MCP.Market

Openharness MCP server

by philo-kim·io.github.philo-kim/openharness·v0.1.1
No reviews yet

Lets AI coding agents discover and reference each other's recent sessions.

B75/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
New

0 stars37 downloads/wk

Reviews

Write one

Nobody has reviewed Openharness yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Openharness tools (2)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_agent_session

    Returns the recent session path for a specific AI coding agent, filtered by the given project directory. The returned path can be read directly to access the full conversation history.

  • get_agent_sessions

    Returns recent session paths for all connected AI coding agents (…), filtered by the given project directory. Each agent can then read the returned path directly to access the full conversation history.

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan15 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 195 days ago4/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Openharness compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 45% of 48,255 servers
Tools
2
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
37
more than 28% of 12,191 servers with a package

What its tools let an agent do: 2 read

Install Openharness in Claude Code, Cursor or VS Code

Runs npx -y @freebird-ai/openharness on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add openharness -- npx -y @freebird-ai/openharness
Add to Cursor

What the publisher says

From the Openharness repository's README, as published. We do not edit it. Read it on GitHub

OpenHarness

AI 코딩 에이전트의 최근 세션 파일을 찾아 서로 참조하게 해주는 로컬 MCP 서버.

전용 하네스 없이 하네스처럼 동작한다. 기존 도구 환경을 그대로 유지하면서, 에이전트 간 세션을 연결하는 디스커버리 레이어.

Supported Agents (MVP)

Prerequisites

  • Each agent must be able to read local files directly.
  • OpenHarness only provides paths and metadata — it does not transform, relay, or store session content.

Install

npm install -g @freebird-ai/openharness
openharness init

This registers OpenHarness as an MCP server in each agent's config.

MCP Tools

getagentsessions

Returns recent session paths for all agents, filtered by project.

Input:

{ "project": "/Users/me/my-app" }

Output:

[
  {
    "agent": "claude-code",
    "path": "/Users/me/.claude/projects/-Users-me-my-app/session.jsonl",
    "format": "jsonl",
    "updatedAt": "2026-03-17T14:32:00Z",
    "matchedProject": "/Users/me/my-app",
    "matchedBy": "directory-name"
  }
]

getagentsession

Returns the recent session path for a specific agent.

Input:

{ "agent": "claude-code", "project": "/Users/me/my-app" }

Output:

{
  "agent": "claude-code",
  "path": "/Users/me/.claude/projects/-Users-me-my-app/session.jsonl",
  "format": "jsonl",
  "updatedAt": "2026-03-17T14:32:00Z",
  "matchedProject": "/Users/me/my-app",
  "matchedBy": "directory-name"
}

Returns null if no session is found.

Project Matching

How It Works

User → Codex: "Review what Claude Code worked on recently"

Codex → OpenHarness MCP: get_agent_session({ agent: "claude-code", project: "..." })
Codex ← receives session path + metadata
Codex → reads the JSONL file directly and performs review

No rules needed in agent instruction files. MCP tool descriptions are enough for agents to use naturally.

Manual MCP Configuration

If you prefer to configure manually instead of using init:

{
  "mcpServers": {
    "openharness": {
      "command": "openharness",
      "args": []
    }
  }
}

Add this to your agent's MCP config file:

License

MIT

Nothing above is checked by us. What we check is on the safety report.

Openharness: common questions

Is Openharness MCP server safe?
Mostly: it is graded B (75/100). Read the Openharness safety report
How do I install Openharness?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Openharness need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Openharness maintained?
The last commit was 232 days ago (2026-03-17). The latest release is v0.1.1.
What can I use instead of Openharness?
Servers from other publishers that do the same job: Inspo MCP server and Deja Vu MCP server.
How does Openharness compare with other MCP servers?
safety score 75/100 (higher than 45% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Openharness

Same job from other publishers: the closest match first, then the best rated.

  • Inspo
    Real production websites for coding agents: palettes, fonts, fold autopsies and reference JSX.
    A
  • Deja Vu
    deja-vu: local memory over the session histories of forty-three coding agents.
    A