mcp server

AgentPlaybooks

Manage portable AI agent playbooks, Agent Skills, MCP configurations, personas, and memory.

Description as published by the maintainer. Source

• version 1.0.0
• active
• memory and context

active — Most recent push to the repository was 2026-08-03. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

47 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

archive_memories(keys, tags, from_tier, playbook_id, older_than_hours, generate_summaries)

Archive memories from working/contextual to longterm tier. Useful for cleaning up after completing tasks. Target a playbook with playbook_id. Required: playbook_id.

call_connected_tool(arguments, server_id, tool_name, playbook_id)

Call a tool on one of this playbook's connected MCP servers. This stable wrapper lets the user control plane apply newly created playbooks without dynamically changing its own tool list. Target a playbook with playbook_id. Required: playbook_id, server_id, tool_name.

consolidate_memories(summary, parent_key, memory_keys, parent_tags, playbook_id, archive_children)

Consolidate multiple related memories into a parent memory with summary. Reduces context size while preserving detail access via children. Target a playbook with playbook_id. Required: playbook_id, memory_keys, parent_key, summary.

create_mcp_server(name, tools, resources, description, playbook_id, transport_type, transport_config)

Connect an MCP or OpenAPI server to this playbook. Requires playbooks:write or full permission. Target a playbook with playbook_id. Required: playbook_id, name.

create_persona(name, metadata, playbook_id, system_prompt)

Set the singleton persona (AI identity and system prompt) for a playbook. Backward-compatible alias for updating persona fields. Required: playbook_id, name, system_prompt.

create_playbook(name, tags, visibility, description, instructions, persona_name, persona_metadata, persona_system_prompt)

Create a new playbook. A playbook is a container for personas (AI personalities), skills (capabilities), and memory (persistent storage). Required: name.

create_run(name, context, playbook_id)

Create a workflow run so this playbook can be applied immediately with isolated context and canvas artifacts. Target a playbook with playbook_id. Required: playbook_id, name.

create_skill(name, content, priority, description, playbook_id)

Create a new skill for this playbook. Use this to expand capabilities. Requires full or skills:write permission. Target a playbook with playbook_id. Required: playbook_id, name, content.

create_task_graph(tags, tasks, plan_key, playbook_id, plan_summary)

Create a hierarchical task plan in one call. Creates a parent 'plan' memory with children for each subtask. Use this for complex multi-threaded work that agent swarms can coordinate on. Each subtask gets its own memory node with status tracking. Target a playbook with playbook_id. Required: playbook_id, plan_key, plan_summary, tasks.

delete_mcp_server(server_id, playbook_id)

Disconnect an MCP or OpenAPI server from this playbook. Requires playbooks:write or full permission. Target a playbook with playbook_id. Required: playbook_id, server_id.

delete_memory(key, playbook_id)

Delete a memory entry (requires API key) Target a playbook with playbook_id. Required: playbook_id, key.

delete_persona(persona_id, playbook_id)

Reset the singleton persona to the default assistant. The playbook always retains one logical persona. Required: playbook_id, persona_id.

delete_playbook(playbook_id)

Delete a playbook and all its contents (personas, skills, memory, API keys). This action cannot be undone! Required: playbook_id.

delete_run(run_id, playbook_id)

Delete a workflow run and its isolated canvas artifacts. Target a playbook with playbook_id. Required: playbook_id, run_id.

delete_secret(name, playbook_id)

Permanently delete a secret. Cannot be undone. Requires secrets:write permission. Target a playbook with playbook_id. Required: playbook_id, name.

delete_skill(skill_id, playbook_id)

Delete a skill from this playbook. Requires full or skills:write permission. Target a playbook with playbook_id. Required: playbook_id, skill_id.

get_canvas_toc(slug, run_id, playbook_id)

Get the table of contents for a canvas document. Returns section IDs, headings, and levels for navigation and patch_canvas_section. Target a playbook with playbook_id. Required: playbook_id, run_id, slug.

get_memory_context(max_items, expand_keys, playbook_id, tags_filter, include_tiers)

Get a context-optimized view of memories. Returns full working memory, summaries for contextual, and keys only for longterm. Target a playbook with playbook_id. Required: playbook_id.

get_memory_tree(root_key, max_depth, playbook_id, include_values)

Get hierarchical tree view of memories showing parent-child relationships. Use this to visualize task graphs and track parallel operations. Includes status for each node. Target a playbook with playbook_id. Required: playbook_id.

get_playbook(playbook_id)

Get a playbook with its singleton persona, skills, connected MCP servers, and memory. Required: playbook_id.

get_skill(skill_id, playbook_id)

