New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Knowledge Extension Ecosystem MCP Protocol Runtime

by echoVic in echoVic/blade-code

覆盖 Session 私有 MCP transport、动态工具与内容目录、Roots、Sampling、Elicitation、 Completion、Logging、OAuth、异步 Tasks、结果制品和故障恢复。进入条件：新增 MCP 能力、调试连接或目录变化、处理不可信协议数据、修改 MCP 工具投影或跨端事件。

MITAuto-check passedAgent Workflows

Install Knowledge Extension Ecosystem MCP Protocol Runtime

skills CLI
$ npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem-mcp-protocol-runtime -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install echoVic/blade-code knowledge-extension-ecosystem-mcp-protocol-runtime --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/echoVic/blade-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.trae/knowledges/extension-ecosystem/mcp-protocol-runtime .claude/skills/knowledge-extension-ecosystem-mcp-protocol-runtime && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
knowledge-extension-ecosystem-mcp-protocol-runtime
GitHub stars
180
Token cost
~2.1k tokens
SKILL.md length
502 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

覆盖 Session 私有 MCP transport、动态工具与内容目录、Roots、Sampling、Elicitation、 Completion、Logging、OAuth、异步 Tasks、结果制品和故障恢复。进入条件：新增 MCP 能力、调试连接或目录变化、处理不可信协议数据、修改 MCP 工具投影或跨端事件。

  • Tasks that involve MCP servers
  • SKILL.md covers Module Structure, Gotchas, Architecture and Decisions, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve OAuth and OpenID Connect

What it does

Knowledge Extension Ecosystem MCP Protocol Runtime is an agent skill from echoVic/blade-code. 覆盖 Session 私有 MCP transport、动态工具与内容目录、Roots、Sampling、Elicitation、 Completion、Logging、OAuth、异步 Tasks、结果制品和故障恢复。进入条件：新增 MCP 能力、调试连接或目录变化、处理不可信协议数据、修改 MCP 工具投影或跨端事件。 不包含：通用工具准入与调度（见 ../../tool-and-automation-platform/）、插件安装和 来源策略（见 ../plugin-lifecycle-and-marketplace/）。关键词：McpClient、 McpRegistry、mcp、tools/listchanged、elicitation、sampling、OAuth、MCP Tasks。

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers and OAuth and OpenID Connect. It works with Model Context Protocol. The repository describes itself as: AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers
  • Tasks that involve OAuth and OpenID Connect

Example prompts

  • “/knowledge-extension-ecosystem-mcp-protocol-runtime”

What it can do on your machine

Read from SKILL.md and the folder at commit 30f8684. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Knowledge Extension Ecosystem MCP Protocol Runtime loads about 2.1k tokens when it runs. Until then it costs about 102 tokens; SKILL.md has 502 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from echoVic/blade-code at commit 30f8684, republished under its MIT licence (© echoVic). 502 words, ~2,102 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-extension-ecosystem-mcp-protocol-runtime/SKILL.md (or your agent's skills folder).
name
knowledge-extension-ecosystem-mcp-protocol-runtime
description
覆盖 Session 私有 MCP transport、动态工具与内容目录、Roots、Sampling、Elicitation、 Completion、Logging、OAuth、异步 Tasks、结果制品和故障恢复。进入条件：新增 MCP 能力、调试连接或目录变化、处理不可信协议数据、修改 MCP 工具投影或跨端事件。 不包含：通用工具准入与调度（见 ../../tool-and-automation-platform/）、插件安装和 来源策略（见 ../plugin-lifecycle-and-marketplace/）。关键词：McpClient、 McpRegistry、mcp__、tools/list_changed、elicitation、sampling、OAuth、MCP Tasks。

Module Structure

MCP 运行时由每个 SessionRuntime 独占：配置先按 source project 合并，Registry 管理 多个 client 的安全投影，动态工具和内容能力再进入该 Session 的 ToolRegistry 与事件流。

