Skip to main content
Glama

memtool

Scan and manipulate process memory on Windows and Linux. Supports value scanning, filtering, reading, writing, and disassembly for reverse engineering tasks.

Instructions

Process memory tool for reverse engineering and game hacking. CheatEngine-style workflow: search → filter → filter → find exact addresses → write. Supported: Windows (ReadProcessMemory/WriteProcessMemory), Linux (/proc/pid/mem). macOS: not supported (SIP). Operations: regions (list memory map), search (value scan or unknown initial value scan, creates session), filter (narrow: exact/changed/unchanged/increased/decreased), undo (restore previous filter), read (hex dump), write (modify memory), disasm (disassemble live memory — x86/x64/ARM/ARM64), info (session status + values), close (end session), struct_search (multi-field pattern), pointer_scan (find pointer chains to address), diff (compare memory snapshots).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationYesOperation: regions, search, filter, read, write, disasm, info, close, undo, struct_search, pointer_scan, diff,required
pidNoTarget process ID (for regions, search, read, write, disasm, struct_search, pointer_scan, diff)
session_idNoSession ID from a previous search (for filter, info, close, undo, diff)
value_typeNoValue type: int8/16/32/64, uint8/16/32/64, float32/64, string, utf16, bytes
valueNoSearch/write value (number for numeric types, text for string/utf16, hex bytes like '4D 5A 90' for bytes). Omit for unknown initial value scan.
endianNoByte order: little (default) or big
filter_typeNoFilter: exact, changed, unchanged, increased, decreased
addressNoHex address (e.g. '0x7FF6A1B20000') for read/write/disasm/pointer_scan
lengthNoBytes to read/disasm (default 256 for read, 64 for disasm, max 4096)
protectionNoFilter by protection: r, rw, rx
max_resultsNoMax results to display (default 100, max 1000)
struct_patternNoJSON array for struct search: [{offset:0,type:'int32',value:'100'},{offset:4,type:'int32',value:'50'}]
max_depthNoPointer scan max chain depth (default 3, max 5)
max_offsetNoPointer scan max offset from target (default 0x1000)
archNoCPU architecture for disasm: x86 (default) or arm
modeNoCPU mode for disasm: 32 or 64 (default)
countNoNumber of instructions to disassemble (default 50, max 200)
Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses supported OS (Windows, Linux), unsupported (macOS), and mentions operations like 'write' (which modifies memory with potential side effects). However, it does not warn about risks like process crashes, permission requirements, or the effect of writing to critical memory regions. The description is partially transparent but misses important behavioral warnings.

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

Conciseness4/5

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

The description is structured with a bullet-like list of operations and key details (OS support, workflow). Every sentence adds value, though the list of operations is somewhat lengthy. It front-loads purpose and workflow effectively. Could be slightly more concise by grouping operations, but overall well-organized.

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

Completeness4/5

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

Given the tool's complexity (17 parameters, 12+ operations), the description covers the workflow, platform support, operation-specific details, and limitations (max values, unsupported macOS). It does not explain return values (no output schema), but it is otherwise fairly complete for an AI agent to understand when and how to use the tool.

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 explains each parameter well. The description adds context by listing which operations use which parameters (e.g., 'address' for read/write/disasm/pointer_scan). However, it does not add new meaning beyond the schema; it rather reorganizes existing info. Baseline 3 is appropriate.

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

Purpose5/5

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

The description clearly states it is a 'Process memory tool for reverse engineering and game hacking' and lists a CheatEngine-style workflow. It enumerates many specific operations like 'search', 'filter', 'read', 'write', etc., making its purpose unmistakable. Among siblings (none are memory tools), it is well-distinguished.

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

Usage Guidelines4/5

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

The description outlines the typical workflow ('search → filter → filter → find exact addresses → write') and states unsupported platforms (macOS). It implicitly guides when to use this tool (memory access tasks) but does not explicitly exclude alternatives or provide when-not-to-use guidance. A slightly more explicit directive would be ideal.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/knewstimek/agent-tool'

If you have feedback or need assistance with the MCP directory API, please join our Discord server