Schema | MCP Tool-Retrieval Gateway

MCP Tool-Retrieval Gateway

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_ROUTER_CONFIG`	No	Path to the YAML/JSON configuration file describing upstream servers and tools.	config.example.yaml
`MCP_ROUTER_EMBEDDER`	No	Embedder implementation to use. Set to 'sentence-transformers' for semantic matching; otherwise the offline default is used.	hashing
`MCP_ROUTER_ST_MODEL`	No	Sentence transformer model name to use when MCP_ROUTER_EMBEDDER=sentence-transformers.	all-MiniLM-L6-v2

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.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{ "listChanged": false }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
find_toolsA	Search all connected MCP servers for the tools most relevant to a natural-language query. Returns up to k tool definitions (name, description, input schema) as JSON. Call this first to discover which tool to use, then invoke it with call_tool.
call_toolA	Invoke a tool by name (as returned by find_tools) on whichever upstream server owns it, forwarding the given arguments, and return that server's result.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sneha4175/mcp-tool-router'

If you have feedback or need assistance with the MCP directory API, please join our Discord server