# AgentPlaybooks (remote · agentplaybooks.ai)

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

- Trust score: 66/100 (medium)
- Registry status: deprecated
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

> **Deprecated**: this server is marked deprecated in the MCP registry.

## Components

- remote · `agentplaybooks.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/ai-agentplaybooks-agentplaybooks/api-mcp-manage.md), [page](https://verifymcp.io/servers/ai-agentplaybooks-agentplaybooks/api-mcp-manage)

## Channel facts

- Endpoint: `https://agentplaybooks.ai/api/mcp/manage`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 47 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 4713 tokens (~100/item across 47 items; 47 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability check failed: schema churn in the 2 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 30 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-agentplaybooks-agentplaybooks https://agentplaybooks.ai/api/mcp/manage
```

### Codex

```toml
[mcp_servers.ai-agentplaybooks-agentplaybooks]
url = "https://agentplaybooks.ai/api/mcp/manage"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-agentplaybooks-agentplaybooks": {
      "type": "remote",
      "url": "https://agentplaybooks.ai/api/mcp/manage",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-agentplaybooks-agentplaybooks --url https://agentplaybooks.ai/api/mcp/manage --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-agentplaybooks-agentplaybooks:
    url: "https://agentplaybooks.ai/api/mcp/manage"
```

### Other

```json
{
  "mcpServers": {
    "ai-agentplaybooks-agentplaybooks": {
      "type": "http",
      "url": "https://agentplaybooks.ai/api/mcp/manage"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 66, 0)

- [security regression] Stability: 0.03 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security] Tool “create_persona” rewrote its description, which is the text the model reads
- [security] Tool “create_skill” rewrote its description, which is the text the model reads
- [security] Tool “delete_memory” rewrote its description, which is the text the model reads
- [security] Tool “delete_persona” rewrote its description, which is the text the model reads
- [security] Tool “delete_skill” rewrote its description, which is the text the model reads
- [security] Tool “get_playbook” rewrote its description, which is the text the model reads
- [security] Tool “get_skill” rewrote its description, which is the text the model reads
- [security] Tool “list_playbooks” rewrote its description, which is the text the model reads
- [security] Tool “list_skills” rewrote its description, which is the text the model reads
- [security] Tool “read_memory” rewrote its description, which is the text the model reads
- [security] Tool “search_memory” rewrote its description, which is the text the model reads
- [security] Tool “update_playbook” rewrote its description, which is the text the model reads
- [security] Tool “update_skill” rewrote its description, which is the text the model reads
- [security] Tool “write_memory” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 66 → 100
- [functional regression] “create_skill” made “content” required, so existing callers break
- [functional] Schema quality: excellent → good
- [functional] New tool “use_secret”
- [functional] New tool “write_canvas”
- [functional] New tool “archive_memories”
- [functional] New tool “call_connected_tool”
- [functional] New tool “consolidate_memories”
- [functional] New tool “create_mcp_server”
- [functional] New tool “create_run”
- [functional] New tool “create_task_graph”
- [functional] New tool “delete_mcp_server”
- [functional] New tool “delete_run”
- [functional] New tool “delete_secret”
- [functional] New tool “get_canvas_toc”
- [functional] New tool “get_memory_context”
- [functional] New tool “get_memory_tree”
- [functional] New tool “list_canvas”
- [functional] New tool “list_mcp_servers”
- [functional] New tool “list_runs”
- [functional] New tool “list_secrets”
- [functional] New tool “list_skill_versions”
- [functional] New tool “lock_canvas_section”
- [functional] New tool “patch_canvas_section”
- [functional] New tool “promote_memory”
- [functional] New tool “read_canvas”
- [functional] New tool “rollback_skill”
- [functional] New tool “rotate_secret”
- [functional] New tool “store_secret”
- [functional] New tool “unlock_canvas_section”
- [functional] New tool “update_mcp_server”
- [functional] New tool “update_run”
- [functional] New tool “update_task_status”
- [cosmetic] “create_playbook” added an optional parameter “persona_metadata”
- [cosmetic] “create_playbook” added an optional parameter “persona_name”
- [cosmetic] “create_playbook” added an optional parameter “persona_system_prompt”
- [cosmetic] “create_playbook” added an optional parameter “tags”
- [cosmetic] “create_skill” added an optional parameter “priority”
- [cosmetic] “search_memory” added an optional parameter “include_children”
- [cosmetic] “search_memory” added an optional parameter “memory_type”
- [cosmetic] “search_memory” added an optional parameter “status”
- [cosmetic] “search_memory” added an optional parameter “tier”
- [cosmetic] “update_playbook” added an optional parameter “config”
- [cosmetic] “update_playbook” added an optional parameter “persona_metadata”
- [cosmetic] “update_playbook” added an optional parameter “persona_name”
- [cosmetic] “update_playbook” added an optional parameter “persona_system_prompt”
- [cosmetic] “update_playbook” added an optional parameter “tags”
- [cosmetic] “update_skill” added an optional parameter “priority”
- [cosmetic] “write_memory” added an optional parameter “memory_type”
- [cosmetic] “write_memory” added an optional parameter “metadata”
- [cosmetic] “write_memory” added an optional parameter “parent_key”
- [cosmetic] “write_memory” added an optional parameter “priority”
- [cosmetic] “write_memory” added an optional parameter “status”
- [cosmetic] “write_memory” added an optional parameter “summary”
- [cosmetic] “write_memory” added an optional parameter “tier”
- [cosmetic] “create_skill” reworded the description of “content”
- [cosmetic] “create_skill” reworded the description of “description”
- [cosmetic] “create_skill” reworded the description of “name”
- [cosmetic] “create_skill” reworded the description of “playbook_id”
- [cosmetic] “delete_memory” reworded the description of “playbook_id”
- [cosmetic] “delete_skill” reworded the description of “playbook_id”
- [cosmetic] “delete_skill” reworded the description of “skill_id”
- [cosmetic] “get_skill” reworded the description of “playbook_id”
- [cosmetic] “get_skill” reworded the description of “skill_id”
- [cosmetic] “list_skills” reworded the description of “playbook_id”
- [cosmetic] “read_memory” reworded the description of “playbook_id”
- [cosmetic] “search_memory” reworded the description of “playbook_id”
- [cosmetic] “search_memory” reworded the description of “search”
- [cosmetic] “update_playbook” reworded the description of “description”
- [cosmetic] “update_playbook” reworded the description of “instructions”
- [cosmetic] “update_playbook” reworded the description of “name”
- [cosmetic] “update_playbook” reworded the description of “playbook_id”
- [cosmetic] “update_skill” reworded the description of “content”
- [cosmetic] “update_skill” reworded the description of “playbook_id”
- [cosmetic] “update_skill” reworded the description of “skill_id”
- [cosmetic] “write_memory” reworded the description of “description”
- [cosmetic] “write_memory” reworded the description of “key”
- [cosmetic] “write_memory” reworded the description of “playbook_id”
- [cosmetic] “write_memory” reworded the description of “tags”
- [cosmetic] “write_memory” reworded the description of “value”
- [cosmetic] “create_skill” dropped the optional parameter “licence”
- [cosmetic] “update_skill” dropped the optional parameter “licence”
- [cosmetic] “create_skill” made “description” optional

### 2026-08-02 (score 66, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-01 (score 66)

First indexed and scored.

## MCP tools (47)

### `list_playbooks` (~28 tokens)

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

### `create_playbook` (~166 tokens)

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

Input parameters:

- `description` (string): Description of what the playbook is for
- `instructions` (string): Always-on project instructions (the AGENTS.md / CLAUDE.md content). Separate from the persona: the persona is who the agent is, these are the rules of this project.
- `name` (string, required): Name of the playbook
- `persona_metadata` (object): Initial persona metadata
- `persona_name` (string): Initial persona name
- `persona_system_prompt` (string): Initial persona/system prompt
- `tags` (array): Discovery and organization tags
- `visibility` (string): Visibility of the playbook

### `get_playbook` (~41 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID of the playbook

### `delete_playbook` (~50 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID of the playbook to delete

### `create_persona` (~85 tokens)

Set the singleton persona (AI identity and system prompt) for a playbook. Backward-compatible alias for updating persona fields.

Input parameters:

- `metadata` (object): Optional metadata
- `name` (string, required): Name of the persona
- `playbook_id` (string, required): UUID of the playbook
- `system_prompt` (string, required): The system prompt that defines this persona's behavior

### `update_persona` (~76 tokens)

Update a persona's name, system prompt, or metadata.

Input parameters:

- `metadata` (object): New metadata
- `name` (string): New name
- `persona_id` (string, required): UUID of the persona
- `playbook_id` (string, required): UUID of the playbook
- `system_prompt` (string): New system prompt

### `delete_persona` (~55 tokens)

Reset the singleton persona to the default assistant. The playbook always retains one logical persona.

Input parameters:

- `persona_id` (string, required): UUID of the persona to delete
- `playbook_id` (string, required): UUID of the playbook

### `list_skills` (~48 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook

### `get_skill` (~53 tokens)

Get detailed information about a specific skill Target a playbook with playbook_id.

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `skill_id` (string, required): Skill ID or name

### `read_memory` (~103 tokens)

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.

Input parameters:

- `key` (string, required): Memory key to read
- `playbook_id` (string, required): UUID or GUID of the target playbook

### `search_memory` (~155 tokens)

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.

Input parameters:

- `include_children` (boolean): Include child memories in results
- `memory_type` (string): Filter by memory type
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `search` (string): Search in keys, descriptions, and summaries
- `status` (string): Filter by task status (hierarchical only)
- `tags` (array): Filter by tags (any match)
- `tier` (string): Filter by memory tier

### `write_memory` (~234 tokens)

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.

Input parameters:

- `description` (string): Human-readable description
- `key` (string, required): Memory key
- `memory_type` (string): flat (default) or hierarchical for task graphs
- `metadata` (object): Graph metadata: dependencies, thread assignment, progress, etc.
- `parent_key` (string): Parent memory key for hierarchical organization
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `priority` (number): Priority 1-100 (default: 50)
- `status` (string): Task status (for hierarchical task tracking)
- `summary` (string): Compact summary for context views
- `tags` (array): Tags for categorization
- `tier` (string): Memory tier (default: contextual)
- `value` (object, required): Value to store

### `delete_memory` (~54 tokens)

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

Input parameters:

- `key` (string, required): Memory key to delete
- `playbook_id` (string, required): UUID or GUID of the target playbook

### `consolidate_memories` (~120 tokens)

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.

Input parameters:

- `archive_children` (boolean): Move children to longterm tier
- `memory_keys` (array, required): Keys of memories to consolidate
- `parent_key` (string, required): New parent memory key
- `parent_tags` (array): Tags for parent memory
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `summary` (string, required): Summary of consolidated memories

### `promote_memory` (~95 tokens)

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

Input parameters:

- `key` (string, required): Memory key to promote
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `priority_boost` (number): Amount to increase priority (0-50)
- `target_tier` (string): Target tier (cannot demote with this tool)

### `get_memory_context` (~121 tokens)

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.

Input parameters:

- `expand_keys` (array): Keys to show full content regardless of tier
- `include_tiers` (array): Tiers to include (default: working, contextual)
- `max_items` (number): Maximum items per tier
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `tags_filter` (array): Only include memories with these tags

### `archive_memories` (~123 tokens)

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

Input parameters:

- `from_tier` (string): Only archive from this tier
- `generate_summaries` (boolean): Auto-generate summaries if missing
- `keys` (array): Specific keys to archive
- `older_than_hours` (number): Archive memories older than X hours
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `tags` (array): Only archive memories with these tags

### `get_memory_tree` (~107 tokens)

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.