Directory Layout
  • packages/cli/src/mcp/ — client、registry、目录、交互、恢复、日志、任务与结果归一化
  • packages/cli/src/mcp/auth/ — OAuth 策略、回调 provider 与凭据账本
  • packages/cli/src/tools/builtin/mcp/ — Resources、Prompts、Completion 与 Tasks 工具适配
  • packages/cli/src/commands/mcp.ts — 进程外 MCP 管理命令
  • packages/cli/src/server/routes/mcp.ts — 当前 Web Session 的 MCP 管理 API
  • packages/cli/src/slash-commands/mcp.ts — 活动 TUI/ACP Session 的 MCP 命令
  • packages/cli/web/src/components/mcp/ — Web MCP 状态与操作面板
Key Entry Points
  • resolveWorkspaceMcpConfig() in packages/cli/src/mcp/resolveWorkspaceMcpConfig.ts — 合并并规范化单个 Session 的 MCP 配置
  • McpRegistry.createIsolated() in packages/cli/src/mcp/McpRegistry.ts — 创建 Session 独占 Registry
  • McpClient.connect() and McpClient.callTool() in packages/cli/src/mcp/McpClient.ts — 建连、能力协商与工具调用
  • createMcpTool() in packages/cli/src/mcp/createMcpTool.ts — 将协议工具映射为 Blade Tool
  • SessionRuntime.registerMcpTools() in packages/cli/src/agent/runtime/SessionRuntime.ts — 注册动态目录、内容工具和事件监听

Gotchas

  • MCP 配置覆盖顺序是 workspace → plugin →显式 Session → CLI，strictCliConfig 会跳过前三类来源；相对 stdio cwd 始终按 source project 解析而不是 task worktree(packages/cli/src/mcp/resolveWorkspaceMcpConfig.ts)
  • --mcp-config 的单个非法文件或 JSON 只记录 warning 并跳过，后续参数仍继续覆盖；调用方不能假设解析失败会使 Session 创建失败(packages/cli/src/mcp/loadMcpConfig.ts)
  • McpRegistry.registerServer() 默认吞掉初始连接异常并保留 ERROR server，Session 可继续启动；需要通过状态或显式 reconnect 区分“已注册”与“已连接”(packages/cli/src/mcp/McpRegistry.ts)
  • 同一 client 同时只允许一个交互式工具调用或 task 创建，因为 Elicitation/Sampling 缺少可靠的父调用关联；并发重叠会在发请求前拒绝(packages/cli/src/mcp/McpClient.ts)
  • transport 进入恢复前会立即撤销旧 tools、resources、prompts 和 instructions；持有旧 Tool 对象或旧 catalog identity 重试会命中死亡 connection generation(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpRegistry.ts)
  • list_changed 通知只登记有界合并刷新，完整新目录全部校验成功后才替换；notification 刷新失败保留上一有效目录，而手动刷新会把错误返回调用方(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpToolCatalog.ts)
  • Resource subscription 分为 desired 与 active：异常断连只清 active 并在新目录确认 URI 后恢复，手动 disconnect、unsubscribe 或 Session dispose 才清 desired(packages/cli/src/mcp/McpClient.ts)
  • MCP Tasks 默认关闭；taskSupport=required 的动态工具会自动后台化，optional 仍以前台调用为默认，只有显式 StartMcpTask 才进入 task 路径(packages/cli/src/mcp/createMcpTool.ts, packages/cli/src/mcp/McpTasks.ts)
  • 模型和用户只能看到 Blade 生成的 mcp_task_*，原始 server task ID 必须留在 manager 内部；ownership 同时校验 Session ID 与 canonical execution workspace(packages/cli/src/mcp/McpTaskManager.ts, packages/cli/src/tools/builtin/mcp/mcpTaskTools.ts)
  • 二进制结果绝不能把 base64 直接注入模型；大文本超过 inline budget 后写 Session 私有 artifact，写入失败也只能返回 hash/size/omitted 元数据(packages/cli/src/mcp/McpToolResult.ts, packages/cli/src/mcp/McpToolArtifactStore.ts)
  • MCP 日志是用户诊断事件而非模型输入，server instructions 才会以明确标注“不可信外部文档”的 scoped reminder 进入 provider boundary；二者不能共用注入路径(packages/cli/src/mcp/McpLogging.ts, packages/cli/src/mcp/McpServerInstructions.ts)

