CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Vscode Terminal Mcp

sirlordt/vscode-terminal-mcp
1STDIOregistry active
Summary

Runs shell commands in visible VSCode terminal tabs instead of hidden processes, giving you real-time output you can scroll through and interact with. The run tool handles one-shot commands with clean output capture, while create/exec/read let you manage persistent sessions for long-running builds or interactive prompts. Session reuse keeps your workspace tidy, and agentId tags let parallel agents work in isolated terminals without cross-contamination. Fire off slow commands with waitForCompletion false, then poll incrementally with read to avoid blocking your LLM conversation. Requires VSCode 1.93+ for Shell Integration API support. Worth setting as your preferred execution tool over inline Bash when you need to watch output live or handle commands that take more than a few seconds.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

vscode-terminal-mcp

npm version

MCP server that executes commands in visible VSCode terminal tabs with full output capture. Unlike inline execution, every command runs in a real terminal you can see, scroll, and interact with.

Key Features

  • Visible Terminals: Commands run in real VSCode terminal tabs, not hidden processes. You see everything in real time.
  • Session Reuse: The run tool automatically reuses idle sessions, creating new terminals only when needed.
  • Long-Running Support: Fire-and-forget execution with waitForCompletion: false, then poll output incrementally with read.
  • Subagent Isolation: Tag sessions with agentId to keep parallel agent workloads separated.

Requirements

  • VS Code 1.93+ (for Shell Integration API)
  • Node.js 20+

Getting Started

Claude Code

claude mcp add BashTerm -- npx vscode-terminal-mcp@latest

VS Code / Copilot

Add to your .vscode/mcp.json:

{
  "servers": {
    "BashTerm": {
      "type": "stdio",
      "command": "npx",
      "args": ["vscode-terminal-mcp@latest"]
    }
  }
}
Cursor

Add to your .cursor/mcp.json:

{
  "mcpServers": {
    "BashTerm": {
      "command": "npx",
      "args": ["-y", "vscode-terminal-mcp@latest"]
    }
  }
}
Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "BashTerm": {
      "command": "npx",
      "args": ["-y", "vscode-terminal-mcp@latest"]
    }
  }
}

Your First Prompt

After installation, try asking:

Run ls -la in the terminal

You should see a new terminal tab open in VSCode with the command output.

Screenshots

Running a command with run

Run command output

Permission dialog for exec

Exec permission dialog

Exec result with clean output

Exec finished

Tools

Quick Execution

ToolDescription
runCreate (or reuse) a terminal and execute a command in one step. Returns clean output with exit code.

Session Management

ToolDescription
createCreate a new visible terminal session. Returns a sessionId.
execExecute a command in an existing session and capture output.
readRead output from a session with pagination. Supports incremental reads and tail mode (offset: -N).
inputSend text to an interactive terminal (prompts, REPLs, confirmations).
listList active sessions. Optionally filter by agentId.
closeClose a terminal session and its VSCode tab.

Usage Patterns

Simple Command

The run tool handles everything — creates a terminal if needed, executes, and returns clean output:

> Run npm test
$ npm test
PASS src/utils.test.ts (3 tests)
PASS src/index.test.ts (5 tests)

[exit: 0 | 1243ms | session-abc123]

Long-Running Process

For builds, deployments, or any command that takes a while:

> Start `npm run build` without waiting, then check progress

The agent will:

  1. Call run with waitForCompletion: false — returns immediately
  2. Call read with offset: -10 to check the last 10 lines
  3. Repeat until the process completes

Interactive Commands

For commands that need user input:

> Run npm init and answer the prompts

The agent will:

  1. Call run with npm init
  2. Call read to see the prompt
  3. Call input to send the answer

Parallel Agents

Subagents can work in isolated terminals using agentId:

> Have one agent run tests while another runs the linter

Each subagent gets its own terminal tagged with its agentId, preventing output from mixing.

Configuration

The extension reads configuration from VSCode settings under terminalMcp.*:

SettingTypeDefaultDescription
terminalMcp.maxSessionsnumber10Maximum concurrent terminal sessions
terminalMcp.commandTimeoutnumber30000Default command timeout in ms
terminalMcp.maxOutputLinesnumber5000Max lines kept in output buffer per session
terminalMcp.idleTimeoutnumber1800000Close idle sessions after this many ms (0 = disabled)
terminalMcp.blockedCommandsstring[]["rm -rf /"]Commands that will be rejected

Recommended: Set as Preferred Tool

LLM agents like Claude Code have a built-in Bash tool that executes commands inline within the chat. The output is embedded in the conversation and hard to read, especially for commands with verbose output. We recommend telling the agent to prefer this MCP over its built-in Bash tool.

Add the following to your project's CLAUDE.md (or equivalent instructions file):

## Terminal Execution

Prefer the BashTerm MCP tools (`run`, `exec`, `read`, etc.) over the built-in Bash tool for executing commands.
BashTerm runs commands in visible VSCode terminal tabs where the user can see output in real time.
Only fall back to the built-in Bash tool for simple, non-interactive operations like reading environment variables.

