Agentos

io.github.imran-siddiquePublished by GitHub account imran-siddiquev1.0.1Updated Oct 24, 2026

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

VerifiedSTDIODesktop onlyDeveloper Tools Security & Monitoring AI & ML

Server details

Identifier: io.github.imran-siddique/agentos
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account imran-siddique for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.imran-siddique%2Fagentos.svg)](https://sourceweft.com/mcp/io.github.imran-siddique%2Fagentos?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A local MCP server for creating, testing, deploying and auditing policy-compliant AI agents with built-in safety policies and compliance checks.

What you can do: Create and manage agents: build agents from natural-language descriptions, attach safety policies, test them in dry-run mode, deploy locally or to cloud, and check status and metrics. Policies: create custom policies from descriptions and browse built-in policy and compliance templates. Approvals: raise approval requests for sensitive actions. Audit and compliance: query the audit trail and check agents against frameworks such as SOC 2, GDPR, HIPAA and PCI DSS. Templates: browse agent and policy template libraries.
When to use it: Useful when you want an assistant to scaffold autonomous agents with guardrails, run dry-run tests before deployment, or produce audit and compliance reports for agent workflows. Less relevant if you only need a single simple tool call.
Requirements: Runs locally over stdio, typically via npx agentos-mcp-server, so Node.js is needed. Optional environment variables: AGENTOS_POLICY_MODE (strict or permissive), AGENTOS_LOG_LEVEL, AGENTOS_DATA_DIR, and AGENTOS_API_KEY for cloud features. Data is stored locally in the data directory by default.

Before you install

Deploying agents can start automation that acts on real data, including email, files, databases and cloud storage; test in dry-run mode first. Policy mode permissive only warns on violations, so strict is safer. AGENTOS_API_KEY is requested for cloud features. Audit logs and agent configurations are written to the local data directory.

Installation

In SourceWeft

Open Agentos in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AgentOS MCP Server

Build safe AI agents with natural language and 0% policy violations

[Image]

[npm version] [MCP Registry] [License: MIT]

Part of Agent OS - Kernel-level governance for AI agents

🚀 Quick Install

npm: agentos-mcp-server
MCP Registry: io.github.imran-siddique/agentos

Overview

AgentOS MCP Server brings the complete Agent OS safety framework to any MCP-compatible AI assistant including Claude Desktop, GitHub Copilot, Cursor, and more. Create, deploy, and manage policy-compliant autonomous agents through natural conversation.

┌─────────────────────────────────────────────────────────────┐│           Claude Desktop / Copilot / Cursor                  ││  ┌────────────────────────────────────────────────────────┐ ││  │            "Create an agent that..."                    │ ││  └──────────────────────┬─────────────────────────────────┘ │└─────────────────────────┼───────────────────────────────────┘                          │ MCP Protocol            ┌─────────────▼─────────────┐            │   🛡️ AgentOS MCP Server   │            │                           │            │  • 10 Tools              │            │  • Policy Engine         │            │  • Approval Workflows    │            │  • Audit Logging         │            │  • Template Library      │            └─────────────┬─────────────┘                          │      ┌───────────────────┼───────────────────┐      │                   │                   │┌─────▼─────┐      ┌──────▼──────┐     ┌─────▼─────┐│  Agents   │      │  Policies   │     │  Audit    ││  (Local)  │      │  (Enforced) │     │  (Logged) │└───────────┘      └─────────────┘     └───────────┘

