# io.github.imran-siddique/agentos (npm · agentos-mcp-server)

Build and manage policy-compliant AI agents with safety enforcement and compliance checking

- Trust score: 60/100 (medium)
- Change this week: +9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `agentos-mcp-server`: 60/100 (this document), [markdown](https://verifymcp.io/servers/imran-siddique-agentos/agentos-mcp-server.md), [page](https://verifymcp.io/servers/imran-siddique-agentos/agentos-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `agentos-mcp-server`
- Version: `1.0.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects uuid 9.0.1, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (123 of 127), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 181 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1591 tokens (~159/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add imran-siddique-agentos -- npx -y agentos-mcp-server
```

### Codex

```bash
codex mcp add imran-siddique-agentos -- npx -y agentos-mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "imran-siddique-agentos": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agentos-mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add imran-siddique-agentos --command npx --arg -y --arg agentos-mcp-server
```

### Hermes

```yaml
mcp_servers:
  imran-siddique-agentos:
    command: "npx"
    args: ["-y", "agentos-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "imran-siddique-agentos": {
      "command": "npx",
      "args": [
        "-y",
        "agentos-mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 60, +35)

- [security regression] CVE-2026-41907 affects this package: high
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT

### 2026-07-31 (score 25, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 24, −27)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified

### 2026-07-27 (score 51)

First indexed and scored.

## MCP tools (10)

### `create_agent` (~189 tokens)

Create a new AI agent from a natural language description. The agent will be configured with appropriate policies and safety guardrails.

Example usage:
\- "Create an agent that processes customer feedback from support emails daily"
\- "Build a data pipeline that backs up my Documents folder to Google Drive"
\- "Set up an agent to monitor our API health and alert on issues"

Returns the agent specification with recommended safety policies.

Input parameters:

- `approvalRequired` (boolean): Whether human approval is required before execution
- `description` (string, required): Natural language description of what the agent should do
- `language` (string): Programming language for the agent
- `policies` (array): Policy templates to apply (e.g., "pii-protection", "rate-limiting")
- `schedule` (string): Cron schedule for recurring execution (e.g., "0 9 * * *" for daily at 9 AM)

### `attach_policy` (~210 tokens)

Attach safety policies to an agent. Policies enforce rules and constraints on agent behavior.

Available policy templates:
\- pii-protection: Protects personally identifiable information (GDPR compliant)
\- rate-limiting: Prevents resource abuse through rate limits
\- cost-control: Prevents runaway costs from automated operations
\- data-deletion: Prevents accidental data loss
\- secrets-protection: Prevents exposure of secrets and credentials
\- human-review: Requires human approval for sensitive actions

Compliance frameworks:
\- gdpr-compliance: EU data protection compliance
\- soc2-security: SOC 2 Type II security controls
\- hipaa-healthcare: Healthcare data privacy (PHI protection)
\- pci-dss-payments: Payment card data security

Input parameters:

- `agentId` (string, required): Agent ID to attach policy to
- `customRules` (array): Additional custom rules to add
- `policyId` (string, required): Policy template ID (e.g., "pii-protection", "gdpr-compliance")

### `test_agent` (~133 tokens)

Test an agent with a simulated scenario before deployment. 

This performs a dry-run that:
\- Validates the agent configuration
\- Checks all policies against the test scenario
\- Simulates workflow execution
\- Reports any policy violations or issues
\- Estimates resource usage and costs

No actual changes are made during testing.

Input parameters:

- `agentId` (string, required): Agent ID to test
- `dryRun` (boolean): Run without side effects (default: true)
- `mockData` (object): Mock data for testing (optional)
- `scenario` (string, required): Test scenario description (e.g., "Process 100 customer emails")

### `deploy_agent` (~118 tokens)

Deploy an agent to start execution.

Deployment environments:
\- local: Runs on your machine (default)
\- cloud: Runs on AgentOS cloud infrastructure (requires API key)

Before deployment, the agent must:
\- Pass all policy checks
\- Have valid configuration
\- Have necessary integrations configured

For scheduled agents, deployment starts the scheduler.
For triggered agents, deployment enables the triggers.

Input parameters:

- `agentId` (string, required): Agent ID to deploy
- `autoStart` (boolean): Start agent immediately after deployment
- `environment` (string): Deployment environment

### `get_agent_status` (~100 tokens)

Get the current status, metrics, and health of an agent.

