Dify Workflow
MCP Server transforms Dify workflow applications into MCP-compatible servers, allowing AI assistants to interact with custom functions defined in Dify. Developed by hjlarry, this plugin enables users to create simple workflow apps in Dify, expose them as endpoints with structured input schemas, and then connect these endpoints to MCP clients like Cursor. The implementation requires minimal setup - just creating a workflow in Dify, adding an endpoint that selects the app, and copying the endpoint URL to the MCP client - making it an efficient bridge between Dify's workflow capabilities and MCP-enabled AI assistants.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- other
- Source
- PulseMCP
- Repository
- github.com/hjlarry/dify-plugin-mcp_server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Dify Workflow from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.