AnubisCAUTION
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Transform your AI agent from chaotic coder to intelligent workflow orchestrator with three powerful capabilities:
Three Pillars of Intelligent Workflow Management
Intelligent Guidance | Seamless Transitions | Repository Pattern Architecture
[](https://github.com/hive-academy/anubis) [](https://github.com/hive-academy/anubis) [](https://github.com/hive-academy/anubis)
[](https://hub.docker.com/r/hiveacademy/anubis)
[NPM Package](https://www.npmjs.com/package/@hive-academy/anubis) • [Docker Hub](https://hub.docker.com/r/hiveacademy/anubis) • [Website](https://hive-academy.github.io/Anubis-MCP/)
QUICK START
Option 1: NPX (Recommended)
Add to your MCP client config
{
"mcpServers": {
"anubis": {
"command": "npx",
"args": ["-y", "@hive-academy/anubis"],
"env": {
"PROJECT_ROOT": "C:\\path\\to\\projects"
}
}
}
}Option 2: Docker (MCP Configuration)
For Unix/Linux/macOS (mcp.json):
{
"mcpServe2990f578d1e0OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add anubis -- npx -y @hive-academy/[email protected]
{
"mcpServers": {
"anubis": {
"command": "npx",
"args": [
"-y",
"@hive-academy/[email protected]"
]
}
}
}Exposed tools (16)
11 read · 5 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
architect | read | Architect role |
bootstrap_workflow | read | Initializes a new workflow execution with product-manager role, starting from git setup through task creation and delegation. |
execute_research_operation | write | Execute research operations including create, update, get, and list operations for research reports |
execute_review_operation | write | Execute review operations including create, update, get for code reviews and completion reports |
execute_transition | write | Executes role transition and returns execution status with essential details for next steps. |
get_role_transitions | read | Gets available role transitions with recommendations, scores, and basic requirements for workflow progression. |
get_step_guidance | read | Provides focused guidance for executing the current workflow step, including commands and validation checklist. |
get_step_progress | read | Get concise step progress focused on essential status information for workflow continuation. |
get_workflow_guidance | read | Provides minimal role identity and basic capabilities for workflow execution. |
individual_subtask_operations | write | Execute individual subtask operations including creation, updates, dependency tracking, and batch management with evidence collection |
init_rules | read | Initialize Anubis workflow rules to specified AI agent (cursor or copilot) |
product-manager | read | Test role |
report_step_completion | read | Report step completion results with structured data and get next step guidance. |
task_operations | write | Execute task lifecycle operations (create, update, get, list) with comprehensive task management capabilities. |
validate_transition | read | Validates role transition requirements and provides pass/fail status with actionable feedback. |
workflow_execution_operations | read | Manages workflow execution state through strongly-typed operations for creating, querying, updating, and completing workflow executions. Handles execution context and progress tracking with validated parameters. |
Trust audit
CAUTIONgrade B · trust 82/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (2 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (12)
workflow.db
- DATABASE_URL=postgresql://workflow:secure_password@postgres:5432/workflow_db
streamable-http
.kilocodemodes
.lintstagedrc.json
.roomodes
import { CodeReview, Prisma } from '../../../../../generated/prisma';import { PrismaService } from '../../../../prisma/prisma.service';import { CompletionReport, Prisma } from '../../../../../generated/prisma';import { PrismaService } from '../../../../prisma/prisma.service';import { DelegationRecord, Prisma } from '../../../../../generated/prisma';@modelcontextprotocol/sdk, @nestjs/common, @nestjs/config, @nestjs/core, @nestjs/platform-express, @prisma/adapter-better-sqlite3, @prisma/client, @rekog/mcp-nest
Gates applied: no_behavioural_pass.
2990f578d1e0full audit observations/trust-audit/mcp-server/hive-academy__anubis.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 2990f578d1e0 | CAUTION | B | 82 | first audit |
Questions
What tools does Anubis expose?
16 in total: 11 read-only, 5 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Anubis safe to connect to an agent?
With care. The audit graded it B (82/100) and found 12 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Anubis need?
No credential environment variables were found in its source, so it appears to need none.
How does Anubis run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @hive-academy/anubis at 1.2.26.
How current is this page?
The grade is for one exact copy of the source (2990f578d1e0), read on 2026-10-07. The repository is watched and re-audited when it changes.