Architecture

  • 每个 Session 创建独立 McpRegistry、client、目录 revision 和 artifact writer，进程级 Store 仅用于启动表面的配置投影，不能作为运行时连接来源(packages/cli/src/agent/runtime/SessionRuntime.ts, packages/cli/src/mcp/McpRegistry.ts, git:6d712a03)
  • 动态工具身份固定为 mcp__<server>__<tool>；不安全或过长片段经 NFKC 与摘要后缀规范化，避免 server 同名工具覆盖彼此或覆盖内置工具(packages/cli/src/mcp/McpToolCatalog.ts)
  • Agent 发起下一次 provider 请求前等待 catalog barrier，随后把完整 MCP 投影一次替换到基础 registry 和每个 executor，并重新应用 whitelist/blacklist(packages/cli/src/agent/runtime/SessionRuntime.ts, packages/cli/src/tools/registry/ToolRegistry.ts)
  • 工具调用同时受父 AbortSignal、idle timeout 和 hard total timeout 约束；合法 progress 刷新 idle timeout，但不能延长 hard timeout，也不会写入 durable transcript(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpCallLifecycle.ts)
  • Resources、templates 和 prompts 使用独立 revision 与 delta；资源与模板同批获取后提交，读取和 prompt 解析只接受当前 catalog 已声明的 identity(packages/cli/src/mcp/McpContentCatalog.ts, packages/cli/src/mcp/McpClient.ts)
  • Elicitation 在展示前和回传前分别经过 Hooks，最终响应仍按原始 requested schema 校验；没有交互面、取消、超时或异常统一收敛为 cancel/decline(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpElicitation.ts)
  • Sampling 使用当前 Session 冻结模型，按每次请求重新审批，并拒绝 tools、context 扩展、task sampling 和并发 nested request(packages/cli/src/mcp/McpSampling.ts, packages/cli/src/mcp/McpClient.ts)
  • 异步 Task watcher 在 transport 不可用时进入 interrupted 并等待同一 client 恢复；恢复后必须验证原始 task ID 与 createdAt 未变化才继续取状态或结果(packages/cli/src/mcp/McpTaskManager.ts, packages/cli/src/mcp/McpTasks.ts)
Show full SKILL.md (195 more words)Show less

Decisions

  • MCP 全协议生命周期在一次集中改造中引入，并将目录、内容、交互、日志、任务和 OAuth 都纳入 Session 隔离，而不是继续扩展进程全局 registry(packages/cli/src/mcp/McpRegistry.ts, packages/cli/src/mcp/McpClient.ts, git:7894b6e6)
  • Sampling 和 Tasks 均选择默认关闭、按 server 显式启用，因为二者会分别产生额外模型调用和后台生命周期，不能从普通工具授权隐式继承(packages/cli/src/mcp/McpSampling.ts, packages/cli/src/mcp/McpTasks.ts)
  • Completion 被建模为只读候选数据而非控制消息，必须先绑定当前 catalog 中的 prompt 参数或 URI template variable，再做字符和结果预算归一化(packages/cli/src/mcp/McpCompletion.ts)
  • tool result 与 MCP content 都采用“文本有界保留、二进制只给 provenance”的策略，避免协议返回绕过模型上下文预算和 Web 事件 allowlist(packages/cli/src/mcp/McpToolResult.ts, packages/cli/src/mcp/McpContentCatalog.ts)
  • MCP artifact 后续迁移到共享的私有 Session 存储实现，新增结果类型应复用该存储而不是另建可见目录(packages/cli/src/mcp/McpToolArtifactStore.ts, git:4553d089)