Input parameters:

- `include_values` (boolean): Include full values (false = summaries only)
- `max_depth` (number): Maximum tree depth
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `root_key` (string): Start from this key (omit for all roots)

### `create_task_graph` (~139 tokens)

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.

Input parameters:

- `plan_key` (string, required): Key for the root plan memory
- `plan_summary` (string, required): High-level summary of the entire plan
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `tags` (array): Tags for the plan
- `tasks` (array, required): List of subtasks to create

### `update_task_status` (~116 tokens)

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.

Input parameters:

- `key` (string, required): Task memory key to update
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `result` (object): Task result data to store in value
- `status` (string, required): New status
- `summary` (string): Updated summary with results

### `list_canvas` (~76 tokens)

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.

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string): Workflow run UUID. Omit to list documents across all runs.

### `read_canvas` (~92 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `section_id` (string): Optional: read only this section
- `slug` (string, required): Document slug

### `write_canvas` (~113 tokens)

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.

Input parameters:

- `content` (string, required): Full markdown content
- `metadata` (object): Custom document metadata
- `name` (string, required): Document title
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `slug` (string, required): URL-friendly document identifier

### `patch_canvas_section` (~123 tokens)

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.

Input parameters:

- `content` (string, required): New section content (markdown)
- `heading` (string): Optional: new heading text
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `section_id` (string, required): Section ID from get_canvas_toc
- `slug` (string, required): Document slug

### `get_canvas_toc` (~81 tokens)

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.

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `slug` (string, required): Document slug

### `lock_canvas_section` (~98 tokens)

Lock a section for exclusive editing. Prevents other agents from modifying it. Remember to unlock when done. Target a playbook with playbook_id.

Input parameters:

- `locked_by` (string, required): Agent identifier
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `section_id` (string, required): Section ID to lock
- `slug` (string, required): Document slug

### `unlock_canvas_section` (~79 tokens)

Unlock a previously locked section so other agents can edit it. Target a playbook with playbook_id.

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `section_id` (string, required): Section ID to unlock
- `slug` (string, required): Document slug

### `create_skill` (~127 tokens)

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

Input parameters:

- `content` (string, required): The instructions/prompt/code for the skill
- `description` (string): What the skill does and when the agent should use it
- `name` (string, required): Agent Skills-compatible name (lowercase kebab-case, e.g. data-analyzer)
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `priority` (number): Priority level (default 50)

### `update_skill` (~106 tokens)

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

Input parameters:

- `content` (string): New content/instructions
- `description` (string): New description
- `name` (string): New name
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `priority` (number): New priority level
- `skill_id` (string, required): ID or name of the skill to update

### `delete_skill` (~66 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `skill_id` (string, required): ID or name of the skill to delete

### `list_skill_versions` (~75 tokens)

List historical versions of a skill for auditing or rollback. Target a playbook with playbook_id.

Input parameters:

- `limit` (number): Max versions to return (default 10)
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `skill_id` (string, required): ID or name of the skill

### `rollback_skill` (~70 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `version_id` (string, required): The specific version ID from list_skill_versions to rollback to

### `update_playbook` (~196 tokens)

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.

Input parameters:

- `config` (object): Replacement playbook configuration
- `description` (string): New playbook description
- `instructions` (string): New always-on project instructions (the AGENTS.md / CLAUDE.md content). Kept separate from the persona: the persona is who the agent is, these are the rules of this project.
- `name` (string): New playbook name
- `persona_metadata` (object): New metadata JSON
- `persona_name` (string): New persona name
- `persona_system_prompt` (string): New core system instructions
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `tags` (array): Replacement discovery tags
- `visibility` (string): New visibility

### `list_mcp_servers` (~57 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook

### `call_connected_tool` (~111 tokens)

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.

