vscode-context-mcp

Provides a Model Context Protocol (MCP) server/extension to expose VS Code context (active files, tabs, diagnostics, terminal output) and enable controlled filesystem and shell command operations to AI assistants.

Evaluated Apr 04, 2026 (16d ago)
Repo ↗ DevTools mcp vscode developer-tools ide-integration filesystem shell-execution ai-assistants
⚙ Agent Friendliness
42
/ 100
Can an agent use this?
🔒 Security
28
/ 100
Is it safe for agents?
⚡ Reliability
11
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
68
Documentation
62
Error Messages
0
Auth Simplicity
45
Rate Limits
0

🔒 Security

TLS Enforcement
20
Auth Strength
30
Scope Granularity
25
Dep. Hygiene
35
Secret Handling
30

README explicitly warns that comprehensive security measures are not yet implemented and cautions user review/approval (e.g., 'Approve Once' and 'Deny' for commands). TLS, auth mechanisms, and secret handling practices are not described. The tool has potentially high-impact capabilities (filesystem writes and shell command execution), so risk depends heavily on the host approval flow and user permissions.

⚡ Reliability

Uptime/SLA
0
Version Stability
25
Breaking Changes
0
Error Recovery
20
AF Security Reliability

Best When

You trust the operating user and the AI assistant interaction flow (e.g., approve/review each command), and you want local IDE context to power development assistance.

Avoid When

You need fine-grained security controls beyond client-side approvals, or you require strict guarantees around safe command execution and robust error recovery.

Use Cases

  • Let AI assistants understand the current VS Code workspace state (open files, diagnostics, terminal output).
  • Read and modify files in a workspace via MCP tools (read/write/edit, directory operations).
  • Search and enumerate project files/directories to support code navigation and debugging assistance.
  • Run shell commands (with user approval in the client) to support build/test/debug workflows.

Not For

  • Automated, unattended operation without user review/approval for commands and writes.
  • Security-sensitive environments where broad filesystem or command execution access is not tightly constrained.
  • Production systems requiring documented SLAs, strong change management, or rigorous error/idempotency guarantees.

Interface

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

Authentication

Methods: Client-side/user approval flow in the MCP host (e.g., Claude Desktop 'Approve Once' / 'Deny')
OAuth: No Scopes: No

No first-class server-side auth/scopes are described; permissions are described as being dictated by the user running the server and the MCP host approval flow for commands.

Pricing

Free tier: No
Requires CC: No

No pricing information provided (appears to be a local tool/OSS component).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • The server includes command execution and file mutation capabilities; README warns it does not implement comprehensive security measures.
  • Client-side approval is required/recommended for shell commands; agents may still attempt dangerous commands if not constrained.
  • Workspace context is tied to the VS Code environment and likely assumes a single active project/session; multi-project support is listed as roadmap.

Alternatives

Full Evaluation Report

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

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