mcp-server-developer-tool

Provides a modular Go implementation of an MCP (Model Context Protocol) server. It includes tools for executing shell commands (with restrictions) and basic file operations (show/search/write), with configuration-driven allow/deny path restrictions.

Evaluated Apr 04, 2026 (17d ago)
Repo ↗ DevTools mcp agent-tools go filesystem sandboxing developer-tools modular tooling
⚙ Agent Friendliness
38
/ 100
Can an agent use this?
🔒 Security
32
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
72
Documentation
58
Error Messages
0
Auth Simplicity
20
Rate Limits
0

🔒 Security

TLS Enforcement
20
Auth Strength
10
Scope Granularity
60
Dep. Hygiene
45
Secret Handling
35

The project claims path restriction for file operations and additional restrictions for the shell command tool (whitelisted utilities, allowed working directories, custom executable path checks). However, the README does not describe transport security (TLS), authentication/authorization for MCP access, logging redaction, rate limiting, or detailed error/exception handling. Shell execution and file writing tools remain high-risk if exposed or misconfigured.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
45
Error Recovery
40
AF Security Reliability

Best When

Used in a local or single-tenant environment where you can tightly configure allowed/denied filesystem paths and understand the security implications of tool-enabled agents.

Avoid When

Avoid exposing the server broadly (e.g., public network) without additional network/auth controls, and avoid running with overly permissive path settings.

Use Cases

  • Agent-assisted codebase/file exploration (read-only operations like show/search)
  • Controlled code generation or patching workflows via write file tool
  • Restricted command execution for build/test or utility runs within an allowed workspace
  • Local development MCP server setup for agent tooling using a Go MCP library

Not For

  • Unrestricted remote shell access (it appears intended to be sandboxed, not fully exposed)
  • Multi-tenant production deployments without a strong external access-control layer
  • Workflows requiring documented API contracts beyond MCP tool definitions

Interface

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

Authentication

OAuth: No Scopes: No

The README describes filesystem restrictions but does not mention transport authentication/authorization for MCP connections.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; appears to be an open-source code repository.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Tool behavior is security-sensitive: shell execution and file writing depend on allow/deny path configuration.
  • Default behavior (allow only current working directory; auto-deny sensitive directories) may surprise agents if the working directory differs from expected workspace.
  • No documented retry/idempotency semantics are provided in the README, so agents should assume writes/executions may not be safe to repeat blindly.

Alternatives

Full Evaluation Report

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

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