codebolt-mcp-access

Core skill for Codebolt agents to interact with the Codebolt MCP (Model Context Protocol) API. Use when agents need to execute tools for file operations, git, browser automation, terminal, memory, orchestration, planning, testing, collaboration, or any Codebolt platform functionality. Triggers on requests involving codebolt.tools.executeTool(), file system operations, git commands, browser control, agent orchestration, task management, or any MCP namespace operations.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "codebolt-mcp-access" with this command: npx skills add codeboltai/codeboltjs/codeboltai-codeboltjs-codebolt-mcp-access

Codebolt MCP Access

Execute Codebolt platform tools via the MCP interface.

Quick Start

const result = await codebolt.tools.executeTool(
  "codebolt.<namespace>",
  "<tool_name>",
  { param1: "value1", param2: "value2" }
);

Tool Categories

Core Tools

NamespaceUse Case
codebolt.fsRead, write, edit files
codebolt.gitVersion control operations
codebolt.browserWeb automation
codebolt.terminalCommand execution
codebolt.searchCode/file search (glob, grep, semantic)

Data & State

NamespaceUse Case
codebolt.memoryPersistent data storage (JSON, markdown, episodic)
codebolt.stateAgent and project state management
codebolt.ragRAG indexes and document retrieval
codebolt.vectorVector database operations
codebolt.knowledgeKnowledge graph management

Agent & Orchestration

NamespaceUse Case
codebolt.orchestrationTasks, agents, threads
codebolt.agentAgent lifecycle management
codebolt.taskTask CRUD operations
codebolt.jobWork items with dependencies
codebolt.capabilitySkills and powers

Project Management

NamespaceUse Case
codebolt.planningRoadmaps and action plans
codebolt.actionPlanAction plan management
codebolt.actionBlockActionBlock management
codebolt.roadmapRoadmap management
codebolt.requirementPlanRequirements planning
codebolt.autoTestingAutomated testing
codebolt.codemapCode structure visualization
codebolt.calendarEvents and scheduling
codebolt.todoTodo list management
codebolt.reviewCode review workflow
codebolt.reviewMergeRequestReview merge requests
codebolt.testingTest suite management

Communication & Collaboration

NamespaceUse Case
codebolt.chatChat and notifications
codebolt.messageMessage handling
codebolt.notificationEvent notifications
codebolt.collaborationFeedback and deliberation
codebolt.swarmSwarm/team/role management
codebolt.agentDeliberationMulti-agent deliberation
codebolt.agentPortfolioAgent portfolio/reputation
codebolt.groupFeedbackGroup feedback sessions
codebolt.mailAgent mail/messaging
codebolt.configMCP server configuration

Memory & Knowledge

NamespaceUse Case
codebolt.memoryPersistent data storage
codebolt.episodicMemoryEpisode-based memory
codebolt.persistentMemoryLong-term memory pipelines
codebolt.dbmemoryDatabase memory
codebolt.eventLogEvent logging
codebolt.stateAgent and project state
codebolt.ragRAG indexes
codebolt.vectorVector database
codebolt.knowledgeKnowledge graph

Project & Code

NamespaceUse Case
codebolt.projectProject info and settings
codebolt.projectStructureProject structure management
codebolt.crawlerWeb crawler
codebolt.codebaseSemantic code search
codebolt.fileIntentFile intent management

Utilities

NamespaceUse Case
codebolt.code_utilsAST and pattern matching
codebolt.tokenizerText tokenization
codebolt.debugDebugging utilities
codebolt.kvStoreKey-value storage
codebolt.outputParsersOutput parsing
codebolt.sideExecutionIsolated code execution
codebolt.userMessageManagerUser message context
codebolt.userMessageUtilitiesMessage utilities
codebolt.historyChat history summarization
codebolt.eventBackground agent events
codebolt.hookEvent-driven hooks
codebolt.orchestratorOrchestrator lifecycle
codebolt.contextRuleEngineConditional memory rules
codebolt.llmLLM inference
codebolt.adminAdmin operations
codebolt.mcpMCP server management

Reference Files

Load the reference file for detailed parameter tables:

Core

ReferenceNamespace
fs.mdcodebolt.fs
git.mdcodebolt.git
browser.mdcodebolt.browser
terminal.mdcodebolt.terminal
search.mdcodebolt.search

