High Risk →

aidex_session

Start or check an AiDex session. Call this at the beginning of a new chat session to: (1) detect files changed externally since last session, (2) auto-reindex modified files, (3) get session note and last session times. Returns info for "What did we do last session?" queries.

Risk signalsAccepts file system path (path)

Part of the Aidex server.

aidex_session can trigger actions in Aidex, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE AIDEX →

Free to start. No card required.

AI agents invoke aidex_session to trigger processes or run actions in Aidex. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.

aidex_session can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "aidex_session": {
      "limits": [
        {
          "counter": "aidex_session_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Aidex policy for all 29 tools.

Get this rule live on your own Aidex server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY AIDEX →

View all 29 tools →

These attack patterns abuse exactly the kind of access aidex_session gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so aidex_session only ever does what you allow.

SECURE AIDEX →

Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the aidex_session tool do? +

Start or check an AiDex session. Call this at the beginning of a new chat session to: (1) detect files changed externally since last session, (2) auto-reindex modified files, (3) get session note and last session times. Returns info for "What did we do last session?" queries.. It is categorised as a Execute tool in the Aidex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on aidex_session? +

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

What risk level is aidex_session? +

aidex_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit aidex_session? +

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

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

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

Enforce policy on every Aidex tool call.

Deterministic rules across all 29 Aidex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.