Schema | Agency MCP Server

Agency MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PORT`	No	HTTP server port (default 3000)	3000
`BASE_PATH`	No	HTTP server path prefix
`DEMO_MODE`	No	Set to 1 to make Search Console and visibility always use fixture and mock data
`MODEL_NAME`	No	Model name to request from the chat-completions endpoint
`CLIENTS_FILE`	No	Client allowlists file (default config/clients.json, the three demo sites)	config/clients.json
`MODEL_API_KEY`	No	API key for the chat-completions endpoint
`MAX_CRAWL_PAGES`	No	Maximum number of pages for a site crawl (default 200)	200
`PAGESPEED_API_KEY`	No	Optional PageSpeed Insights key. Without a key, calls share Google's anonymous daily quota.
`MODEL_API_BASE_URL`	No	Base URL of any endpoint that accepts POST {base}/chat/completions, used by answer_engine_visibility
`GSC_OAUTH_CLIENT_ID`	No	OAuth client id, used with a refresh token for Search Console access
`FETCH_RATE_PER_SECOND`	No	Outbound politeness limit: requests per second per host (default 2)	2
`GSC_OAUTH_CLIENT_SECRET`	No	OAuth client secret, used with a refresh token for Search Console access
`GSC_OAUTH_REFRESH_TOKEN`	No	OAuth refresh token for Search Console access
`GSC_SERVICE_ACCOUNT_JSON`	No	Search Console service-account key, as a file path or inline JSON

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessNo issues