Schema | anythingllm-mcp

anythingllm-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`ANYTHINGLLM_API_KEY`	Yes	The API key to authenticate with AnythingLLM.
`ANYTHINGLLM_BASE_URL`	No	The web address where your AnythingLLM lives. Defaults to http://localhost:3001.

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": true }

Functions exposed to the LLM to take actions

Name	Description
check_authA	Verify the configured API key can reach AnythingLLM. Returns whether authentication succeeded.
list_workspacesA	List all AnythingLLM workspaces with their display name and slug. Use a name or slug from here with the other tools.
list_documentsB	List the documents currently embedded (searchable) in a workspace. Accepts a workspace name or slug.
query_workspaceA	Ask a natural-language question answered from a workspace's embedded documents. Default 'query' mode answers ONLY from the documents (grounded, cites sources); 'chat' mode also allows the model's general knowledge. Read-only.

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/DezGDNY/anythingllm-mcp'

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