MCP360 Universal Gateway
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP360_API_KEY | Yes | Your MCP360 API key (required). Get it from https://mcp360.ai in Settings → API Keys | |
| MCP360_GATEWAY_URL | No | Custom gateway URL (optional) | https://connect.mcp360.ai/v1/mcp360/mcp |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchD | search tool |
| executeD | execute tool |
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 2 tools
The two tools have clearly distinct purposes: 'execute' suggests performing an action or running something, while 'search' implies finding or retrieving information. There is no overlap or ambiguity between these functions, making it easy for an agent to choose the correct tool.
Both tool names follow a consistent pattern: they are single, descriptive verbs in lowercase. There are no deviations in style or convention, making the naming predictable and easy to understand across the set.
With only two tools, the server feels thin for a 'Universal Gateway', which implies broad functionality. This limited set is likely insufficient for comprehensive coverage of a gateway's typical operations, such as routing, transformation, or monitoring, making it borderline too few for the apparent scope.
Given the server's name as a 'Universal Gateway', there are significant gaps in the tool surface. Core gateway operations like configuration management, logging, or connection handling are missing, leaving agents unable to perform essential tasks beyond basic execution and search, which will likely cause failures in broader workflows.