About specwise-mcp
specwise-mcp is a legacy package for OpenAPI and JSON Schema validation and OpenAPI breaking-change diffs. It now installs and forwards to bytestay-specwise-mcp and receives no further updates.
Key features
- 01Forwards to bytestay-specwise-mcp
- 02No further updates
Use cases
- 01Replace the package in an MCP client config
- 02Continue using existing environment variables
MCP support
The package is an MCP server entry point that forwards to bytestay-specwise-mcp. Its tools validate OpenAPI and JSON Schema and report OpenAPI breaking-change diffs, as described in the tagline.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx hybridforgelab-specwise-mcpRAPIDAPI_KEYSecretYour RapidAPI keyAPI_MARKET_KEYSecretYour api.market key, used when RAPIDAPI_KEY is not setHFL_MARKETPLACErapidapi or apimarket, when both keys are setLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEhybridforgelab-specwise-mcp: moved to bytestay-specwise-mcp
This package has moved to bytestay-specwise-mcp. Hybrid Forge Lab is now ByteStay.
This last version only installs bytestay-specwise-mcp and forwards to it. It prints a one-line notice on stderr and gets no more updates.
Switch
Replace hybridforgelab-specwise-mcp with bytestay-specwise-mcp in your MCP client config:
"command": "uvx",
"args": ["--from", "bytestay-specwise-mcp", "specwise-mcp"]
Or with Claude Code:
claude mcp add specwise --env RAPIDAPI_KEY=your-rapidapi-key -- uvx --from bytestay-specwise-mcp specwise-mcp
The environment variables are the same, so your keys keep working.
Links
- Package: bytestay-specwise-mcp
- Source: Bytestay/specwise-mcp
- Specwise API: specwise.bytestay.pt
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.