# @uluops/ops-mcp [Health: Active]

**Category:** 📋 Product Management  
**Repository:** https://github.com/Uluops/-uluops-ops-mcp  
**GitHub Stars:** 0  
**npm Downloads (last month):** 1437  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/uluops-ops-mcp

## Description
MCP server for the UluOps tracker API — runs, findings, issues, analytics, the project log and org management

## Tools
Capabilities this server exposes over MCP:

- **save_run** — Save validation pipeline output with issue correlation
- **query_issues** — Query issues with filtering by status, priority, validator
- **update_status** — Update issue status (completed, deferred, wontfix)
- **get_project_summary** — Get project overview with workflow and validator stats
- **delete_project** — Delete project data (requires confirmation)
- **create_issue** — Create a user-submitted issue directly (outside validation runs)
- **get_issue_details** — Full issue lifecycle with occurrences, notes, history
- **get_run_details** — Run information with all recommendations and stats
- **diff_runs** — Compare two validation runs (fixed, new, unchanged issues)
- **archive_runs** — Archive old runs without deletion
- **get_analytics** — Eight metrics; list metrics support negotiated `format=page` with totals and implementation metadata. Legacy shapes and limit20 default remain.
- **search_issues** — Search issues across projects with relevance ranking
- **list_agents** — Discover agent names recorded in run history; default lists the full 30-day result, `format=page` opts into filters and paging
- **validate_run** — Preview save operation without modifying database
- **get_issue_history** — Merged audit-event stream (occurrences, status, notes) as an envelope `{issueId, events[], totalEvents, truncated}` — includes undo tombstones (v0.4.0+)
- **add_issue_note** — Add context, resolution, or blocker notes to issues
- **edit_issue** — Edit issue metadata (title, file_path, severity, etc.)
- **merge_issues** — Merge duplicate issues into a target issue
- **bulk_update_status** — Bulk update multiple issue statuses in one transaction, by issue UUID across the org (`project` is informational, not a scope)
- **update_run** — Enrich run telemetry and set unrecorded score/gate fields; identity and timestamp are immutable; changing an already recorded `averageScore` or `allGatesPassed` is refused with `FINALIZED_RUN_FIELD_IMMUTABLE`. Per-agent analysis writes use replace (default) or merge via `record_write_mode`; analysi…
- **preview_update_run** — Read-only preview of an analysis-bearing update under the requested mode (metadata and quality edits are not previewed): per agent, what the write would supersede, create, and (replace only) retire
- **get_agent_reliability** — Analyze agent effectiveness: false-positive, declined (wontfix) and resolution rates plus reliability score
- **get_agent_lifecycle** — Lifecycle metrics for an agent across runs
- **list_projects** — List all active projects
- **get_project** — Get a single project by ID or name
- **get_project_trends** — Get issue trends over time for a project
- **create_project** — Create a new project
- **update_project** — Update a project name
- **soft_delete_project** — Soft delete a project (can be restored later)
- **restore_project** — Restore a soft-deleted project
- **update_profile** — Update the authenticated user's profile (username, name, bio, timezone, websiteUrl). Setting `username` confirms it **one-time** — required before creating or publishing registry definitions
- **merge_projects** — Merge one project into another — runs and issues re-keyed into the target, colliding issues deduplicated by fingerprint, source soft-deleted. Durable (no undo) — always `dry_run` first
- **rehome_project** — Move a project and its whole history into another org (project-org-routing-and-rehome §4.1). **`org` is the SOURCE** (where the project is now), `target_org` the destination; admin/owner in both. The old `(org, name)` becomes a `410 PROJECT_REHOMED` tombstone, not a fork; reversible by moving back.…
- **get_org_audit_feed** — Read an org's member-visible audit feed (D19): today, projects that left the org for someone's personal org — who, when, where to. `org` names the org whose feed to read (required in effect). Each re-home entry carries a one-line `summary`; the operator's `reason` is redacted; page with `nextCursor…
- **get_project_log** — One page of the project log: `run` (what was examined), `decision` (what was decided, with reasons) and `regression` (what a run re-detected) events interleaved newest first; keyset-paged — pass `nextCursor` back as `cursor`. Optional `format: "actionable"` negotiates `projectLog/actionable-v1` thr…
- **get_log_stat** — The rollup — examined / found / decided / cameBack / activity — for `project` when given, else for the org the call resolves to (`org`, else the workspace default, else your personal org — looked up, never guessed). Two frames on two clocks: `decided` is the *current* status of the window's finding…
- **get_run** — Get a run by UUID
- **list_runs** — List runs for a project
- **get_latest_run** — Get the latest run for a project; `{ run: null, message }` when it has none yet
- **delete_run** — Permanently delete a run (`confirm: true` required — false or missing is refused by the schema, nothing is sent)
- **get_issue_by_fingerprint** — Get an issue by its SHA-256 fingerprint
- **update_issue_by_fingerprint** — Update an issue status by its fingerprint
- **restore_issue** — Restore a soft-deleted issue
- **soft_delete_issue** — Soft delete an issue (can be restored later)
- **undo_issue_status** — Undo the last status change on an issue
- **get_taxonomy** — Get the failure taxonomy schema (domains, modes, severities)
- **get_full_taxonomy_analytics** — Get full taxonomy analytics with distribution by domain
- **get_burndown** — Get taxonomy burndown with time series and trend analysis per failure domain
- **get_velocity** — Get velocity metrics per failure mode with sparkline data and trend reliability
- **get_discovery** — Get discovery timeline showing new vs recurring issues over time
- **get_agent_matrix** — Get agent-taxonomy coverage matrix with blind spot detection. `minIssues` filters rows by total qualifying issues per agent (default 5). `effectiveMinIssues` and `eligibility` explain the applied threshold and excluded rows. Single-point/overlap analysis uses canonical modes before threshold filter…
- **get_run_analysis** — Structured analysis records for a single run (decision, scoring, findings)
- **get_project_analysis** — Aggregated analysis records across all runs in a project
- **query_analysis_records** — Query analysis records by type, classification, severity
- **get_agent_runs_analysis** — Per-run analysis records grouped by agent

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "ops-mcp": {
    "command": "npx",
    "args": ["-y","@uluops/ops-mcp"]
  }
}
```

## Documentation

## 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:

```bash
npx -y @uluops/ops-mcp
```

Alternatively, install it globally:

```bash
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.

_Full upstream README: https://allmcps.com/mcp/uluops-ops-mcp/readme_