Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

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

CapabilityDetails
tools
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
skill_searchA

按任务检索 skill:混合检索(BM25 + 向量 + RRF)+ 五维任务适配打分,返回带理由的候选列表。先做这个再动手。

skill_inspectC

查看 skill 的 manifest、依赖树与权限清单(不含正文,成本低)。

skill_getC

获取 skill 的完整包:manifest + SKILL.md 正文 + 文件清单 + 已解析依赖(渐进披露的正文环节)。

skill_planC

把任务规划成 skill 组合的 workflow DAG(分解-检索-组合;无 LLM 时用能力闭包图搜索)。

skill_runA

在权限沙箱中执行单个 skill。权限不足时返回 requiresApproval(两段式 HITL,approveAsks: true 授权后重试)。

workflow_runB

执行 skill_plan 产出的 DAG:拓扑序数据流、重试、检查点、整链授权。

skill_feedbackA

报告执行结果与评分,驱动 bandit/Elo 排名与备选检索(学习闭环;会覆盖同一次 skill_run 的自动记账,不重复计数)。

skill_registerA

注册或升级 skill(append-only;v3:trust 模式需 Ed25519 签名,gate 模式下升级需自带 tests 过沙箱)。

skill_statsA

查看 skill 的评价指标:成功率(Wilson)、Elo、质量分、延迟成本,以及挖掘出的 workflow recipe。

Prompts

Interactive templates invoked by user choice

NameDescription
skill-briefing启动引导:给定任务,提示 agent 先检索技能再动手

Resources

Contextual data attached and managed by the client

NameDescription
skill catalog全部 skill 的轻量索引
workflow recipes从执行日志挖掘的高频成功组合

Latest Blog Posts

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/2428424081cn/Skill-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server