┌─────────────────────────────────────────────────────────────┐│           Claude Desktop / Copilot / Cursor                  ││  ┌────────────────────────────────────────────────────────┐ ││  │            "Create an agent that..."                    │ ││  └──────────────────────┬─────────────────────────────────┘ │└─────────────────────────┼───────────────────────────────────┘                          │ MCP Protocol            ┌─────────────▼─────────────┐            │   🛡️ AgentOS MCP Server   │            │                           │            │  • 10 Tools              │            │  • Policy Engine         │            │  • Approval Workflows    │            │  • Audit Logging         │            │  • Template Library      │            └─────────────┬─────────────┘                          │      ┌───────────────────┼───────────────────┐      │                   │                   │┌─────▼─────┐      ┌──────▼──────┐     ┌─────▼─────┐│  Agents   │      │  Policies   │     │  Audit    ││  (Local)  │      │  (Enforced) │     │  (Logged) │└───────────┘      └─────────────┘     └───────────┘

✨ Features

🤖 Natural Language Agent Creation

User: Create an agent that processes customer feedback from support emails daily
Claude: ✅ Agent Created Successfully!
Agent: customer-feedback-processor✅ Data Source: Email inbox via IMAP✅ Processing: Sentiment analysis + categorization✅ Output: Daily summary to Slack✅ Schedule: Every day at 9 AM
Safety Policies Applied:🛡️ PII Protection: Customer emails/names anonymized🛡️ Rate Limiting: Max 1000 emails per run🛡️ Human Review: Negative sentiment cases flagged

User: Create an agent that processes customer feedback from support emails daily
Claude: ✅ Agent Created Successfully!
Agent: customer-feedback-processor✅ Data Source: Email inbox via IMAP✅ Processing: Sentiment analysis + categorization✅ Output: Daily summary to Slack✅ Schedule: Every day at 9 AM
Safety Policies Applied:🛡️ PII Protection: Customer emails/names anonymized🛡️ Rate Limiting: Max 1000 emails per run🛡️ Human Review: Negative sentiment cases flagged

🛡️ Policy Enforcement with 0% Violations

6 built-in policies (PII, rate-limiting, cost-control, data-deletion, secrets, human-review)
Real-time policy evaluation
Automatic blocking of violations
Clear explanations and alternatives

✅ Human-in-the-Loop Approval Workflows

Risk-based approval requirements
Multi-party approval for critical actions
Email/Slack notifications
Expiration handling

📊 Complete Audit Trail

Every action logged immutably
Policy evaluations recorded
Compliance report generation
Export for auditors

📋 Template Library

10+ agent templates (data processor, email assistant, backup, scraper, etc.)
6+ policy templates (GDPR, SOC 2, HIPAA, PCI DSS, etc.)
Industry-specific compliance frameworks

🏛️ Compliance Ready

SOC 2 - Security & availability controls
GDPR - EU data protection
HIPAA - Healthcare data privacy
PCI DSS - Payment card security
CCPA - California privacy
NIST - Cybersecurity framework
ISO 27001 - Information security
FedRAMP - Federal authorization

🚀 Quick Start

Step 1: Configure Claude Desktop

Add to your claude_desktop_config.json:

Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

json

{  "mcpServers": {    "agentos": {      "command": "npx",      "args": ["-y", "agentos-mcp-server"],      "env": {        "AGENTOS_POLICY_MODE": "strict"      }    }  }}

{  "mcpServers": {    "agentos": {      "command": "npx",      "args": ["-y", "agentos-mcp-server"],      "env": {        "AGENTOS_POLICY_MODE": "strict"      }    }  }}

Step 2: Restart Claude Desktop

Close and reopen Claude Desktop to load the MCP server.

Step 3: Start Building Agents!

Just ask Claude naturally:

Claude will:

Create the agent with appropriate configuration
Suggest safety policies based on the task
Let you test before deployment
Deploy with monitoring enabled

💬 Example Conversations

Creating a Data Processing Agent

User: I need an agent that processes customer feedback from support emails daily
Claude: ✅ Agent Created Successfully!
Agent: customer-feedback-processorID: a1b2c3d4-e5f6-7890-abcd-ef1234567890Status: draftLanguage: python
Task:Process customer feedback from support emails daily
Workflow Steps:1. connect_email: email.connect2. process_data: execute3. output_results: output
Safety Policies Applied:🛡️ PII Protection: Customer emails/names anonymized🛡️ Rate Limiting: Max 1000 emails per run🛡️ Human Review: Negative sentiment cases flagged
Next Steps:1. Use `test_agent` to run a dry-run test2. Use `attach_policy` to add more safety policies3. Use `deploy_agent` when ready to run

