terminal-mcp-server

An MCP server that provides AI agents with multi-session terminal execution, batch/concurrent command execution, workflow orchestration (DAG/sequences), and a local web UI for real-time terminal output and system stats.

Evaluated Apr 04, 2026 (16d ago)
Homepage ↗ Repo ↗ DevTools mcp terminal agent-tools concurrency web-monitoring fastapi websockets python
⚙ Agent Friendliness
67
/ 100
Can an agent use this?
🔒 Security
22
/ 100
Is it safe for agents?
⚡ Reliability
36
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
70
Error Messages
--
Auth Simplicity
95
Rate Limits
10

🔒 Security

TLS Enforcement
15
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
40

Security posture is unclear: README does not mention authentication/authorization, transport security for the web interface, or logging redaction. The tool enables arbitrary command execution in local terminals, which increases risk if accessible to untrusted actors. Dependencies listed are common libraries, but no vulnerability/CVE or hardening details are provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
40
Error Recovery
70
AF Security Reliability

Best When

Used locally by trusted operators/agents to orchestrate shell commands with concurrency and monitoring on a developer workstation or CI-like environment.

Avoid When

Avoid exposing the service to untrusted networks/users or using it in environments where arbitrary shell command execution cannot be tightly controlled.

Use Cases

  • Run multiple development/ops tasks in parallel (frontend/backend/DB) via a single MCP workflow
  • Collect system information concurrently (CPU/memory/disk/OS) and return aggregated outputs
  • Execute dependent build-test-deploy steps using a DAG/workflow model
  • Run retryable commands for transient failures (e.g., network/package installs)
  • Provide a web-based live monitoring view of terminal sessions using xterm.js

Not For

  • Internet-facing remote shell access for untrusted users
  • Compliance-critical environments without further audit of command execution and logging
  • Use cases requiring strict resource isolation/tenant separation beyond local machine execution

Interface

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

Authentication

OAuth: No Scopes: No

README does not describe any authentication/authorization mechanism for the MCP tools or the local web server. Tool access appears to be controlled implicitly by local IDE configuration.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; package appears to be an open-source tool distributed via PyPI/GitHub (MIT license).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Documented

Known Gotchas

  • README suggests MCP tool definitions may be cached by the IDE; restart IDE if tools descriptions appear incorrect
  • Use batch tools (create_batch/execute_batch) instead of single tools for concurrency/non-blocking behavior
  • Conversations should avoid repeated get_output polling loops; rely on check_completion/check_completion flow or documented anti-loop behavior

Alternatives

Full Evaluation Report

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