Skip to main content
Glama
deenesjakoruzh
tao-izm

devpulse-mcp

by tao-izm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

devpulse

AI 코딩 어시스턴트가 개발 환경에서 실제로 무슨 일이 일어나고 있는지 확인할 수 있게 해주는 MCP 서버입니다.

Claude Code나 Cursor로 디버깅할 때, AI는 개발 서버가 실행 중인지, 로그에 어떤 오류가 나타났는지, 현재 어떤 브랜치에 있는지 알지 못합니다. 결국 매 세션마다 동일한 컨텍스트를 복사해서 붙여넣게 됩니다. devpulse는 단 한 번의 도구 호출로 이 문제를 해결합니다.

AI가 확인하는 정보

{
  "diagnosis": {
    "health": "broken",
    "primary_issue": "Port conflict — dev server cannot start",
    "suggested_action": "Kill the process using that port or change your dev server port",
    "confidence": "high"
  },
  "session": {
    "project": "my-app",
    "framework": "nextjs",
    "branch": "feat/auth",
    "uncommitted_files": 3
  },
  "services": {
    "running": [],
    "expected_but_missing": [3000]
  },
  "recent_errors": [
    { "time": "2m ago", "level": "ERROR", "message": "EADDRINUSE :::3000" }
  ],
  "env": {
    "node": "20.11.0",
    "package_manager": "pnpm"
  }
}

AI는 무엇이 문제인지 물어볼 필요 없이 이미 파악하고 있습니다.

Related MCP server: AI Knowledge Center MCP

설정

Claude Code

claude mcp add devpulse -- npx -y devpulse-mcp

Cursor / Claude Desktop / Windsurf

{
  "mcpServers": {
    "devpulse": {
      "command": "npx",
      "args": ["-y", "devpulse-mcp"]
    }
  }
}

API 키, 계정, 설정 파일이 필요 없습니다.

도구

  • get_session_snapshot — 전체 진단 스냅샷, 가장 먼저 호출하세요

  • get_recent_errors — 로그 파일의 최근 오류 (보안 정보는 마스킹됨)

  • get_running_services — 개발 포트에서 실행 중인 서비스 및 누락된 서비스 확인

지원되는 프레임워크

package.json에서 자동으로 감지 — Next.js, Vite, Express, FastAPI 등. 더 많은 프레임워크가 추가될 예정입니다.

개인정보 보호

사용자의 컴퓨터에서 완전히 실행됩니다. 어떤 데이터도 외부로 유출되지 않습니다. API 키와 보안 정보는 로그 출력에서 자동으로 제거됩니다.

라이선스

MIT

Available Tools

3 tools
get_recent_errorsA

Returns recent ERROR and WARN log entries from the detected project's log files. Deduped, timestamped, secrets redacted. Defaults to last 50 lines.

ParametersJSON Schema
NameRequiredDescriptionDefault
cwdNo
limitNo

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description covers key behaviors: returns only ERROR/WARN, deduped, timestamped, secrets redacted, defaults to last 50 lines. It does not mention idempotency or side effects, but as a read operation this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences are concise and front-loaded with the tool's purpose. Every word adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and lack of output schema, the description covers core functionality and features. It lacks detail on return format or real-time behavior, but it is largely sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage. The description mentions 'Defaults to last 50 lines' explaining the limit parameter, but 'cwd' (current working directory) is not explained. It adds some value beyond the bare schema but leaves ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns ERROR and WARN log entries with dedup, timestamping, and secret redaction. It distinguishes itself from sibling tools (get_running_services, get_session_snapshot) which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving recent log errors/warnings but does not explicitly state when to use this tool versus alternatives or provide exclusions. No guidance on prerequisites or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_running_servicesB

Lists processes running on common dev ports (3000, 4000, 5173, 8080 etc). Shows what is running and what is expected but missing.

ParametersJSON Schema
NameRequiredDescriptionDefault
cwdNo

TDQS

B3.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool shows running and missing processes on specific ports, but does not mention side effects, permissions, or any limitations beyond the listed ports.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two clear sentences with no redundant information. Each sentence adds value: first states what it does, second adds the expected-but-missing aspect.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of output schema and minimal parameter documentation, the description omits important details such as return format, what 'expected but missing' means, and how the cwd parameter affects the output. More context would be beneficial for a complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has one parameter (cwd) with no description, and schema description coverage is 0%. The description does not explain what cwd does or how it affects the results, leaving the agent with no guidance on its usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('lists') and resource ('processes on common dev ports'), and distinguishes the tool from siblings by focusing on a specific set of ports and including expected but missing processes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for checking processes on common dev ports, but does not explicitly state when to use it versus alternatives like get_recent_errors or get_session_snapshot, nor does it provide any exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_session_snapshotA

Returns a real-time diagnostic snapshot of the current dev environment. Includes health diagnosis, running services, recent errors, git state, and environment info. Call this first to orient yourself in the user's dev session.

ParametersJSON Schema
NameRequiredDescriptionDefault
cwdNo

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It states it returns a snapshot, implying read-only and non-destructive. However, it does not explicitly mention permissions or side effects, though 'snapshot' strongly suggests a safe operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences: first states action, second lists contents, third gives usage advice. No redundancy, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Well-structured but lacks parameter documentation. With no output schema, the description lists return categories but omits format details. The missing parameter explanation is a notable gap for a tool with one parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has one optional parameter 'cwd' with no description and 0% schema coverage. The tool description does not mention this parameter, leaving the agent without guidance on its purpose or usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it returns a real-time diagnostic snapshot of the current dev environment, listing specific contents. It distinguishes from siblings get_recent_errors and get_running_services as a broader orientation tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to 'Call this first to orient yourself in the user's dev session,' providing clear guidance on when to use this tool versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.0
    • First observedget_recent_errors
    • First observedget_running_services
    • First observedget_session_snapshot
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A3.7/5.0

Scored across 3 tools

Disambiguation3/5

The tools have overlapping information: get_session_snapshot includes recent errors and running services, making it redundant with the other two. Descriptions help clarify usage order, but ambiguity remains.

Naming Consistency5/5

All tools follow a consistent 'get_' prefix with clear noun phrases, forming a predictable and readable pattern.

Tool Count4/5

Three tools is on the low side for a dev diagnostic server, but the snapshot tool consolidates key info, making the count reasonable for basic orientation.

Completeness4/5

The set covers errors, services, and a broad snapshot (git, env, health). Minor gaps like detailed log history or dependency checks exist, but core diagnostics are present.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-devenv

    dicoy
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that gives your AI assistant full awareness of your local dev environment — running processes, Docker containers, git state, open ports, log files, and more.
    6 npm
    1
    MIT

  • itaca

    Lukapetro
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first MCP server that indexes all projects on your machine and provides coding agents with briefings about each project's stack, services, and run instructions, so they can start sessions with context across all repos. No cloud, no accounts, no telemetry.
    12 npm
    MIT