mcp-forge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODE_ENV | No | Environment | development |
| LOG_LEVEL | No | pino log level | info |
| PROMPTS_DIR | No | Override the prompts directory location | .claude/commands (relative to binary) |
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 |
|---|---|
| list_stepsA | List all rewrite steps (0–14) in order. Optionally filter by projectType to see which steps apply or are skipped. |
| get_stepA | Get the full prompt content for a specific step (0–14). For step 8 (Entrypoint Layer), you must provide projectType. |
| get_entrypointB | Get the entrypoint-specific instructions (Step 8) for a given project type (http-api, library, cli, worker, mcp-server). |
| get_master_promptA | Get the complete master prompt for single-pass rewrites of small projects (< 2000 lines). Handles all project types automatically. |
| validate_manifestA | Validate an AUDIT_MANIFEST JSON string against the expected schema (produced by Step 0). Returns a list of validation errors, or confirms the manifest is valid. |
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 5 tools
Each tool serves a distinct purpose: retrieving specific prompts (entrypoint, master, or step), listing steps, or validating manifests. No ambiguity in their roles.
All tool names follow a consistent verb_noun pattern (e.g., get_entrypoint, list_steps, validate_manifest), ensuring predictability.
With 5 tools, the server is well-scoped for its domain of prompt management and validation, neither too sparse nor too heavy.
The tool set covers retrieval of all prompt variations, step listing, and manifest validation, leaving no obvious gaps for the intended use case.