Schema | markdown-for-agents-mcp

markdown-for-agents-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HTTP_PORT`	No	When set, starts an HTTP server on this port instead of stdio
`LOG_LEVEL`	No	DEBUG, INFO, WARN, or ERROR	INFO
`LOG_FORMAT`	No	text (human-readable) or json (structured)	text
`CACHE_TTL_MS`	No	Cache entry TTL (15 minutes)	900000
`MAX_REDIRECTS`	No	Max redirect hops before error	10
`MCP_AUTH_TOKEN`	No	Bearer token required on all HTTP requests (HTTP mode only)
`CACHE_MAX_BYTES`	No	Max LRU cache size (50 MB)	52428800
`FETCH_TIMEOUT_MS`	No	Timeout per fetch request (ms)	30000
`PLAYWRIGHT_PROXY`	No	Proxy server URL for Playwright (e.g. http://proxy.example.com:8080)
`BLOCKLIST_DOMAINS`	No	Comma-separated domains to block (or allow in allowlist mode)
`MAX_CONTENT_LENGTH`	No	Max content size (chars) before truncation	100000
`USE_ALLOWLIST_MODE`	No	When true, only domains in BLOCKLIST_DOMAINS are allowed	false
`DOWNLOAD_TIMEOUT_MS`	No	Timeout for binary file downloads (ms)	60000
`BLOCKLIST_URL_PATTERNS`	No	Comma-separated regex patterns to block by URL path
`MAX_CONCURRENT_FETCHES`	No	Max parallel fetches in batch operations	5
`PLAYWRIGHT_PROXY_BYPASS`	No	Comma-separated domains to bypass the proxy
`WEB_SEARCH_DEFAULT_TIMEOUT_MS`	No	Default timeout for search requests (ms)	30000

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

ActivityInactive

ResponsivenessNo issues