tmux-mcp-server

Tmux MCP server that exposes tools to an AI agent for creating, managing, and inspecting tmux terminal sessions via MCP over stdio. Tools include starting sessions, sending keystrokes/commands, viewing screen contents, listing/joining sessions, and closing sessions.

Evaluated Apr 04, 2026 (16d ago)
Repo ↗ DevTools devtools infrastructure terminal tmux mcp automation agent-tools
⚙ Agent Friendliness
51
/ 100
Can an agent use this?
🔒 Security
37
/ 100
Is it safe for agents?
⚡ Reliability
25
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
55
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
100
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
45
Secret Handling
40

Primary risk is authorization: the server is stdio-based and the README does not describe authentication/authorization. This tool enables interactive command/keystroke execution in a tmux session, so it should be run only in trusted, sandboxed environments with strict agent constraints. TLS is not directly applicable to stdio, but no network transport is described. Screen capture may expose secrets present in terminal output.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
40
Error Recovery
20
AF Security Reliability

Best When

You need an agent to control existing terminal sessions in tmux as part of an interactive automation loop, and you can run the MCP server locally/inside a controlled environment.

Avoid When

You cannot restrict what commands the agent may send, or you require fine-grained auditing/authorization for terminal actions.

Use Cases

  • Automating interactive terminal workflows with an LLM (REPLs, shells, CLI tools)
  • Agent-driven code editing inside tmux (e.g., vim/nano workflows)
  • Remote/centralized terminal session control for multi-step tasks
  • Capturing terminal screen output for agent observation

Not For

  • Production workloads requiring strong isolation between users/agents
  • Environments where allowing an agent to type commands into a shell is unacceptable
  • Use cases needing stable, documented HTTP/SDK-based APIs

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

The README describes stdio-based MCP execution and does not mention authentication, authorization, or session scoping controls.

Pricing

Free tier: No
Requires CC: No

No pricing information provided (open-source style repository inferred, but not guaranteed).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Sending keystrokes/commands can have side effects; agent must be constrained/allowed-list aware
  • Session state timing can matter (screen/view vs send_commands sequencing)
  • Special key handling depends on the expected <COMMAND> mapping; mismatches may lead to unexpected keystrokes
  • Viewing the screen may include sensitive data from the terminal buffer

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for tmux-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered