Skill MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| workspace | No | The directory path used for workspace file operations like file_read, file_write, and file_edit. | |
| skills-dir | Yes | The directory where skill folders are stored for auto-discovery and loading. |
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": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| skillC | Load a skill to get detailed instructions for a specific task. No skills are currently available. |
| list_skillsA | List all available skills with their names and descriptions. Use this to discover what skills are available before loading one. |
| skill_resourceA | Read a resource file from a skill's directory. Use this tool after loading a skill to read referenced files like templates, examples, or reference documentation. The resource_path should be relative to the skill's base directory (e.g., 'assets/template.md', 'references/api_reference.md'). |
| skill_scriptB | Execute a script from a skill's scripts/ directory. Use this tool to run Python (.py), Shell (.sh/.bash), JavaScript (.js), or TypeScript (.ts) scripts bundled with a skill. Scripts are executed in the workspace directory. |
| file_readB | Read a file from the workspace directory. Use this tool to read files generated by skills or modified by the user. |
| file_writeA | Create or overwrite a file in the workspace. Use this tool when a skill needs to generate output files. |
| file_editB | Edit an existing file in the workspace using search and replace. The old_string must exist in the file and should be unique. |
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 (edit/read/write) are separate from skill operations (list/load/resource/script). The descriptions reinforce unique functions, such as file_edit for search-and-replace versus file_write for creation/overwriting, and skill_script for execution versus skill_resource for reading files. An agent can easily differentiate between tools based on their specific actions and contexts.
All tools follow a consistent snake_case naming pattern with clear verb_noun structures: file_edit, file_read, file_write, list_skills, skill, skill_resource, and skill_script. The naming is predictable, using prefixes like 'file_' and 'skill_' to group related tools, making it easy for agents to understand relationships and purposes without confusion or deviation.
With 7 tools, the count is well-scoped for the server's purpose of managing files and skills. It covers essential operations like file CRUD (edit/read/write) and skill lifecycle (list/load/resource/script), providing a balanced set without being too sparse or overwhelming. Each tool earns its place by addressing a core need in the domain, avoiding redundancy or gaps.
The tool surface is nearly complete for the domain of file and skill management, covering key operations like file editing, reading, writing, skill listing, loading, resource access, and script execution. A minor gap exists in file operations, such as the lack of a delete_file tool, but agents can work around this by using file_write to overwrite or clear files. Overall, it supports core workflows effectively with no dead ends.