User: I need an agent that processes customer feedback from support emails daily
Claude: ✅ Agent Created Successfully!
Agent: customer-feedback-processorID: a1b2c3d4-e5f6-7890-abcd-ef1234567890Status: draftLanguage: python
Task:Process customer feedback from support emails daily
Workflow Steps:1. connect_email: email.connect2. process_data: execute3. output_results: output
Safety Policies Applied:🛡️ PII Protection: Customer emails/names anonymized🛡️ Rate Limiting: Max 1000 emails per run🛡️ Human Review: Negative sentiment cases flagged
Next Steps:1. Use `test_agent` to run a dry-run test2. Use `attach_policy` to add more safety policies3. Use `deploy_agent` when ready to run

Testing Before Deployment

User: Test this agent with a scenario of processing 100 emails
Claude: ✅ Test PASSED
Agent: customer-feedback-processorScenario: Process 100 customer emailsMode: Dry Run (no changes)
Configuration Check: ✅ ValidWorkflow Check: ✅ Valid (3 steps)
Policy Evaluation: ✅ No violations detected
Warnings:⚠️  PII access logged
Resource Estimates:- Duration: ~30 seconds- Cost: $0.05
Next Step: Use `deploy_agent` to deploy this agent.

User: Test this agent with a scenario of processing 100 emails
Claude: ✅ Test PASSED
Agent: customer-feedback-processorScenario: Process 100 customer emailsMode: Dry Run (no changes)
Configuration Check: ✅ ValidWorkflow Check: ✅ Valid (3 steps)
Policy Evaluation: ✅ No violations detected
Warnings:⚠️  PII access logged
Resource Estimates:- Duration: ~30 seconds- Cost: $0.05
Next Step: Use `deploy_agent` to deploy this agent.

Checking Compliance

User: Check if this agent is SOC 2 compliant
Claude: # Compliance Report: SOC2
Agent: customer-feedback-processorFramework: SOC2Date: 2026-01-30
## Summary✅ COMPLIANTScore: 100% (4/4 controls passed)
## Control Assessment
✅ CC6.1: Logical Access Controls   Restrict logical access to information assets   Evidence: Policy enforcement enabled, Access logging active
✅ CC6.6: Security Event Monitoring   Detect and respond to security events   Evidence: Audit logging enabled, Event timestamps recorded
✅ CC7.2: Incident Response   Respond to security incidents   Evidence: Human review enabled, Escalation procedures in place
✅ CC8.1: Change Management   Manage changes to system components   Evidence: Deployment approval required, Version control enabled

User: Check if this agent is SOC 2 compliant
Claude: # Compliance Report: SOC2
Agent: customer-feedback-processorFramework: SOC2Date: 2026-01-30
## Summary✅ COMPLIANTScore: 100% (4/4 controls passed)
## Control Assessment
✅ CC6.1: Logical Access Controls   Restrict logical access to information assets   Evidence: Policy enforcement enabled, Access logging active
✅ CC6.6: Security Event Monitoring   Detect and respond to security events   Evidence: Audit logging enabled, Event timestamps recorded
✅ CC7.2: Incident Response   Respond to security incidents   Evidence: Human review enabled, Escalation procedures in place
✅ CC8.1: Change Management   Manage changes to system components   Evidence: Deployment approval required, Version control enabled

Creating Custom Policies

User: Create a policy that blocks access to customer credit card data
Claude: ✅ Custom Policy Created
Policy: Block Access To CustomerID: custom-a1b2c3d4Category: security
Description:Block access to customer credit card data
Rules Generated (1):
🟠 custom_block_rule [high]   Block actions based on: block access to customer credit card data   Action: deny
Usage:1. Attach to agent: `attach_policy` with policyId "custom-a1b2c3d4"2. Test enforcement: `test_agent` with policy scenarios3. View active policies: `get_agent_status`

