@kud/mcp-harness-fme
Enables reading and toggling feature flags, managing environments, segments, and change requests for Harness FME (Split.io).
README
<div align="center">
MCP server for Harness FME (Split.io) — read and toggle feature flags.
<a href="https://kud.io/projects/mcp-harness-fme">Website</a> · <a href="https://kud.io/projects/mcp-harness-fme/docs">Documentation</a>
</div>
Features
- 28 tools — covers workspaces, environments, feature flags, flag definitions, segments, rule-based segments, and change requests.
- Kill & restore — instantly kill a flag to force all traffic to the default treatment, or restore it with a single tool call.
- Safety guard — every destructive operation (delete, kill, archive, disable) requires
confirm: true, preventing accidental changes. - Rule-based segments — create, update, enable, disable, and submit change requests for rule-based segments per environment.
- Change request flow — submit segment definition changes with optional approvers for teams that require approval gates.
- Zero-config startup — reads
MCP_HARNESS_FME_API_KEYfrom the environment and exits immediately if it is missing.
Install
Add to your MCP client config (see Usage below), or install globally to run manually:
npx --yes @kud/mcp-harness-fme@latest
Set the environment variable MCP_HARNESS_FME_API_KEY to your Harness FME API key before starting the server.
Usage
Claude Desktop / Claude Code
{
"mcpServers": {
"harness-fme": {
"command": "npx",
"args": ["--yes", "@kud/mcp-harness-fme@latest"],
"env": {
"MCP_HARNESS_FME_API_KEY": "your_api_key"
}
}
}
}
For Claude Code, add via the CLI:
claude mcp add --transport stdio --scope user harness-fme \
--env MCP_HARNESS_FME_API_KEY=your_api_key \
-- npx --yes @kud/mcp-harness-fme@latest
Available tools
| Tool | Description |
|---|---|
list_workspaces |
List all FME workspaces in the account |
list_environments |
List all environments in a workspace |
list_traffic_types |
List all traffic types in a workspace |
list_rollout_statuses |
List rollout status definitions for a workspace |
list_feature_flags |
List feature flags in a workspace (filter by tag, status, name) |
get_feature_flag |
Get metadata for a specific feature flag |
create_feature_flag |
Create a new feature flag for a given traffic type |
update_feature_flag |
Update a flag's description, tags, owners, or rollout status |
delete_feature_flag |
Permanently delete a feature flag (confirm: true required) |
archive_feature_flag |
Archive a flag, removing it from active use (confirm: true required) |
unarchive_feature_flag |
Restore a previously archived feature flag |
kill_feature_flag |
Kill a flag in an environment — forces default treatment (confirm: true required) |
restore_feature_flag |
Restore a killed feature flag in an environment |
list_flag_definitions |
List flag targeting rules in an environment |
get_flag_definition |
Get treatments and targeting rules for a flag in an environment |
create_flag_definition |
Activate a flag in an environment with treatments and targeting rules |
update_flag_definition |
Fully replace a flag's targeting rules in an environment |
delete_flag_definition |
Remove a flag's targeting rules from an environment (confirm: true required) |
list_segments |
List all segments in a workspace |
list_rule_based_segments |
List all rule-based segments in a workspace |
get_rule_based_segment |
Get a rule-based segment's workspace-level metadata |
create_rule_based_segment |
Create a new rule-based segment in a workspace |
delete_rule_based_segment |
Permanently delete a rule-based segment (confirm: true required) |
list_rule_based_segment_definitions |
List rule-based segment definitions in an environment |
update_rule_based_segment_definition |
Update a rule-based segment's rules in an environment |
enable_rule_based_segment_definition |
Activate a rule-based segment in an environment |
disable_rule_based_segment_definition |
Remove a rule-based segment from an environment (confirm: true required) |
create_rule_based_segment_change_request |
Submit a change request for a segment definition with optional approval flow |
Development
git clone https://github.com/kud/mcp-harness-fme.git
cd mcp-harness-fme
npm install
npm run dev # run from source with tsx
npm run inspect:dev # MCP Inspector at http://localhost:5173
npm test # vitest
npm run build # compile to dist/
The server reads MCP_HARNESS_FME_API_KEY at startup and exits immediately if it is absent. All tools are defined in src/index.ts.
📚 Full documentation → mcp-harness-fme/docs
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。