agentforge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTFORGE_API_KEY | Yes | Your AgentForge API key (required for invoke_agent tool) | |
| AGENTFORGE_BASE_URL | No | Override base URL for the AgentForge API (default: https://patreon.zeabur.app) |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_agentsA | List all AI agents available on the AgentForge marketplace. Returns agent IDs, names, descriptions, pricing, and categories. |
| get_agentC | Get detailed information about a specific AI agent including its input/output schema, pricing, and usage examples. |
| invoke_agentA | Invoke any AI agent on the AgentForge marketplace. Requires AGENTFORGE_API_KEY environment variable. Supports streaming responses and returns the assistant reply. |
| check_agent_healthC | Check the health / availability status of a specific AI agent. |
| get_platform_statsB | Get aggregate statistics about the AgentForge platform: total agents, active users, requests served, etc. |
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 5 tools
Each tool has a clearly distinct purpose with no overlap. check_agent_health focuses on availability, get_agent provides detailed metadata, get_platform_stats offers aggregate platform data, invoke_agent executes agent calls, and list_agents shows the marketplace catalog. An agent can easily distinguish between these operations.
All tools follow a consistent verb_noun pattern with snake_case. The verbs (check, get, get, invoke, list) are appropriate and predictable, making the set easy to navigate and understand at a glance.
Five tools is well-scoped for managing an AI agent platform. It covers essential operations like listing, retrieving details, invoking agents, checking health, and viewing platform stats without being overwhelming or insufficient for the domain.
The toolset covers core workflows: discovery (list_agents, get_agent), execution (invoke_agent), monitoring (check_agent_health, get_platform_stats). A minor gap is the lack of update/delete tools for managing agents, but this might be intentional if the platform is read-only for users.