mcp_skill_provider
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp_skill_providersearch skills for load testing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp_skill_provider
MCP skill provider — search, retrieve, and execute commands for Harness Engineering skills.
mcp_skill_provider is a standalone MCP module registered with mcp_daemon_engine. It exposes three tools to agents:
search_skills(query, limit?)— lexical search over the skill catalogget_skill(name)— retrieve full skill instructions from Harness Engineeringrun_command(name, argv, workspace_scope?)— execute an allowlisted command for a skill
Installation
pip install -e .Related MCP server: Harness MCP Server
Configuration
Set the Harness Engineering GraphQL endpoint via environment variable:
HSK_GRAPHQL_ENDPOINT=http://localhost:8000/graphqlUsage with mcp_daemon_engine
Register the module through mcp_daemon_engine's loadMcpConfiguration mutation. mcp_configuration.py already declares the tools, modules, and module_links blocks the daemon needs — it points every tool at:
{
"module_name": "mcp_skill_provider",
"class_name": "mcp_skill_provider.mcp_skill_provider.MCPSkillProvider",
"package_name": "mcp_skill_provider",
"source": ""
}source: "" means the package must be importable from the daemon's sys.path (e.g. pip install -e .); it is not fetched from S3. Real GraphQL endpoint/credential values are supplied at registration time via loadMcpConfiguration's variables argument, which overrides the placeholder setting.graphql_modules values in the manifest.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to discover, install, and manage SKILL.md skills from a Git-backed registry via MCP tools for search, install, and list operations.51MIT
- AlicenseAqualityFmaintenanceProvides AI agents full access to the Harness.io platform through 10 consolidated tools and 137 resource types, enabling management of CI/CD, GitOps, Feature Flags, cost data, and more.113,6268Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables coding agents to search, recommend, and validate a stack of reusable skills from a local catalog, producing deterministic plans without modifying the project.8,4261MIT
- AlicenseAqualityBmaintenanceEnables AI agents to autonomously search, evaluate, and install skills from the skills.sh catalog.2413ISC
Related MCP Connectors
Search your team's shared AI-skill library, get install commands, and save skills from your agent.
Search harness engineering, agentic AI patterns, architectures, governance and agent taxonomy.
Agent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ideabosque/mcp_skill_provider'
If you have feedback or need assistance with the MCP directory API, please join our Discord server