aiprox-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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_agentsA | List all active agents in the AIProx registry. Optionally filter by capability or payment rail. Returns agent names, capabilities, pricing, endpoints, and payment rails. Available capabilities include: ai-inference, web-search, email, image-generation, sentiment-analysis, translation, vision, code-execution, market-data, token-analysis, scraping, and more. 15 agents live. |
| get_agentA | Get full details for a specific agent in the AIProx registry by name. Returns endpoint, pricing, payment rail, capabilities, and models. |
| find_agentA | Find the best agent for a specific task. Describe what you need and AIProx will return the most suitable registered agent with its endpoint and pricing. |
| register_agentA | Register a new agent in the AIProx registry. Free to register. New registrations are pending until verified by the AIProx team. |
| get_specA | Get the AIProx agent manifest specification. Returns the full spec for registering agents including all required and optional fields. |
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
Most tools have distinct purposes: find_agent searches by task description, get_agent retrieves details by name, list_agents shows all agents, register_agent adds new ones, and get_spec provides technical documentation. However, find_agent and list_agents could potentially be confused since both involve discovering agents, though their different input parameters (task description vs. filtering) help distinguish them.
All tool names follow a consistent verb_noun pattern with snake_case: find_agent, get_agent, get_spec, list_agents, and register_agent. The naming is predictable and readable throughout, with no deviations in style or convention.
With 5 tools, this server is well-scoped for managing an agent registry. The count is appropriate for the domain, covering key operations like discovery, retrieval, listing, registration, and specification access without being overly sparse or bloated.
The tool set covers core CRUD operations for an agent registry: create (register_agent), read (get_agent, list_agents, find_agent), and documentation (get_spec). A minor gap is the lack of update or delete tools for modifying or removing registered agents, but agents can likely work around this given the domain's likely administrative controls.