User: Create a policy that blocks access to customer credit card data
Claude: ✅ Custom Policy Created
Policy: Block Access To CustomerID: custom-a1b2c3d4Category: security
Description:Block access to customer credit card data
Rules Generated (1):
🟠 custom_block_rule [high]   Block actions based on: block access to customer credit card data   Action: deny
Usage:1. Attach to agent: `attach_policy` with policyId "custom-a1b2c3d4"2. Test enforcement: `test_agent` with policy scenarios3. View active policies: `get_agent_status`

🔧 Available Tools

Tool	Description
`create_agent`	Create agent from natural language description
`attach_policy`	Attach safety policies to agents
`test_agent`	Dry-run test before deployment
`deploy_agent`	Deploy agent locally or to cloud
`get_agent_status`	Get agent status and metrics
`list_templates`	Browse agent and policy templates
`request_approval`	Create approval request for sensitive actions
`audit_log`	Query audit trail
`create_policy`	Create custom policy from description
`check_compliance`	Check against compliance frameworks

Tool Details

`create_agent`

Create a new AI agent from a natural language description with automatic policy recommendations.

Parameters:

Parameter	Type	Required	Description
`description`	string	✅	Natural language description of agent task
`policies`	string[]		Policy templates to apply
`approvalRequired`	boolean		Require human approval before execution
`language`	string		`python`, `typescript`, `javascript`, `go`
`schedule`	string		Cron schedule for recurring execution

`attach_policy`

Attach safety policies to an agent with conflict detection.

Parameters:

`test_agent`

Run a dry-run test with simulated scenarios.

Parameters:

`deploy_agent`

Deploy an agent to local or cloud environment.

Parameters:

`check_compliance`

Check an agent against regulatory frameworks.

Parameters:

📋 Policy Templates

Built-in Security Policies

Policy ID	Name	Description
`pii-protection`	PII Protection	Protects personally identifiable information (GDPR)
`rate-limiting`	Rate Limiting	Prevents resource abuse through rate limits
`cost-control`	Cost Control	Prevents runaway costs from automation
`data-deletion`	Data Deletion Safety	Prevents accidental data loss
`secrets-protection`	Secrets Protection	Prevents exposure of credentials
`human-review`	Human Review Required	Requires approval for sensitive actions

Compliance Templates

Template ID	Framework	Description
`gdpr-compliance`	GDPR	EU General Data Protection Regulation
`soc2-security`	SOC 2	SOC 2 Type II security controls
`hipaa-healthcare`	HIPAA	Healthcare data privacy (PHI protection)
`pci-dss-payments`	PCI DSS	Payment card data security
`read-only-access`	Security	Restricts database to read-only
`production-safety`	Operations	Extra safeguards for production

🤖 Agent Templates

Data Processing

Template	Description	Default Policies
`data-processor`	Processes and transforms data files	rate-limiting, cost-control
`web-scraper`	Scrapes websites for data collection	rate-limiting, cost-control
`report-generator`	Generates periodic reports	pii-protection, rate-limiting

Communication

Infrastructure

Template	Description	Default Policies
`backup-agent`	Backs up files to cloud storage	cost-control
`api-monitor`	Monitors API health and performance	rate-limiting
`file-organizer`	Organizes files based on rules	data-deletion

Analytics

⚙️ Configuration

Environment Variables

Variable	Description	Default
`AGENTOS_API_KEY`	API key for cloud features	(none)
`AGENTOS_POLICY_MODE`	`strict` or `permissive`	`strict`
`AGENTOS_DATA_DIR`	Local data directory	`.agentos`
`AGENTOS_LOG_LEVEL`	`debug`, `info`, `warn`, `error`	`info`