Patterns

  • 所有会跨异步边界返回的协议对象先 structuredClone 或重新归一化，事件再附加单调 revision，防止 listener 修改 Registry 内部状态(packages/cli/src/mcp/McpRegistry.ts)
  • 目录分页统一限制页数、条目数、重复 cursor、identity 和总字节；超限按整个目录失败处理，不提交部分目录(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpToolCatalog.ts, packages/cli/src/mcp/McpContentCatalog.ts)
  • 恢复、Completion、Tasks 和 resource subscription 都捕获当前 client/generation，异步结果返回时发现 client 已变化就拒绝，避免旧 transport 的迟到结果污染新连接(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpConnectionRecovery.ts)

Dependencies

  • MCP transport、schema 和实验性 Tasks 依赖 @modelcontextprotocol/sdk；Blade 在 SDK 校验后仍执行自己的目录、结果、Unicode 和生命周期边界(packages/cli/src/mcp/McpClient.ts, packages/cli/package.json)
  • 动态 MCP 工具复用 Blade 的 TypeBox Tool contract、权限确认、进度事件和 SessionArtifactStore，因此协议层修改必须同时检查 ToolRegistry 与 SessionRuntime 投影(packages/cli/src/mcp/createMcpTool.ts, packages/cli/src/mcp/McpToolArtifactStore.ts)

Security Considerations

  • OAuth 只允许 HTTPS，loopback 可用 HTTP；禁止 URL credentials、手写 Authorization header 和旧式 secret/endpoint 字段，网络请求不跟随 redirect(packages/cli/src/mcp/auth/McpOAuthPolicy.ts)
  • OAuth 凭据身份由 endpoint、client ID 和排序 scopes 哈希生成，账本与锁文件必须是当前用户拥有的普通 0600 文件，写入使用进程内 mutex、跨进程排他锁和原子替换(packages/cli/src/mcp/auth/OAuthTokenStorage.ts)
  • ACP Session 不读取宿主 OAuth 凭据、不暴露本地 roots 或 artifact path，也不向模型投影 server instruction/log 正文(packages/cli/src/agent/runtime/SessionRuntime.ts, docs/reference/mcp-session-isolation.md)
  • Form Elicitation 拒绝原型污染字段、额外属性和不安全数字；URL Elicitation 只接受无凭据的 HTTP(S) URL，敏感数据应留在外部 URL 流程(packages/cli/src/mcp/McpElicitation.ts)
  • Prompt 与 Completion 参数必须来自当前 catalog 声明，未知参数、缺失 required 参数和 __proto__/constructor/prototype 在协议请求前拒绝(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpCompletion.ts)
  • 连接错误、Task status/error 与工具错误分别执行 URL、Bearer、API key、控制字符和 UTF-8 字节上限清理，不能把 transport 文本直接用作模型指令(packages/cli/src/mcp/McpConnectionRecovery.ts, packages/cli/src/mcp/McpTasks.ts, packages/cli/src/mcp/McpToolResult.ts)

Error Handling & Recovery

  • 自动恢复是 single-flight generation 状态机；手动 disconnect 或 dispose 会提升 generation、取消连接和退避，旧 close/error 回调不能覆盖新状态(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/McpConnectionRecovery.ts)
  • 只有 session-not-found、连续终端 transport 错误和健康检查阈值进入恢复；普通协议校验错误不会触发重连风暴(packages/cli/src/mcp/McpClient.ts, packages/cli/src/mcp/HealthMonitor.ts)
  • Session dispose 先取消当前 Session 的 MCP Tasks，再解除 Registry listener 并断开全部 client，防止终态事件写入已释放的执行器目录(packages/cli/src/agent/runtime/SessionRuntime.ts, packages/cli/src/mcp/McpTaskManager.ts)

© echoVic, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .trae/knowledges/extension-ecosystem/mcp-protocol-runtime of echoVic/blade-code.

