Skip to main content
Glama
Sign In
IDA-MCP

IDA-MCP

by Captain-AI-Hub
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Py Eval

py_eval

Runs Python code in an IDA Pro context to automate reverse engineering, inspect binaries, and target a specific database when multiple instances are open.

Instructions

Execute Python code in IDA context.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "code": "<code>"
    },
    "name": "py_eval"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesPython code to execute in IDA context
timeoutNoTimeout in seconds
instance_idNoREQUIRED whenever more than one database is open (from open_database's result or list_databases()); optional only while exactly one instance is live.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.0.1
    • changedInput schema / properties / instance_id / description
      Previous value: -"Instance id override"New value: +"REQUIRED whenever more than one database is open (from open_database's result or list_databases()); optional only while exactly one instance is live."
  2. First observedv0.9.7

TDQS

C2.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It does not disclose that arbitrary code runs with database access, what side effects or persistence occur, whether timeouts abort execution cleanly, or what is returned. For an arbitrary-code-execution tool this is a major disclosure gap.

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

Conciseness3/5

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

A single short sentence with no wasted words, but it is under-specified rather than deliberately concise. Front-loading is fine but the brevity reflects missing content, not efficiency.

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

Completeness2/5

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

This is a high-risk arbitrary code execution tool with no annotations and no output schema. The description omits safety, side effects, error behavior, and any routing to sibling tools, leaving it far short of what an agent needs to invoke it correctly and safely.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents code, timeout, and instance_id (including the multi-database requirement). The description adds nothing further, which meets the baseline 3 but no more.

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

Purpose3/5

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

States a specific verb and resource ("Execute Python code") with a scoping clause ("in IDA context"). However, it does nothing to distinguish this from sibling tools like py_exec_file or ida_python_reference, so an agent cannot tell which execution entry point to choose from the text alone.

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

Usage Guidelines2/5

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

There is no guidance on when to use this versus py_exec_file, ida_python_reference, or the many dedicated IDA tools. The description provides no context, exclusions, or prerequisites, leaving the agent to infer everything.

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