Policy Modes

Data Storage

All data is stored locally in the AGENTOS_DATA_DIR:

.agentos/├── agents/           # Agent configurations│   └── {id}.json├── approvals/        # Approval requests│   └── {id}.json└── audit/            # Audit logs (JSONL format)    └── {date}.jsonl

.agentos/├── agents/           # Agent configurations│   └── {id}.json├── approvals/        # Approval requests│   └── {id}.json└── audit/            # Audit logs (JSONL format)    └── {date}.jsonl

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐│                     Claude Desktop                           ││  ┌────────────────────────────────────────────────────────┐ ││  │                    Claude AI Model                      │ ││  │     Natural language understanding & orchestration      │ ││  └──────────────────────┬─────────────────────────────────┘ ││                         │ MCP Protocol                       ││  ┌──────────────────────▼─────────────────────────────────┐ ││  │                    MCP Client                           │ ││  │          Tool discovery & request handling              │ ││  └──────────────────────┬─────────────────────────────────┘ │└─────────────────────────┼───────────────────────────────────┘                          │ stdio┌─────────────────────────▼───────────────────────────────────┐│               @agentos/mcp-server (Node.js)                 ││  ┌────────────────────────────────────────────────────────┐ ││  │                    MCP Server                           │ ││  │            Tool/Resource/Prompt handlers                │ ││  └────────────────────────────────────────────────────────┘ ││  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌───────────────┐  ││  │  Agent   │ │  Policy  │ │ Approval │ │    Audit      │  ││  │ Manager  │ │  Engine  │ │ Workflow │ │   Logger      │  ││  └──────────┘ └──────────┘ └──────────┘ └───────────────┘  ││  ┌────────────────────────────────────────────────────────┐ ││  │              Template Library (50+ templates)           │ ││  └────────────────────────────────────────────────────────┘ │└─────────────────────────────────────────────────────────────┘                          │ HTTPS (optional)┌─────────────────────────▼───────────────────────────────────┐│              AgentOS Cloud Platform (Future)                ││     • Persistent storage  • Multi-tenant  • Enterprise      │└─────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────┐│                     Claude Desktop                           ││  ┌────────────────────────────────────────────────────────┐ ││  │                    Claude AI Model                      │ ││  │     Natural language understanding & orchestration      │ ││  └──────────────────────┬─────────────────────────────────┘ ││                         │ MCP Protocol                       ││  ┌──────────────────────▼─────────────────────────────────┐ ││  │                    MCP Client                           │ ││  │          Tool discovery & request handling              │ ││  └──────────────────────┬─────────────────────────────────┘ │└─────────────────────────┼───────────────────────────────────┘                          │ stdio┌─────────────────────────▼───────────────────────────────────┐│               @agentos/mcp-server (Node.js)                 ││  ┌────────────────────────────────────────────────────────┐ ││  │                    MCP Server                           │ ││  │            Tool/Resource/Prompt handlers                │ ││  └────────────────────────────────────────────────────────┘ ││  ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌───────────────┐  ││  │  Agent   │ │  Policy  │ │ Approval │ │    Audit      │  ││  │ Manager  │ │  Engine  │ │ Workflow │ │   Logger      │  ││  └──────────┘ └──────────┘ └──────────┘ └───────────────┘  ││  ┌────────────────────────────────────────────────────────┐ ││  │              Template Library (50+ templates)           │ ││  └────────────────────────────────────────────────────────┘ │└─────────────────────────────────────────────────────────────┘                          │ HTTPS (optional)┌─────────────────────────▼───────────────────────────────────┐│              AgentOS Cloud Platform (Future)                ││     • Persistent storage  • Multi-tenant  • Enterprise      │└─────────────────────────────────────────────────────────────┘

🔒 Security

Feature	Description
Policy Enforcement	All actions validated against policies before execution
Data Redaction	Sensitive data automatically redacted from logs
Secret Protection	Secrets never stored in plain text
Audit Trail	Complete immutable log for compliance
Human Approval	Required for high-risk operations
Local-First	All data stored locally by default

