linkml-mcp
linkml-mcp
LinkML YAML 스키마를 커밋 기준으로 편집하는 MCP 서버입니다.
프로젝트 범위와 마일스톤 경계는 SCOPE.md를 참조하세요.
설치
uv sync --devRelated MCP server: github-mcp-tool
MCP 서버 실행
로컬 편집기/Codex 테스트의 경우 현재 권장되는 전송 방식은 HTTP입니다:
uv run linkml-mcp --transport http --host 127.0.0.1 --port 8765호스트 이름이나 리버스 프록시를 통해 요청을 받으려면 localhost를 벗어나 바인딩하고 외부 Host 헤더를 허용하세요:
uv run linkml-mcp \
--transport http \
--host 0.0.0.0 \
--port 8765 \
--allowed-host essentialcomplexity.eu프록시가 다른 Host 헤더를 전달하는 경우, 해당 값을 추가 --allowed-host로 전달하세요.
다음 MCP 구성을 사용하세요:
{
"servers": {
"linkml-server": {
"type": "http",
"url": "http://127.0.0.1:8765/mcp"
}
},
"inputs": []
}Stdio도 사용할 수 있습니다:
uv run linkml-mcp서버는 기본적으로 작업 공간을 .linkml-mcp/workspaces 아래에 저장합니다. 이를 재정의하려면:
export LINKML_MCP_WORKSPACE_ROOT=/path/to/workspaces
export LINKML_MCP_GENERATOR_OUTPUT_ROOT=/path/to/generated테스트 클라이언트
워크스페이스 생성:
uv run linkml-mcp-client init --name test_schema시맨틱 변경셋 적용:
uv run linkml-mcp-client apply-change \
--workspace-id ws_... \
--base-commit abc123 \
--changes-json examples/add_person.json \
--message "Add Person"커밋 시점의 스키마 읽기:
uv run linkml-mcp-client read-schema \
--workspace-id ws_... \
--commit-id def456테스트 실행:
uv run pytestMaintenance
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
- AlicenseBqualityBmaintenanceEnables MCP clients to manage Overleaf projects via Git sync, including listing, reading, writing, and syncing files.446MIT
- FlicenseNot gradedqualityDmaintenanceEnables managing GitHub repositories, files, and user information through MCP, with support for creating, updating, and deleting repository contents, as well as fetching user profiles.1
- AlicenseAqualityAmaintenanceRepository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.6302MIT
- AlicenseNot gradedqualityAmaintenanceProvides MCP tools that give AI agents persistent, append-only memory in a git repository, letting them record observations, decisions, and corrections while retrieving context briefs, current facts, conflicts, and traceable event history without a vector database.MIT
Related MCP Connectors
Turn a GitHub repo or docs site into agent-ready context: pack it or search it, over MCP.
A MCP server built for developers enabling Git based project management with project and personal…
Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current.
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/sandervd/linkml-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server