Log inSubmit server
Ops MCP logo

Ops MCP

by @uluops

Connects AI agents to the UluOps tracker for managing runs, issues, analytics, projects, and organization data.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Ops MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "uluops-ops-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@uluops/ops-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command installed and started the server, which then stopped for configuration (such as an API key) that our sandbox does not have — expected for servers that connect to your account.

npx -y @uluops/ops-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked Today.

Overview

@uluops/ops-mcp exposes the UluOps tracker API through MCP tools for runs, findings, issues, analytics, projects, and organization management. It translates MCP stdio JSON-RPC requests into REST API calls and keeps business logic in the backend. Use it when an agent needs to inspect validation history, record pipeline results, manage issue lifecycles, or analyze agent reliability. The package supports Claude Code, Claude Desktop, Codex, Cursor, and other MCP hosts.

Use cases

  • Record validation pipeline results in the UluOps tracker
  • Search and triage issues across projects
  • Compare runs to identify fixed and newly introduced findings
  • Measure agent reliability and lifecycle outcomes
  • Manage project creation, restoration, and archival workflows

Key features

  • Run validation, comparison, archival, and telemetry updates
  • Issue search, history, notes, editing, merging, and bulk status changes
  • Project summaries, trends, analytics, and organization management
  • Agent discovery, reliability scoring, and lifecycle metrics
  • Read-only previews for save and analysis-update operations
  • MCP stdio JSON-RPC to UluOps REST API translation

Tools55

What Ops MCP lets your agent do. Expand a tool for its parameters.

Self-reported~1.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9h ago via OSV.dev · @uluops/ops-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads1.4kPackage downloads in the last 30 days.
Last commit8d agoMost recent push to the default branch.
Install checkRunsOur sandbox started it; it then asked for an API key or config.
Tools exposed55Callable tools this server registers over MCP.

How Ops MCP works

What @uluops/ops-mcp does

@uluops/ops-mcp gives MCP-compatible agents access to the UluOps tracker API. Its toolset covers validation runs, issue records, project management, analytics, agent metrics, and organization-level operations. Agents can save or preview run results, inspect recommendations and issue history, update or merge issues, and compare runs to identify fixed, new, and unchanged findings.

Project operations include listing, creating, renaming, soft-deleting, restoring, and retrieving projects. The tracker-facing toolset also includes project summaries, trends, agent discovery, reliability analysis, and lifecycle metrics. Organization-oriented operations include bulk issue status changes across the organization, while project deletion requires confirmation.

How it works

The package follows a thin-client design. It does not implement tracker validation, storage, analytics, or other business rules locally. Instead, it translates MCP's stdio JSON-RPC messages into requests to the UluOps REST API and returns the API responses to the MCP host.

Run-related tools preserve agent execution metadata and optional token counters when those values are supplied. Analysis-bearing operations support agent attribution, including agent names and types, while preview tools allow an agent to inspect the effect of a write before changing tracker data. validate_run previews a save, and preview_update_run shows analysis records that would be replaced, created, or retired under the requested write mode.

Setup and configuration

Node.js 20.3 or later is required. The package can be run without a global installation:

Terminal
npx -y @uluops/ops-mcp

Alternatively, install it globally:

Terminal
npm install -g @uluops/ops-mcp

The global installation provides the uluops-ops-mcp executable on the system path. Register that command with an MCP host, then restart the host's tracker connection after upgrades so it loads the new server and tool schemas. The server is intended for stdio-based MCP connections.

Tools and capabilities

The available operations include:

  • Save, validate, update, inspect, archive, and compare validation runs.
  • Query, search, create, edit, merge, and inspect issues.
  • Add notes, retrieve merged issue history, and update statuses individually or in bulk.
  • Review project summaries, trends, analytics, and validator statistics.
  • Measure agent reliability and lifecycle performance across runs.
  • Create, update, soft-delete, restore, list, and retrieve projects.
  • Discover agents recorded in run history and access project-log and organization-audit operations.

Analytics list responses can negotiate a paged format with totals and implementation metadata. Search results use relevance ranking, while issue history is returned as an event envelope that can include occurrences, status changes, notes, and undo tombstones.

Limitations and notes

The server depends on the UluOps tracker API for processing, validation, persistence, and analytics. It is therefore a protocol adapter rather than an independent tracker implementation. Write operations can modify or delete tracker data: project deletion requires confirmation, and soft deletion should be used when later restoration may be needed.

Run analysis has attribution rules. Registered agents use their saved execution-version type, while unregistered agents may declare a type. Multi-agent entries without an agent name can be stored under the run's default name, so callers should provide attribution when it matters. update_run does not change immutable run identity or timestamp fields and refuses changes to already recorded score or gate fields. Preview tools are available for checking save and analysis-update effects before committing them.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Ops MCP

@uluops/ops-mcp is an MCP server that connects AI agents to the UluOps tracker API. Its main tools manage validation runs, issues, projects, analytics, and agent metrics, including saving and previewing runs, searching and updating issues, comparing runs, and measuring agent reliability.

Install it with `npx -y @uluops/ops-mcp` or run `npm install -g @uluops/ops-mcp`. The global installation provides the `uluops-ops-mcp` command. Node.js 20.3 or later is required, and the MCP host connection should be restarted after upgrades.

Yes, @uluops/ops-mcp is documented for use with Cursor. It uses an MCP stdio connection, so register the server command with the client and restart the connection after changing the installation.

Yes, `validate_run` previews a run-save operation and `preview_update_run` previews an analysis-bearing update. The update preview reports records that would be superseded, created, or retired according to the requested write mode.

Related MCP servers

All in Product Management All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewOps MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/uluops-ops-mcp?style=directory)](https://allmcps.com/mcp/uluops-ops-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/uluops-ops-mcp"><img src="https://allmcps.com/api/badge/uluops-ops-mcp?style=directory" alt="Ops MCP on AllMCPs" /></a>