Input parameters:

- `arguments` (object): Arguments passed to the connected tool
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `server_id` (string, required): Connected server UUID or name
- `tool_name` (string, required): Tool name exposed by the connected server

### `create_mcp_server` (~141 tokens)

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

Input parameters:

- `description` (string): What this server provides
- `name` (string, required): Display name of the connected server
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `resources` (array): Known resource definitions, if already discovered
- `tools` (array): Known tool definitions, if already discovered
- `transport_config` (object): Transport-specific configuration. Do not put plaintext secrets here.
- `transport_type` (string): Connection type (default: http)

### `update_mcp_server` (~126 tokens)

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

Input parameters:

- `description` (string): New description
- `name` (string): New display name
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `resources` (array): Updated resource definitions
- `server_id` (string, required): Connected server UUID
- `tools` (array): Updated tool definitions
- `transport_config` (object): Updated transport-specific configuration
- `transport_type` (string): Connection type

### `delete_mcp_server` (~68 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `server_id` (string, required): Connected server UUID

### `list_runs` (~50 tokens)

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

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook

### `create_run` (~74 tokens)

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

Input parameters:

- `context` (object): Initial execution context
- `name` (string, required): Human-readable run name
- `playbook_id` (string, required): UUID or GUID of the target playbook

### `update_run` (~87 tokens)

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

Input parameters:

- `context` (object): Replacement execution context
- `name` (string): New run name
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID
- `status` (string): New run status

### `delete_run` (~55 tokens)

Delete a workflow run and its isolated canvas artifacts. Target a playbook with playbook_id.

Input parameters:

- `playbook_id` (string, required): UUID or GUID of the target playbook
- `run_id` (string, required): Workflow run UUID

### `list_secrets` (~75 tokens)

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.

Input parameters:

- `category` (string): Filter by category
- `playbook_id` (string, required): UUID or GUID of the target playbook

### `use_secret` (~275 tokens)

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.

Input parameters:

- `body` (object): JSON request body (for POST/PUT/PATCH)
- `extra_headers` (object): Additional headers (e.g. {"Content-Type": "application/json"})
- `header_name` (string): Header name to inject the secret into (default: Authorization)
- `header_prefix` (string): Prefix before the secret value (default: 'Bearer '). Use empty string for raw value.
- `method` (string): HTTP method (default: GET)
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `secret_name` (string, required): Name of the secret to use (e.g. OPENAI_API_KEY)
- `timeout_ms` (number): Request timeout in milliseconds (default: 30000, max: 60000)
- `url` (string, required): The URL to send the HTTP request to

### `store_secret` (~145 tokens)

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.

Input parameters:

- `category` (string): Secret type (default: general)
- `description` (string): What this secret is used for
- `expires_at` (string): ISO 8601 expiration date (optional)
- `name` (string, required): Secret name (letters, numbers, hyphens, underscores)
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `value` (string, required): The secret value to encrypt and store

### `rotate_secret` (~84 tokens)

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.

Input parameters:

- `name` (string, required): Secret name to rotate
- `playbook_id` (string, required): UUID or GUID of the target playbook
- `value` (string, required): New secret value

### `delete_secret` (~61 tokens)

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

Input parameters:

- `name` (string, required): Secret name to delete
- `playbook_id` (string, required): UUID or GUID of the target playbook

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-agentplaybooks-agentplaybooks/api-mcp-manage#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 66
- 2026-08-01: 66

## Links

- Remote endpoint: https://agentplaybooks.ai/api/mcp/manage
- Authorisation metadata: https://agentplaybooks.ai/.well-known/oauth-protected-resource/api/mcp/manage
- Repository: https://github.com/matebenyovszky/agentplaybooks
- Website: https://agentplaybooks.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-agentplaybooks-agentplaybooks/api-mcp-manage/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-agentplaybooks-agentplaybooks/api-mcp-manage/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-agentplaybooks-agentplaybooks/api-mcp-manage