ModelBound
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODELBOUND_API_KEY | No | Optional API key for cloud sync features. Without it, local tools still work. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ide.detectLayoutA | Detect which IDE skill/rule layouts exist in the current working directory. Returns the list of matching adapters (e.g. cursor, claude, kiro). Local-only, no network. |
| skills.listLocalA | List all skill / rule files found in the detected IDE directories under the current working directory. |
| skills.readLocalA | Read a local skill file (raw contents). Path must be inside the current working directory. |
| skills.writeLocalA | Write a local skill file. Creates parent directories. Path must be inside the current working directory. |
| skills.lintA | Lint a skill file: front-matter, token count, broken links, TODO markers. Local-only. |
| skills.validateFormatC | Validate a skill file against the agentskills.io standard. |
| skills.convertA | Convert a skill file from one IDE format to another (e.g. cursor → claude). Round-trips through a canonical {frontmatter, body} representation. |
| skills.diffA | Diff a local skill file against its cloud counterpart by slug. Local-side diff is computed here; the cloud half requires MODELBOUND_API_KEY. |
| cloud.pullSkillB | Pull a skill from the ModelBound cloud library. Response includes ai_type, source_platform, source_path, and repo when known. Requires MODELBOUND_API_KEY. |
| cloud.pushSkillB | Create or update a skill in the cloud library. Requires MODELBOUND_API_KEY. |
| cloud.listSkillsA | List skills in the cloud library. Supports ai_type (skill|hook|steering|system-prompt|rule|agent|memory|spec|instructions|prompt) and source_platform (claude-code|cursor|kiro|amazon-q|copilot|windsurf|codex|agents|modelbound) filters. Each row includes ai_type, source_platform, source_path, and repo for hierarchy-aware orchestration. Requires MODELBOUND_API_KEY. |
| cloud.resourceTreeA | Return the team's full AI resource hierarchy grouped by platform → top-level directory (.claude/skills, .cursor/rules, .kiro/steering, …) → files. Use this BEFORE listSkills when an orchestrator needs to map available context before loading. Requires MODELBOUND_API_KEY. |
| cloud.searchC | Full-text search across all cloud content. Requires MODELBOUND_API_KEY. |
| cloud.installMarketplaceSkillB | Install a public marketplace skill into your library. Requires MODELBOUND_API_KEY. |
| optimization.healthA | Get token health scores and staleness for your context library. Requires MODELBOUND_API_KEY. |
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 15 tools
Tools are clearly separated into namespaces (cloud, ide, optimization, skills) with distinct actions. No two tools overlap in purpose; each targets a specific operation (e.g., install vs. list vs. pull).
All tool names follow consistent camelCase with a namespace.verb convention (e.g., cloud.installMarketplaceSkill, skills.convert). No mixing of snake_case or other patterns.
15 tools cover cloud operations (6), local skill management (7), IDE detection (1), and optimization (1). This is well-scoped for a skill management server without being overwhelming.
Covers core CRUD for both cloud and local skills, plus conversion, linting, validation, and health. Missing explicit delete operations for cloud or local skills, but the main workflows are well-served.