mcp-api-translator
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Controls the log level for the server. Logs are structured JSON lines on stderr in containers, readable text on a TTY. | |
| LOG_FORMAT | No | Controls the log format. Logs are structured JSON lines on stderr in containers, readable text on a TTY. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_specA | Parse an OpenAPI or Postman spec and preview the MCP tools that would be generated, without writing any files. Use this to curate (filter/inspect) before generating. |
| generate_mcp_serverB | Generate a complete, runnable TypeScript MCP server project from an OpenAPI or Postman spec. Writes the project to outputDir. Use force to overwrite a non-empty directory. |
| extend_mcp_serverA | Append the operations from another spec to an already-generated project (identified by its .mcp-translator.json manifest). Idempotent: operations already present are skipped, and hand-edited tool files are preserved unless force is set. Enables aggregating multiple APIs into one MCP server. |
| list_supported_featuresA | Report the input formats, auth schemes, transports, and limits this tool supports. |
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 4 tools
Each tool has a clearly distinct purpose: analyze_spec previews without writing, generate_mcp_server creates a new project, extend_mcp_server appends to an existing one, and list_supported_features reports capabilities. There is no overlap in verbs or intended outcomes, so an agent can easily select the right tool.
All four names follow a strict verb_noun snake_case convention. The generate_mcp_server / extend_mcp_server pair even shares a consistent resource suffix, reinforcing the pattern.
Four tools is well-scoped for a spec-to-MCP-server translator: preview, generate, extend, and capability reporting. Each tool is substantive and earns its place with no redundancy.
The lifecycle is largely covered: inspect a spec, generate a project, aggregate additional specs, and query supported features. Minor gaps exist around updating or regenerating an existing project from a changed spec and removing operations, but agents can work around these via force-based regeneration.