Get detailed information about a specific skill Target a playbook with playbook_id. Required: playbook_id, skill_id.

list_canvas(run_id, playbook_id)

List canvas documents in a workflow run. Canvas documents are collaborative markdown files that multiple agents can edit in parallel. Target a playbook with playbook_id. Required: playbook_id.

list_mcp_servers(playbook_id)

List the MCP and OpenAPI servers connected to this playbook, including transport metadata and discovered capability counts. Target a playbook with playbook_id. Required: playbook_id.

list_playbooks

List playbooks owned by or shared with the authenticated user, including access role and content counts.

list_runs(playbook_id)

List workflow runs for this playbook. Runs isolate canvas artifacts and execution context. Target a playbook with playbook_id. Required: playbook_id.

list_secrets(category, playbook_id)

List all secret names and metadata in this playbook. Does NOT return values — secret values are never exposed to agents. Requires secrets:read permission. Target a playbook with playbook_id. Required: playbook_id.

list_skill_versions(limit, skill_id, playbook_id)

List historical versions of a skill for auditing or rollback. Target a playbook with playbook_id. Required: playbook_id, skill_id.

list_skills(playbook_id)

List all skills (capabilities/rules) in this playbook Target a playbook with playbook_id. Required: playbook_id.

lock_canvas_section(slug, run_id, locked_by, section_id, playbook_id)

Lock a section for exclusive editing. Prevents other agents from modifying it. Remember to unlock when done. Target a playbook with playbook_id. Required: playbook_id, run_id, slug, section_id, locked_by.

patch_canvas_section(slug, run_id, content, heading, section_id, playbook_id)

Edit a specific section of a canvas document. Parallel-safe: only updates the targeted section. Lock the section first for safety in multi-agent scenarios. Target a playbook with playbook_id. Required: playbook_id, run_id, slug, section_id, content.

promote_memory(key, playbook_id, target_tier, priority_boost)

Promote a memory to a higher tier or boost its priority for active use. Target a playbook with playbook_id. Required: playbook_id, key.

read_canvas(slug, run_id, section_id, playbook_id)

Read a canvas document. Returns full content, sections structure, and metadata. Optionally read a specific section by ID. Target a playbook with playbook_id. Required: playbook_id, run_id, slug.

read_memory(key, playbook_id)

Read a specific memory entry by key. Automatically increments access count. Memory supports 3 tiers: 'working' (active scratch pad), 'contextual' (recent context), 'longterm' (archived). Use 'hierarchical' memory_type for complex task graphs with parallel threads. Target a playbook with playbook_id. Required: playbook_id, key.

rollback_skill(version_id, playbook_id)

Rollback a skill to a previous version. Requires full or skills:write permission. Target a playbook with playbook_id. Required: playbook_id, version_id.

rotate_secret(name, value, playbook_id)

Rotate (update) an existing secret with a new value. The old value is permanently replaced and cannot be recovered. Requires secrets:write permission. Target a playbook with playbook_id. Required: playbook_id, name, value.

search_memory(tags, tier, search, status, memory_type, playbook_id, include_children)

Search memories by text, tags, tier, or type. Returns summaries for large memories. Use tags for categorical search; use tier to focus on active vs archived data; use memory_type to find task graphs. Target a playbook with playbook_id. Required: playbook_id.

store_secret(name, value, category, expires_at, description, playbook_id)

Store a new encrypted secret. The value is encrypted with AES-256-GCM using a per-user derived key and never stored or returned in plaintext. Requires secrets:write permission. Target a playbook with playbook_id. Required: playbook_id, name, value.

unlock_canvas_section(slug, run_id, section_id, playbook_id)

Unlock a previously locked section so other agents can edit it. Target a playbook with playbook_id. Required: playbook_id, run_id, slug, section_id.

update_mcp_server(name, tools, resources, server_id, description, playbook_id, transport_type, transport_config)

Update a connected MCP or OpenAPI server. Requires playbooks:write or full permission. Target a playbook with playbook_id. Required: playbook_id, server_id.

update_persona(name, metadata, persona_id, playbook_id, system_prompt)

Update a persona's name, system prompt, or metadata. Required: playbook_id, persona_id.

update_playbook(name, tags, config, visibility, description, playbook_id, instructions, persona_name, persona_metadata, persona_system_prompt)

Update the persona/system prompt or the project instructions of this playbook. Handle with extreme care! Requires full or playbooks:write permission. Target a playbook with playbook_id. Required: playbook_id.

update_run(name, run_id, status, context, playbook_id)

Update a workflow run's name, status, or context. Target a playbook with playbook_id. Required: playbook_id, run_id.

update_skill(name, content, priority, skill_id, description, playbook_id)

