How do I use anythingllm-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@anythingllm-mcp ask my workspace about the quarterly financial report" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

anythingllm-mcp

by moliver28

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

AnythingLLM MCP Server

Complete MCP (Model Context Protocol) server for AnythingLLM - the all-in-one AI document chat platform.

Features

Zero human interaction. Just set your API key and go.

Tools (15 total)

System

check_token - Validate API token
generate_api_key - Generate new API key (admin)

Workspaces

list_workspaces - List all workspaces
get_workspace - Get workspace details
create_workspace - Create new workspace
update_workspace - Update workspace settings
delete_workspace - Delete a workspace

Chat

chat - Send chat message (chat/query mode)
stream_chat - Stream chat response

Documents

upload_document - Upload document to workspace
update_embeddings - Manage workspace embeddings
list_workspace_documents - List workspace documents

Threads

list_threads - List workspace threads
get_thread - Get thread details
delete_thread - Delete a thread

System & Compatible

get_system_env - Get system configuration
openai_chat_completion - OpenAI-compatible endpoint

Related MCP server: AnythingLLM MCP Server

Quick Start

1. Install

npm install -g anythingllm-mcp

2. Set API Key

Get your API key from AnythingLLM: Settings > Developer API

export ANYTHING_LLM_API_KEY="your-api-key-here"
export ANYTHING_LLM_BASE="http://localhost:3001/api/v1"  # optional, default

3. Add to OpenCode

Add to your opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "anythingllm": {
      "type": "local",
      "command": ["anythingllm-mcp"],
      "environment": {
        "ANYTHING_LLM_API_KEY": "your-api-key-here",
        "ANYTHING_LLM_BASE": "http://localhost:3001/api/v1"
      },
      "enabled": true
    }
  }
}

4. Use in Any Session

The tools are now available. Example:

> Use the chat tool to ask AnythingLLM about my documents

Development

git clone https://github.com/moliv/anythingllm-mcp.git
cd anythingllm-mcp
npm install
npm run build

Requirements

AnythingLLM running (local or remote)
Valid API key from AnythingLLM
Node.js 18+

License

MIT

Available Tools

17 tools

chatC

Send a chat message to a workspace (mode: chat or query)

Inputs: workspace (required), message (required), mode, userId.

check_tokenA

Validate the current API token

Inputs: no named parameters.

create_workspaceC

Create a new workspace

Inputs: name (required), slug, openAiTemp, openAiHistory, +2 more.

delete_threadC

Delete a thread from a workspace

Inputs: workspace (required), threadSlug (required).

delete_workspaceC

Delete a workspace

Inputs: slug (required).

generate_api_keyB

Generate a new API key (admin)

Inputs: no named parameters.

get_system_envB

Get system environment configuration

Inputs: no named parameters.

get_threadC

Get details of a specific thread

Inputs: workspace (required), threadSlug (required).

get_workspaceB

Get details of a specific workspace

Inputs: slug (required).

list_threadsC

List all threads in a workspace

Inputs: workspace (required).

list_workspace_documentsC

List all documents in a workspace

Inputs: slug (required).

list_workspacesB

List all workspaces

Inputs: no named parameters.

openai_chat_completionC

OpenAI-compatible chat completion endpoint (use workspace as model)

Inputs: model (required), messages (required), stream.

stream_chatC

Stream a chat message to a workspace

Inputs: workspace (required), message (required), mode, userId, +1 more.

update_embeddingsC

Add or remove documents from workspace embeddings

Inputs: workspace (required), adds, deletes.

update_workspaceD

Update workspace settings

Inputs: slug (required), name, openAiTemp, openAiHistory, +3 more.

upload_documentC

Upload a document to a workspace

Inputs: workspace (required), filePath (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.9/5.0

Scored 2026-05-02 05:40 across 17 tools

Disambiguation5/5

All tools target distinct operations: chat, workspace, thread, document, and admin functions. Chat variants (chat, stream_chat, openai_chat_completion) differ by mode, and workspace/thread/document tools have clear boundaries.

Naming Consistency4/5

Most tools follow verb_noun pattern in snake_case (e.g., create_workspace, list_threads). A few like 'chat' and 'openai_chat_completion' deviate slightly, but overall naming is predictable.

Tool Count5/5

17 tools cover workspace, document, thread, chat, and admin operations without feeling excessive. The scope matches the server's purpose well.

Completeness4/5

CRUD operations are present for workspaces and threads (though thread creation is implicit via chat). Document management includes upload, listing, and embedding updates. Missing explicit delete document but covered via update_embeddings.

Resources

Related MCP Connectors

mcp-server
com.niftypm
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Project Management Communication File Systems
2
https://mcp.niftypm.com/mcp
Flowra
io.github.flowradev
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Agent Orchestration Autonomous Agents
11
https://mcp.flowra.dev/mcp
jumpcloud-genai
com.jumpcloud
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
Cloud Platforms Security Developer Tools
2
https://mcp.jumpcloud.com/v1
mcp-aichat
io.github.AceDataCloud
MCP server for AI dialogue using various LLM models via AceDataCloud
AI & Machine Learning
2
https://aichat.mcp.acedata.cloud/mcp

Related MCP Servers

litellm-mcp
AI & Machine Learning Developer Tools
weeebdev
A
license
Not graded
quality
D
maintenance
MCP server that provides tools to interact with the LiteLLM proxy API, enabling LLM completions, embeddings, image generation, and admin operations.
Updated 5 months ago (2026-06-09 20:24 UTC)
70 npm
MIT
AnythingLLM MCP Server
AI & Machine Learning RAG Systems
andreperez
A
license
A
quality
C
maintenance
Enables MCP-compatible clients to interact with AnythingLLM, providing tools for workspace management, chat and thread operations, document operations, vector search, and system inspection.
Updated 7 days ago (2026-11-05 17:14 UTC)
34
6
MIT
rocketchat-mcp
Communication Workplace & Productivity
SufiSR
F
license
Not graded
quality
D
maintenance
MCP server for Rocket.Chat, enabling AI agents to interact with Rocket.Chat workspaces via tools like listing users, sending messages, and managing channels.
Updated 9 months ago (2026-02-26 11:06 UTC)
2
-
AnythingLLM Control Plane MCP
RAG Systems AI & Machine Learning
TheNovaNodes
A
license
A
quality
B
maintenance
Enables managing and controlling AnythingLLM instances through MCP, providing tools to list, create, and delete workspaces, retrieve system environment settings, and get vector counts.
Updated 2 months ago (2026-09-05 21:32 UTC)
5
1
MIT

AnythingLLM MCP Server

Features

Tools (15 total)

Quick Start

1. Install

2. Set API Key

3. Add to OpenCode

4. Use in Any Session

Development

Requirements

License

Available Tools

Tool Schema Changelog

TDQS

Resources

Related MCP Connectors

Related MCP Servers

litellm-mcp

AnythingLLM MCP Server

rocketchat-mcp

AnythingLLM Control Plane MCP