Schema | mcp-ddg-research

mcp-ddg-research

Describes the environment variables required to run the server.

Name	Required	Description	Default
`MCP_HOST`	No	Host used for optional streamable HTTP mode.	0.0.0.0
`MCP_PORT`	No	Port used for optional streamable HTTP mode.	8000
`MCP_CACHE_DIR`	No	Directory for JSON cache files.	/data/cache
`MCP_TRANSPORT`	No	MCP transport. 'stdio' is the default. 'http' uses streamable HTTP when supported by the installed SDK.	stdio
`MCP_AUTH_TOKEN`	No	Bearer token for HTTP mode. If set, every HTTP request must send Authorization: Bearer <token>. If unset, HTTP mode logs a warning and runs without auth.
`MAX_CONCURRENCY`	No	Default deep search page fetch concurrency limit when max_concurrency is omitted. Runtime caps this at 12.	5
`MCP_ALLOWED_HOSTS`	No	Comma-separated Host allowlist for HTTP mode. '*' supports arbitrary deployment hosts by disabling SDK Host/Origin rebinding checks.	*
`DDG_TIMEOUT_SECONDS`	No	DuckDuckGo provider and fallback timeout in seconds.	15
`MCP_ALLOWED_ORIGINS`	No	Comma-separated Origin allowlist for HTTP mode. '*' supports arbitrary origins by disabling SDK Host/Origin rebinding checks.	*
`DDG_CACHE_TTL_SECONDS`	No	Search cache TTL in seconds.	21600
`FETCH_TIMEOUT_SECONDS`	No	Web fetch timeout in seconds.	15
`FETCH_CACHE_TTL_SECONDS`	No	Web fetch cache TTL in seconds.	7200

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