Data & State

ReferenceNamespace
memory.mdcodebolt.memory
state.mdcodebolt.state
rag.mdcodebolt.rag
knowledge.mdcodebolt.knowledge
context.mdcodebolt.context
codebase.mdcodebolt.codebase

Agent & Orchestration

ReferenceNamespace
orchestration.mdcodebolt.orchestration
agent.mdcodebolt.agent
job.mdcodebolt.job
capability.mdcodebolt.capability
admin.mdcodebolt.admin
llm.mdcodebolt.llm

Project Management

ReferenceNamespace
planning.mdcodebolt.planning
calendar.mdcodebolt.calendar
todo.mdcodebolt.todo
review.mdcodebolt.review
testing.mdcodebolt.testing
project.mdcodebolt.project

Communication

ReferenceNamespace
chat.mdcodebolt.chat
collaboration.mdcodebolt.collaboration
mcp_servers.mdcodebolt.mcp

Multi-Agent & Collaboration

ReferenceNamespace
swarm.mdcodebolt.swarm
agentDeliberation.mdcodebolt.agentDeliberation
agentPortfolio.mdcodebolt.agentPortfolio
groupFeedback.mdcodebolt.groupFeedback
mail.mdcodebolt.mail
collaboration.mdcodebolt.collaboration

Planning & Project Management

ReferenceNamespace
actionPlan.mdcodebolt.actionPlan
actionBlock.mdcodebolt.actionBlock
roadmap.mdcodebolt.roadmap
requirementPlan.mdcodebolt.requirementPlan
autoTesting.mdcodebolt.autotesting
codemap.mdcodebolt.codemap
reviewMergeRequest.mdcodebolt.reviewMergeRequest

Memory & Knowledge

ReferenceNamespace
episodicMemory.mdcodebolt.episodicMemory
persistentMemory.mdcodebolt.persistentMemory
dbmemory.mdcodebolt.dbmemory
eventLog.mdcodebolt.eventLog

Project & Code

ReferenceNamespace
projectStructure.mdcodebolt.projectStructure
crawler.mdcodebolt.crawler
hook.mdcodebolt.hook
orchestrator.mdcodebolt.orchestrator
contextRuleEngine.mdcodebolt.contextRuleEngine

Utilities

ReferenceNamespace
kvStore.mdcodebolt.kvStore
outputParsers.mdcodebolt.outputparsers
sideExecution.mdcodebolt.sideExecution
userMessageManager.mdcodebolt.userMessageManager
userMessageUtilities.mdcodebolt.userMessageUtilities
history.mdcodebolt.history
codeboltEvent.mdcodebolt.event
vector.mdcodebolt.vector
tokenizer.mdcodebolt.tokenizer
code_utils.mdcodebolt.code_utils
debug.mdcodebolt.debug
notification.mdcodebolt.notification
message.mdcodebolt.message
config.mdcodebolt.config
task.mdcodebolt.task
problem.mdcodebolt.problem

Common Patterns

Read then Edit

// 1. Read file first
const content = await codebolt.tools.executeTool("codebolt.fs", "read_file", {
  absolute_path: "/path/to/file.js"
});

// 2. Edit with old_string/new_string
await codebolt.tools.executeTool("codebolt.fs", "edit", {
  absolute_path: "/path/to/file.js",
  old_string: "original text",
  new_string: "replacement text"
});

Search then Act

// 1. Search for files
const files = await codebolt.tools.executeTool("codebolt.search", "glob", {
  pattern: "**/*.ts"
});

// 2. Search content
const matches = await codebolt.tools.executeTool("codebolt.search", "grep", {
  pattern: "function\\s+\\w+",
  path: "./src"
});

Multi-Agent Task

// 1. Find suitable agent
const agents = await codebolt.tools.executeTool("codebolt.orchestration", "agent_find", {
  task: "Write unit tests"
});

// 2. Create and assign task
const task = await codebolt.tools.executeTool("codebolt.orchestration", "task_create", {
  title: "Write tests for auth module"
});

// 3. Execute with agent
await codebolt.tools.executeTool("codebolt.orchestration", "task_execute", {
  task_id: task.id,
  agent_id: agents[0].id
});

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

codebolt-agent-development

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

codebolt-api-access

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

openclaw-version-monitor

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Archived SourceRecently Updated
Coding

ask-claude

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).

Archived SourceRecently Updated