> ## Documentation Index
> Fetch the complete documentation index at: https://docs.skillcreator.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP tools

> Complete reference for all MCP tools exposed by SkillCreator.

The SkillCreator MCP server exposes the following tools to AI agents.

## Skill management

### `get_status`

Get the current runtime status.

**Parameters:** None

**Returns:** Runtime version, database path, skill count, uptime.

### `search_skills`

Search skills by keyword.

**Parameters:**

<ParamField path="query" type="string" required>
  Search query string.
</ParamField>

**Returns:** Array of matching skills with name, description, and relevance score.

### `inspect_skill`

Get detailed information about a specific skill.

<ParamField path="skillId" type="string" required>
  Skill name (kebab-case identifier).
</ParamField>

**Returns:** Full skill metadata, content, file list, and latest eval scores.

## Health and evaluation

### `get_health_overview`

Get aggregate health metrics across all skills.

**Parameters:** None

**Returns:** Total skills, average scores, skills needing attention, recent eval activity.

### `get_skill_health`

Get health metrics for a specific skill.

<ParamField path="skillId" type="string" required>
  Skill name.
</ParamField>

**Returns:** Eval scores per dimension, trend direction, last eval date, improvement suggestions.

### `get_eval_trend`

Get eval score history for a skill.

<ParamField path="skillId" type="string" required>
  Skill name.
</ParamField>

<ParamField path="limit" type="number">
  Maximum number of eval runs to return.
</ParamField>

**Returns:** Array of eval runs with timestamps and scores.

## Run history

### `get_run_history`

Get execution history for a skill.

<ParamField path="skillId" type="string" required>
  Skill name.
</ParamField>

<ParamField path="limit" type="number">
  Maximum number of runs to return.
</ParamField>

**Returns:** Array of skill runs with timestamps, agent runtime, and outcome.

### `report_run`

Report a skill execution (used by agents to log skill usage).

<ParamField path="skillId" type="string" required>
  Skill name.
</ParamField>

<ParamField path="agent" type="string">
  Agent runtime that used the skill.
</ParamField>

<ParamField path="outcome" type="string" required>
  Execution outcome: `success`, `partial`, or `failure`.
</ParamField>

**Returns:** Confirmation of recorded run.

## Additional tools

The following tools are also available but not fully documented here:

* `list_skills` - List all skills in the library, with optional filters.
* `get_skill` - Get a skill by ID.
* `create_skill` - Create a new skill.
* `delete_skill` - Delete a skill by ID.
* `read_skill_file` - Read the content of a file within a skill.
* `write_skill_file` - Write or update a file within a skill.
* `run_eval` - Trigger an evaluation run for a skill.
* `install_skill` - Install a skill into an agent runtime.
* `preview_install` - Preview what installing a skill would do, without making changes.
* `detect_agents` - Detect which agent runtimes are present on the system.