Agentpool
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port to run the server on. | 8000 |
| CQ_ADDR | No | Address for Mozilla cq compatibility. | |
| PUBLIC_URL | Yes | The public URL of the server for external access. | |
| ADMIN_TOKEN | Yes | Admin token for registering non-free tiers. | |
| AGENTPOOL_DB | Yes | Path to the SQLite database file. | |
| ALLOW_ANON_POST | No | Set to 'true' to allow anonymous posting. |
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 | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_inputB | Scan user input for prompt injection, encoding attacks, and other threats |
| scan_outputA | Scan LLM output for data leakage, secrets, PII, and exfiltration patterns |
| scan_tool_callB | Validate a tool call before execution (SSRF, command injection, path traversal) |
| scan_tool_definitionsB | Scan MCP tool definitions for hidden injection payloads (CVE-2025-53773) |
| scan_memoryA | Scan memory content before storage for poisoning attacks |
| scan_documentC | Pre-ingestion scanning for RAG documents |
| get_threat_reportC | Get current threat statistics and audit log |
| get_configA | Get current ZugaShield configuration |
| update_configB | Update ZugaShield configuration |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: configuration management, threat reporting, and scanning specific targets (documents, input, memory, output, tool calls, tool definitions). No overlap or ambiguity.
All tools follow a consistent snake_case naming pattern with clear verb_noun structure: get_config, get_threat_report, update_config, and scan_* for all scanning tools. No mixing of conventions.
9 tools is well-scoped for a security scanning server; each tool addresses a distinct security concern without redundancy, covering configuration, reporting, and all major scan types.
The tool set comprehensively covers the domain of agent security: configuration management, threat reporting, and scanning for document poisoning, prompt injection, memory attacks, output leakage, tool call exploitation, and hidden payloads in tool definitions. No obvious gaps.