Open the folder on GitHubat commit 30f8684

Compare with similar skills

Knowledge Extension Ecosystem MCP Protocol Runtime next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Knowledge Extension Ecosystem MCP Protocol Runtime compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Extension Ecosystem MCP Protocol Runtime this skillechoVic/blade-code180—~2.1kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Cao MCP Appsawslabs/cli-agent-orchestrator1.4k—~1.9kAutomated safety check: PassApache-2.0
Building MCP Server On CloudflareCommandCodeAI/agent-skills132—~1.5kAutomated safety check: PassMIT
Nuxt Agent Ready Best Practicesvinayakkulkarni/nxui212—~2.4kAutomated safety check: PassMIT
Nv Onboard Dcr MCPnovuhq/novu40k—~1.8kAutomated safety check: PassCustom licence

Similar skills

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Cao MCP Apps

    awslabs/cli-agent-orchestrator

    Official

    Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).

    1.4k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Building MCP Server On Cloudflare

    CommandCodeAI/agent-skills

    Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment.

    132 GitHub stars~1.5k tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed

  • Nuxt Agent Ready Best Practices

    vinayakkulkarni/nxui

    Nuxt agent-readiness guidelines for making a site operable by autonomous AI agents — not just cited by them.

    212 GitHub stars~2.4k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Nv Onboard Dcr MCP

    novuhq/novu

    Onboard a new DCR OAuth MCP catalog entry with provider-doc vetting and curl probes.

    40k GitHub stars~1.8k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Agent Tools

    VectorSpaceLab/AREX-Skill

    A skill your agent uses when configuring LiteLLM for MCP tools, A2A agents, Claude Code/Cursor agent gateway traffic, MCP auth/OAuth, tool permissions, semantic filtering, or agent-specific proxy…

    328 GitHub stars~1.2k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from echoVic/blade-code

All 38 skills in this repo

  • Base64 Parser

    echoVic/blade-code

    Base64 编解码工具，支持编码/解码文本、JSON、二进制文件，自动检测格式，支持批量处理. An agent skill from echoVic/blade-code.

    180 GitHub stars~545 tokensUpdated 10 days ago
    Auto-check: notes

  • Code Review

    echoVic/blade-code

    Review frontend code for best practices, bugs, and improvements.

    180 GitHub stars~377 tokensUpdated 10 days ago
    Auto-check: notes

  • GitHub Explorer

    echoVic/blade-code

    Explore and summarize popular GitHub projects. An agent skill from echoVic/blade-code.

    180 GitHub stars~434 tokensUpdated 10 days ago
    Auto-check passed

  • Knowledge Extension Ecosystem Lsp Code Intelligence

    echoVic/blade-code

    覆盖 Session 级 LSP 配置快照、stdio 进程、文档同步、语义查询、诊断回注、崩溃恢复 和子 Session 继承。进入条件：新增语言服务器、修改 LSP 工具、排查诊断缺失/重复、 处理 worktree 或 ACP 差异、修复进程泄漏或 transport 代际问题。不包含：VS Code 扩展桥接（见…

    180 GitHub stars~1.9k tokensUpdated 10 days ago
    Auto-check passed

  • Knowledge Extension Ecosystem Skills And Custom Commands

    echoVic/blade-code

    覆盖 SkillRegistry、SKILL.md 延迟加载、自定义命令 Markdown 解析、来源覆盖、插件 命名空间、Session 快照和模型/用户调用入口。进入条件：新增 Skill 或命令字段、调整 发现优先级、调试 /command 或 Skill 工具、修改 Prompt 元数据或消费者集成。不包含： 插件安装生命周期（见…

    180 GitHub stars~2.1k tokensUpdated 10 days ago
    Auto-check passed

  • Knowledge Integration And Workflow Tool Adapters

    echoVic/blade-code

    Covers 领域能力如何包装成内置工具、getBuiltinTools 的 Session 依赖注入、ToolSearch 延迟激活，以及 Goal/Task/Team/Plan/Skill/LSP/MCP/Web/Config/Worktree 适配边界。

    180 GitHub stars~2.1k tokensUpdated 10 days ago
    Auto-check passed

Works with

Categories

Questions about Knowledge Extension Ecosystem MCP Protocol Runtime

What does Knowledge Extension Ecosystem MCP Protocol Runtime do?

覆盖 Session 私有 MCP transport、动态工具与内容目录、Roots、Sampling、Elicitation、 Completion、Logging、OAuth、异步 Tasks、结果制品和故障恢复。进入条件：新增 MCP 能力、调试连接或目录变化、处理不可信协议数据、修改 MCP 工具投影或跨端事件。. Knowledge Extension Ecosystem MCP Protocol Runtime is an agent skill from echoVic/blade-code.

When should I use Knowledge Extension Ecosystem MCP Protocol Runtime?

Knowledge Extension Ecosystem MCP Protocol Runtime fits situations like: tasks that involve MCP servers; tasks that involve OAuth and OpenID Connect.

How do I install Knowledge Extension Ecosystem MCP Protocol Runtime in Claude Code?

Run `npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem-mcp-protocol-runtime -a claude-code`. Or copy the skill folder (.trae/knowledges/extension-ecosystem/mcp-protocol-runtime in echoVic/blade-code) into .claude/skills/knowledge-extension-ecosystem-mcp-protocol-runtime in your project. Claude Code loads it when a task matches its description.

How do I install Knowledge Extension Ecosystem MCP Protocol Runtime in Codex?

Run `npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem-mcp-protocol-runtime -a codex`. Or copy the skill folder (.trae/knowledges/extension-ecosystem/mcp-protocol-runtime in echoVic/blade-code) into .agents/skills/knowledge-extension-ecosystem-mcp-protocol-runtime in your project. Codex loads it when a task matches its description.

Can I use Knowledge Extension Ecosystem MCP Protocol Runtime in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add echoVic/blade-code --skill knowledge-extension-ecosystem-mcp-protocol-runtime -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/knowledge-extension-ecosystem-mcp-protocol-runtime, .gemini/skills/knowledge-extension-ecosystem-mcp-protocol-runtime, .github/skills/knowledge-extension-ecosystem-mcp-protocol-runtime and .opencode/skills/knowledge-extension-ecosystem-mcp-protocol-runtime in your project.

What does Knowledge Extension Ecosystem MCP Protocol Runtime need to run?

SKILL.md names no scripts, command-line tools or credentials: Knowledge Extension Ecosystem MCP Protocol Runtime is instructions for the agent only.

Does Knowledge Extension Ecosystem MCP Protocol Runtime access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Knowledge Extension Ecosystem MCP Protocol Runtime safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Knowledge Extension Ecosystem MCP Protocol Runtime use?

Knowledge Extension Ecosystem MCP Protocol Runtime is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Knowledge Extension Ecosystem MCP Protocol Runtime use?

About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Knowledge Extension Ecosystem MCP Protocol Runtime?

Skills that share tags, products or a category with Knowledge Extension Ecosystem MCP Protocol Runtime: MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars), Cao MCP Apps (awslabs/cli-agent-orchestrator, 1.4k stars), Building MCP Server On Cloudflare (CommandCodeAI/agent-skills, 132 stars) and Nuxt Agent Ready Best Practices (vinayakkulkarni/nxui, 212 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Extension Ecosystem MCP Protocol Runtime?

echoVic (a GitHub user) maintains it in echoVic/blade-code, which has 180 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on September 27, 2026.

Source: echoVic/blade-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.