prompt-injection-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_attack_categoriesB | 列出所有攻击类别及其描述 |
| get_payloads_by_categoryC | 获取指定类别的所有攻击载荷 |
| get_payload_by_idC | 根据载荷ID获取特定攻击载荷 |
| run_test_sequenceC | 执行预定义的测试序列 |
| generate_custom_payloadC | 基于模板生成自定义攻击载荷 |
| analyze_responseC | 分析目标AI系统的响应，检测是否成功绕过安全限制 |
| generate_reportC | 生成测试报告 |
| search_payloadsC | 搜索包含特定关键词的攻击载荷 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| 所有攻击载荷数据库 | 完整的提示词注入攻击载荷数据库 |
| 使用文档 | MCP Server 使用指南 |
TDQS
Scored across 8 tools
Each tool targets a distinct phase of the testing workflow: listing categories, retrieving payloads (by category, ID, or keyword), generating custom payloads, running tests, analyzing responses, and reporting. Minor overlap exists between search_payloads and get_payloads_by_category, but their scopes and verbs are clearly differentiated.
All tool names use consistent snake_case and follow a verb_noun or verb_noun_preposition pattern (list_, get_, run_, generate_, analyze_, search_). No conventions are mixed.
8 tools cover the entire prompt-injection testing lifecycle without redundancy. Each tool maps to a natural workflow step, making the set lean yet sufficient.
The core workflow from payload discovery to report generation is fully covered. Missing management operations for payloads (update/delete) and test sequences, but the read/generate/run/analyze path is complete for typical testing use.