For commands that may take longer than 30 seconds or produce large amounts of output (builds, test suites,
deployments, installs), use the pull mode pattern:
1. Call `run` with `waitForCompletion: false` to launch the command without blocking.
2. Call `read` with `offset: -10` to check the last 10 lines of output.
3. Repeat step 2 until you see the command has finished (look for exit messages, prompts, or "Done").
4. Report the final result to the user.

This prevents conversation timeouts and lets the user watch progress in the terminal in real time.

Why this matters:

Built-in BashBashTerm MCP
Output visibilityEmbedded in chat, hard to scrollVisible in VSCode terminal tab
Real-time feedbackUser sees nothing until command finishesUser watches output live
Long-running commandsBlocks the conversation until timeoutFire-and-forget + polling
Session stateEach command is isolatedPersistent sessions with history
Interactive commandsNot supportedSend input to prompts/REPLs

Development: Updating the Extension

VSCode aggressively caches extensions in memory. When developing locally, code --install-extension and even "Developer: Reload Window" may not reload your changes. Use this workflow:

Quick update (no restart needed)

After modifying source files, build and copy directly into the installed extension directory:

cd /path/to/vscode-terminal-mcp
npm run build
cp dist/extension.js ~/.vscode/extensions/sirlordt.vscode-terminal-mcp-<version>/dist/extension.js

Then run "Developer: Reload Window" (Ctrl+Shift+P).

Full reinstall (when quick update doesn't work)

If VSCode still uses old code:

# 1. Uninstall and remove all copies
code --uninstall-extension sirlordt.vscode-terminal-mcp
rm -rf ~/.vscode/extensions/sirlordt.vscode-terminal-mcp-*

# 2. Check for ghost entries with old publisher names
# Look in ~/.vscode/extensions/extensions.json for stale entries
# Remove any entries with old publisher IDs (e.g., "terminal-mcp.vscode-terminal-mcp")

# 3. Close VSCode completely (not just reload)

# 4. Rebuild and install
npm run build
npx vsce package --allow-missing-repository
code --install-extension vscode-terminal-mcp-<version>.vsix --force

# 5. Open VSCode

Verify the correct version is loaded

# Check which extension directories exist
ls ~/.vscode/extensions/ | grep terminal

# Verify your changes are in the installed extension
grep "YOUR_UNIQUE_STRING" ~/.vscode/extensions/sirlordt.vscode-terminal-mcp-*/dist/extension.js

# Compare checksums
md5sum dist/extension.js ~/.vscode/extensions/sirlordt.vscode-terminal-mcp-*/dist/extension.js

Large Output Handling

When read returns output that exceeds the MCP client's token limit, the system automatically saves the full output to a temporary JSON file and returns the file path in the error message.

To extract the relevant content:

# Get the last 50 lines (most relevant for status)
tail -50 /path/to/saved/file.txt

# Or parse the JSON to extract the text content
python3 -c "import json; data=json.load(open('/path/to/file.txt')); print(data[0]['text'][-2000:])"

The file format is JSON: [{"type": "text", "text": "..."}]

This commonly happens with commands that produce heavy TUI output (progress bars, ANSI escape codes). Use smaller offset values (e.g., offset: -20 instead of offset: -100) to reduce the captured output size.

How It Works

  1. The VSCode extension activates and starts an IPC server on a Unix socket
  2. The MCP entry point (mcp-entry.js) is spawned by the MCP client and bridges JSON-RPC stdio with the IPC socket
  3. Commands execute in real VSCode terminals using the Shell Integration API for reliable output capture and exit code detection
  4. Output is stored in circular buffers with pagination support for efficient reading

Latest Changes (0.1.6)

  • Screenshots in README for marketplace
  • Clean output format for all tools — no more raw JSON
  • Fixed waitForCompletion: false not working
  • Disabled idle reaper — user closes sessions manually
  • Unique IPC socket per workspace (multi-instance support)
  • Custom terminal tab names with date format
  • Large output handling documentation

See CHANGELOG.md for full history.

License

MIT

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
Developer Tools
Registryactive
Packagevscode-terminal-mcp
TransportSTDIO
UpdatedMar 18, 2026
View on GitHub

Related Developer Tools MCP Servers

View all →
Git Mcp Server

ray0907/git-mcp-server

MCP server for GitLab and GitHub
Git Mcp Server

cyanheads/git-mcp-server

Comprehensive Git MCP server enabling native git tools including clone, commit, worktree, & more.
221
Atlassian Dc Mcp Bitbucket

io.github.b1ff/atlassian-dc-mcp-bitbucket

MCP server for Atlassian Bitbucket Data Center - interact with repositories and code
77
Atlassian Dc Mcp Jira

io.github.b1ff/atlassian-dc-mcp-jira

MCP server for Atlassian Jira Data Center - search, view, and create issues
77
Atlassian Jira

com.mcparmory/atlassian-jira

Create, search, and manage issues, projects, and team workflows
25
Bitbucket

aashari/mcp-server-atlassian-bitbucket

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
146