Update an existing skill in this playbook. Requires full or skills:write permission. Target a playbook with playbook_id. Required: playbook_id, skill_id.

update_task_status(key, result, status, summary, playbook_id)

Update the status of a task node in a hierarchical plan. When all children of a parent are 'completed', the parent is auto-updated. Returns the current subtree state. Target a playbook with playbook_id. Required: playbook_id, key, status.

use_secret(url, body, method, timeout_ms, header_name, playbook_id, secret_name, extra_headers, header_prefix)

Make an HTTP request with a secret injected as a header. The secret value is NEVER returned to the agent — it is decrypted and used server-side only. Use this to authenticate API calls without exposing credentials. Example: use_secret({secret_name: 'OPENAI_API_KEY', url: 'https://api.openai.com/v1/models'}) sends GET with 'Authorization: Bearer <key>'. Requires secrets:read permission. Target a playbook with playbook_id. Required: playbook_id, secret_name, url.

write_canvas(name, slug, run_id, content, metadata, playbook_id)

Create or fully replace a canvas document. Markdown headings are auto-parsed into sections for parallel editing. Use patch_canvas_section for partial updates. Target a playbook with playbook_id. Required: playbook_id, run_id, slug, name, content.

write_memory(key, tags, tier, value, status, summary, metadata, priority, parent_key, description, memory_type, playbook_id)

Write a memory entry. Use tier='working' for active tasks, 'contextual' for background context, 'longterm' for completed work. Set memory_type='hierarchical' and parent_key to build task graphs. Use status to track task progress in parallel workflows. Target a playbook with playbook_id. Required: playbook_id, key, value.

Last successful function declaration observed on 2026-08-13. Source: https://agentplaybooks.ai/api/mcp/manage. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://agentplaybooks.ai/api/mcp/manage.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/matebenyovszky/agentplaybooks
• Website — https://agentplaybooks.ai
• Remote endpoint (streamable-http) — https://agentplaybooks.ai/api/mcp/manage

Related, by what their authors tagged them

• com.clauxel.agentskillupdategate/agentskillupdategate-mcp — last commit 2026-05-20, shares agent, skill
  Paid remote MCP for Claude Code skill update gate MCP, structured receipts, audit logs, and reviewer
• 971184676-skill-manager-skill-manager — last commit 2026-06-02, shares skill
  管理所有已安装的 AI 技能(Skills)，支持 Claude Code、OpenClaw、Codex、Trae、Hermes 等多种智能体。在编程/开发任务的计划阶段自动分析项目并推荐技能组合，推荐尽可能简洁且必须基于已有的技能。若现…
• anbeime-skill-agent-team — last commit 2026-08-06, shares skill
  统一管理多智能体角色的团队协作框架，支持智能体动态组合、灵活协作和扩展新角色。智能体本质上是"角色定义"，可以根据任务需求灵活组建团队，实现从会议决策到系统构建的完整能力。智能体角色明确分工：有干活的、有指挥的、有挑毛病的，能实时看到沟通…
• anbeime-skill-agentkit-multimedia-shopping — last commit 2026-08-06, shares skill
  基于ByteDance agentkit-samples多媒体用例的小省导购员数字人带货视频生成技能，整合多模态内容生成能力（图像、视频、音频），支持AI绘画、语音合成、视频生成，与小省导购员人设融合，9:16竖屏适配，直接对接带货视频生…
• anbeime-skill-article-illustrator — last commit 2026-08-06, shares skill
  分析文章内容，在需要视觉辅助理解的位置生成插画。配图可以是信息补充、概念具象化，或引导读者想象。当用户要求"给文章配图"、"为文章生成插图"、"添加配图"时使用此技能。
• anbeime-skill-article-illustrator-079aaf — last commit 2026-08-06, shares skill
  分析文章内容，在需要视觉辅助理解的位置生成插画。配图可以是信息补充、概念具象化，或引导读者想象。当用户要求"给文章配图"、"为文章生成插图"、"添加配图"时使用此技能。
• anbeime-skill-baoyu-format-markdown — last commit 2026-08-06, shares skill
  Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use w…
• anbeime-skill-baoyu-post-to-wechat — last commit 2026-08-06, shares skill
  Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdo…
• anbeime-skill-baoyu-post-to-x — last commit 2026-08-06, shares skill
  Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown…
• anbeime-skill-baoyu-url-to-markdown — last commit 2026-08-06, shares skill
  Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for use…

These share tags the maintainers applied themselves, such as agent, skill. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

How the author describes it

Topics the maintainer set on GitHub: agent, ai, mcp, mcp-server, mcp-server-store, mcp-servers-directory, playbook, playbooks, skill, skills.