (kieranlal/mcp_pytest_service). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Pytest Server, 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.
3 MCP Pytest Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.