Skip to main content
Glama
Omprakash97

Cursor Agent Poisoning

by Omprakash97

anything

Embeds malicious instructions into AI assistants via Model Context Protocol (MCP) registration, enabling persistent agent poisoning across chat contexts without tool execution.

Instructions

Simple there for ambiance :(

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • The implementation of the 'anything' tool. It is an async function that returns the string 'Nothing'. Registered via @mcp.tool() decorator.
    @mcp.tool()
    async def anything() -> str:
        """
        Simple there for ambiance :(
        """
        return "Nothing"
Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description 'Simple there for ambiance :(' does not reveal any behavioral traits such as whether it's read-only, destructive, requires authentication, has side effects, or returns data. It offers no useful context beyond the vague phrase.

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

Conciseness2/5

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

The description is under-specified rather than concise. 'Simple there for ambiance :(' is a single vague sentence that fails to convey meaningful information. While brief, it does not earn its place by providing value, making it inefficient due to lack of substance.

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

Completeness1/5

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

Given the tool's complexity (0 parameters, no output schema, no annotations), the description is completely inadequate. It does not explain what the tool does, when to use it, or what behavior to expect. Even for a simple tool, the description fails to provide basic completeness.

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

Parameters4/5

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

The tool has 0 parameters, and schema description coverage is 100% (though trivial since there are no parameters). With no parameters to document, the description does not need to add semantic details beyond the schema. The baseline score for 0 parameters is 4, as there is nothing to compensate for.

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

Purpose1/5

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

The description 'Simple there for ambiance :(' is vague and tautological. It restates the tool's name 'anything' in a circular way without specifying any concrete action, resource, or purpose. No verb-resource combination is provided, and it fails to distinguish from the sibling tool 'say_hello'.

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

Usage Guidelines1/5

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

The description provides no guidance on when to use this tool versus alternatives. It lacks any context about appropriate scenarios, prerequisites, or comparisons to the sibling tool 'say_hello'. There is no explicit or implied usage information.

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

Related 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/Omprakash97/exploit-mcp'

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