Returns:
\- Current status (draft, testing, deployed, paused, stopped, error)
\- Execution metrics (runs, success rate, errors)
\- Recent activity
\- Policy compliance stats
\- Resource usage

Input parameters:

- `agentId` (string, required): Agent ID to get status for
- `includeLogs` (boolean): Include recent logs
- `includeMetrics` (boolean): Include execution metrics

### `list_templates` (~178 tokens)

Browse the library of pre-built agent and policy templates.

Agent templates include:
\- Data processors, email assistants, database analysts
\- File organizers, backup agents, web scrapers
\- Slack bots, API monitors, report generators

Policy templates include:
\- Security: PII protection, secrets protection, data deletion safety
\- Compliance: GDPR, SOC 2, HIPAA, PCI DSS
\- Operational: Rate limiting, cost control, human review

Use templates as a starting point for your custom agents.

Input parameters:

- `category` (string): Filter by category (e.g., "data", "security", "compliance")
- `framework` (string): Filter by compliance framework (e.g., "GDPR", "SOC2")
- `search` (string): Search query to filter templates
- `type` (string): Template type to list

### `request_approval` (~165 tokens)

Request human approval for a sensitive agent action.

Use this when:
\- Policy requires human review before execution
\- Agent attempts a high-risk action
\- You want to add an extra safety check

Approval requests are sent to designated approvers via:
\- Email notification
\- Slack notification (if configured)
\- Dashboard alert

Requests expire after the specified time (default: 24 hours).

Input parameters:

- `action` (string, required): Action requiring approval (e.g., "delete_files", "send_email")
- `agentId` (string, required): Agent ID requesting approval
- `approvers` (array, required): Email addresses of approvers
- `description` (string, required): Detailed description of what will happen if approved
- `expiresInHours` (number): Hours until approval expires (default: 24)

### `audit_log` (~151 tokens)

Query the audit trail for an agent.

The audit log records:
\- Every action attempted by the agent
\- Policy evaluations and decisions
\- Approval requests and outcomes
\- Success/failure status
\- Timestamps and metadata

Use for:
\- Debugging agent behavior
\- Compliance reporting
\- Security investigations
\- Performance analysis

Input parameters:

- `actionFilter` (string): Filter by action type
- `agentId` (string, required): Agent ID to get audit log for
- `endTime` (string): End of time range (ISO 8601)
- `limit` (number): Maximum entries to return (default: 100)
- `startTime` (string): Start of time range (ISO 8601)

### `create_policy` (~173 tokens)

Create a custom policy from a natural language description.

Policies define rules that agents must follow. Example policies:
\- "Block access to customer credit card data"
\- "Require approval for any external API calls"
\- "Rate limit database queries to 100 per minute"
\- "Log all file deletions"

Policies can be based on existing templates:
\- pii-protection, rate-limiting, cost-control
\- gdpr-compliance, soc2-security, hipaa-healthcare

The policy engine will translate your description into enforceable rules.

Input parameters:

- `basedOn` (string): Policy template to extend
- `category` (string, required): Policy category
- `description` (string, required): Natural language policy description
- `framework` (string): Compliance framework (e.g., "SOC2", "GDPR", "HIPAA")

### `check_compliance` (~174 tokens)

Check an agent's compliance with regulatory frameworks.

Supported frameworks:
\- SOC2: Service Organization Control 2 Type II
\- GDPR: EU General Data Protection Regulation
\- HIPAA: Health Insurance Portability and Accountability Act
\- PCI_DSS: Payment Card Industry Data Security Standard
\- CCPA: California Consumer Privacy Act
\- NIST: NIST Cybersecurity Framework
\- ISO27001: ISO/IEC 27001 Information Security
\- FEDRAMP: Federal Risk and Authorization Management Program

The compliance check evaluates:
\- Policy coverage for framework requirements
\- Audit trail completeness
\- Access control implementation
\- Data protection measures

Input parameters:

- `agentId` (string, required): Agent ID to check
- `framework` (string, required): Compliance framework to check against
- `generateReport` (boolean): Generate detailed compliance report

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/imran-siddique-agentos/agentos-mcp-server#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 60
- 2026-08-01: 25
- 2026-07-31: 25
- 2026-07-30: 24
- 2026-07-28: 51
- 2026-07-27: 51

## Links

- npm package: https://www.npmjs.com/package/agentos-mcp-server
- Socket report: https://socket.dev/npm/package/agentos-mcp-server
- Repository: https://github.com/imran-siddique/agent-os
- Changelog RSS feed: https://verifymcp.io/servers/imran-siddique-agentos/agentos-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/imran-siddique-agentos/agentos-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/imran-siddique-agentos/agentos-mcp-server