AI Development Pipeline MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VERCEL_TOKEN | Yes | Your Vercel authentication token | |
| AIRTABLE_API_KEY | Yes | Your Airtable API key | |
| AIRTABLE_BASE_ID | Yes | Your Airtable base ID | |
| ANALYTICS_SECRET | Yes | Your analytics secret key | |
| VERCEL_PROJECT_ID | Yes | Your Vercel project ID | |
| AIRTABLE_TABLE_NAME | Yes | Your Airtable table name | |
| NEXT_PUBLIC_APP_URL | Yes | The public URL of your application | |
| SQUARE_ACCESS_TOKEN | Yes | Your Square access token | |
| SQUARE_APPLICATION_ID | Yes | Your Square application ID |
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 |
|---|---|
| read_project_fileB | Read a local file from the VS Code workspace (restricted to workspace directory) |
| write_project_fileB | Write to a local file in the VS Code workspace (restricted to workspace directory) |
| run_shell_commandB | Run a whitelisted shell command in the workspace (npm, yarn, git, node, npx, tsc, eslint, prettier) |
| check_file_existsB | Check if a local file exists (restricted to workspace directory) |
| list_directory_filesC | List files in a workspace directory (restricted to workspace directory) |
| run_augment_promptC | Send a prompt to the local Augment coding agent |
| run_project_testsB | Run project tests (npm test, yarn test, etc.) |
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 7 tools
Each tool has a clearly distinct purpose with no overlap: file operations (check, list, read, write), running tests, executing shell commands, and interacting with an AI agent. The descriptions make it easy to tell them apart, preventing misselection.
Most tools follow a consistent verb_noun pattern (e.g., check_file_exists, list_directory_files, run_project_tests), but 'run_augment_prompt' deviates slightly by including the agent name. Overall, the naming is predictable and readable with only minor inconsistency.
With 7 tools, this server is well-scoped for AI development pipeline tasks. Each tool earns its place by covering essential operations like file management, testing, shell commands, and AI interaction, without being too sparse or bloated.
The toolset covers core AI development workflows effectively, including file CRUD, testing, and command execution. A minor gap exists in version control operations (e.g., git commits or branches), but agents can work around this using the shell command tool.