Skip to main content
Glama

Start Frida Session

start_frida_session

Attach Frida to a selected process or spawn a target paused for script loading before execution; closing detaches instrumentation without killing the target.

Instructions

Attach Frida to one selected process or spawn one selected target. Spawned targets remain paused until resume_frida_session, allowing scripts to load before execution. Closing a session detaches instrumentation; it does not kill the target.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "pid": 1234,
      "mode": "attach",
      "device_id": "local"
    },
    "name": "start_frida_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
pidNo
argvNo
modeYesOperation mode that selects the requested behavior.
remoteNo
programNo
device_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare the generic profile (not read-only, open-world, not idempotent, not destructive). The description adds real state semantics beyond that: spawned targets stay paused until resumed so scripts can load first, and session close detaches instrumentation without terminating the target. Session-handle return value and error/failure behavior are left unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action, then state behavior, then the lifecycle caveat. No redundant restatement of the title and every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Coverage of paused-spawn and detach-vs-kill semantics is strong for a stateful session tool with no output schema. However, with six largely undocumented parameters and no mention of what a successful start returns (a session identifier for later resume/close calls), an agent still has gaps before it can call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Six parameters with only 17% schema description coverage, and the description never maps pid/program/argv to attach versus spawn, nor explains device_id, the nested remote object, or the keepalive interval. It only vaguely gestures at 'one selected process or spawn one selected target', leaving most parameter meaning undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Attach Frida to one selected process or spawn one selected target') and makes the two operating modes explicit. Siblings such as resume_frida_session and close_frida_session are only implied through the lifecycle references, not named as alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The attach-vs-spawn distinction gives an implied decision rule, and the reference to resume_frida_session hints at the follow-up step. There is no explicit guidance on when to choose this over instrument_with_frida or binary_session, nor prerequisites such as a preceding list_frida_processes / list_frida_devices call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools