Dify Knowledge MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DIFY_API_KEY | Yes | Your Dify API key | |
| DIFY_API_URL | Yes | The Dify API endpoint URL, which includes your Dataset ID (e.g., https://api.dify.ai/v1/datasets/YOUR_DATASET_ID/documents/query) |
Instructions
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.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| query_dify_knowledgeC | Query Dify knowledge base with a search query |
| get_dify_configB | Get current Dify API configuration status |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one retrieves configuration status, while the other queries a knowledge base. There is no overlap in functionality, making it easy for an agent to select the correct tool based on the task.
Both tools follow a consistent verb_noun pattern with snake_case naming (get_dify_config, query_dify_knowledge). The verbs 'get' and 'query' are appropriate and distinct, maintaining a predictable naming convention throughout.
With only 2 tools, the server feels thin for a knowledge base domain. It lacks essential operations like creating, updating, or deleting knowledge entries, which limits its utility and scope compared to typical MCP servers.
The tool surface is severely incomplete for a knowledge base server. It only allows querying and checking configuration, missing critical CRUD operations (e.g., add, update, delete knowledge) and other lifecycle management tools, which will likely cause agent failures in comprehensive workflows.