elevanaltd/hestai-mcp/mcp-tools
Claude Code and agent skill by elevanaltd/hestai-mcp
- community
Checking that the SKILL.md file is still in the repository.
MCP tool implementation patterns for HestAI including tool structure, session tools, and shared utilities
Install
npx vskill@latest install elevanaltd/hestai-mcp/mcp-toolsSKILL.md
===MCP_TOOLS=== META: TYPE::SKILL VERSION::"1.0" STATUS::ACTIVE PURPOSE::"MCP tool implementation patterns for HestAI" DOMAIN::HEPHAESTUS[tool_crafting]⊕HERMES[communication]
§1::TOOL_STRUCTURE LOCATION::src/hestai_mcp/mcp/tools/ RETURN_TYPE::dict[str,Any] PATTERN::[ "async def my_tool_async(", " required_param: str,", " optional_param: str | None = None,", ") -> dict[str, Any]:", " \"\"\"Tool description.\"\"\"", " # Validate inputs first", " validated = validate_param(required_param)", " # Implementation", " return {\"status\": \"success\", \"data\": result}" ]
§2::SESSION_TOOLS CLOCK_IN::[ PURPOSE::"Start session, returns context paths + AI synthesis", PARAMS::[role,working_dir,focus?,model?], RETURNS::[session_id,context_paths,ai_synthesis] ] CLOCK_OUT::[ PURPOSE::"Archive session transcript to OCTAVE", PARAMS::[session_id,description?], RETURNS::[archive_path,learnings] ] BIND::[ PURPOSE::"Bootstrap agent binding with low token usage", PARAMS::[role,topic?,tier?,working_dir?], RETURNS::[agent_file,skills,context_paths] ]
§3::KEY_DIRECTORIES CONTEXT::.hestai/state/context/["Living context files (PROJECT-CONTEXT, etc.)"] ACTIVE::.hestai/state/sessions/active/["Current session data (gitignored)"] ARCHIVE::.hestai/state/sessions/archive/["Compressed session archives"] NORTH_STAR::.hestai/north-star/["North Star and specs (committed, PR-controlled)"]
§4::SHARED_UTILITIES LOCATION::src/hestai_mcp/mcp/tools/shared/ MODULES::[ path_resolution.py::"Path validation and traversal prevention", security.py::"Input sanitization", fast_layer.py::"Git state and branch detection", compression.py::"OCTAVE compression helpers" ]
§5::SECURITY PATH_VALIDATION::prevent_traversal[../,symlinks] INPUT_SANITIZATION::validate_before_use ROLE_VALIDATION::allowlist_pattern["^[a-z][a-z0-9-]*$"]
§6::ASYNC_PATTERNS REQUIREMENT::all_MCP_tools_must_be_async AI_INTEGRATION::AIClient.complete_text()[optional_synthesis] ERROR_HANDLING::graceful_fallback_on_failure
===END===
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsrc/hestai_mcp/_bundled_hub/library/skills/mcp-tools/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/elevanaltd/hestai-mcp/mcp-tools)