💻 Development

Local Development

bash

# Clone the repositorygit clone https://github.com/imran-siddique/agent-oscd agent-os/packages/mcp-server
# Install dependenciesnpm install
# Buildnpm run build
# Run in stdio mode (for Claude Desktop)npm start -- --stdio
# Run in HTTP mode (for development)npm start -- --http --port 3000

# Clone the repositorygit clone https://github.com/imran-siddique/agent-oscd agent-os/packages/mcp-server
# Install dependenciesnpm install
# Buildnpm run build
# Run in stdio mode (for Claude Desktop)npm start -- --stdio
# Run in HTTP mode (for development)npm start -- --http --port 3000

Project Structure

packages/mcp-server/├── src/│   ├── index.ts              # Main entry point│   ├── cli.ts                # CLI with --stdio/--http modes│   ├── server.ts             # MCP server implementation│   ├── tools/                # 10 MCP tools│   │   ├── create-agent.ts│   │   ├── attach-policy.ts│   │   ├── test-agent.ts│   │   ├── deploy-agent.ts│   │   ├── get-agent-status.ts│   │   ├── list-templates.ts│   │   ├── request-approval.ts│   │   ├── audit-log.ts│   │   ├── create-policy.ts│   │   └── check-compliance.ts│   ├── services/             # Core business logic│   │   ├── agent-manager.ts│   │   ├── policy-engine.ts│   │   ├── approval-workflow.ts│   │   ├── audit-logger.ts│   │   └── template-library.ts│   ├── prompts/              # MCP prompts│   └── types/                # TypeScript definitions├── package.json├── tsconfig.json└── README.md

packages/mcp-server/├── src/│   ├── index.ts              # Main entry point│   ├── cli.ts                # CLI with --stdio/--http modes│   ├── server.ts             # MCP server implementation│   ├── tools/                # 10 MCP tools│   │   ├── create-agent.ts│   │   ├── attach-policy.ts│   │   ├── test-agent.ts│   │   ├── deploy-agent.ts│   │   ├── get-agent-status.ts│   │   ├── list-templates.ts│   │   ├── request-approval.ts│   │   ├── audit-log.ts│   │   ├── create-policy.ts│   │   └── check-compliance.ts│   ├── services/             # Core business logic│   │   ├── agent-manager.ts│   │   ├── policy-engine.ts│   │   ├── approval-workflow.ts│   │   ├── audit-logger.ts│   │   └── template-library.ts│   ├── prompts/              # MCP prompts│   └── types/                # TypeScript definitions├── package.json├── tsconfig.json└── README.md

Running Tests

📊 Performance

📜 License

MIT License - see LICENSE.

Build safe AI agents with AgentOS

GitHub · Documentation · Report Issue

Made with 🛡️ by the Agent OS team

Source: extensions/mcp-server/README.md at commit a7ee6eb

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v1.0.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts

Template	Description	Default Policies
`email-assistant`	Monitors and processes emails	pii-protection, human-review
`slack-bot`	Automated Slack notifications	human-review, rate-limiting

Template	Description	Default Policies
`database-analyst`	Queries databases and generates reports	data-deletion, pii-protection
`content-moderator`	Moderates user-generated content	human-review, pii-protection

Metric	Target
MCP server startup	<2 seconds
Tool response time	<500ms (p95)
Memory footprint	<100MB
Policy evaluation	<50ms

Parameter	Type	Required	Description
`agentId`	string	✅	Agent ID to check
`framework`	string	✅	`SOC2`, `GDPR`, `HIPAA`, `PCI_DSS`, `CCPA`, `NIST`, `ISO27001`, `FEDRAMP`
`generateReport`	boolean		Generate detailed report

Mode	Behavior
strict	Any policy violation blocks the action
permissive	Only critical violations block (warnings logged)