Skip to main content
Glama

Device Linkage Blocking Agent

This is an AiPy extension scaffold built on the latest version of FastMCP, designed for subsequent integration with AF device linkage blocking capabilities.

Project Structure

  • device_block_agent/: Core Python source code and MCP tool implementation.

  • docs/: API documentation, solution documents, and original PDFs.

  • assets/: Static resources such as icons.

  • examples/: Whitelist samples and reference materials.

  • Root directory: Contains project entry files such as main.py, manifest.json, requirements.txt, and README.md.

Related MCP server: NHN Server MCP

Current Status

  • Integrated FastMCP 3.2.4.

  • Provided a Streamable HTTP MCP service entry point, with the default exposure path at /mcp.

  • Provided the addition-system-instruction prompt required by AiPy.

  • Provided three authentication tools: auth_login, auth_keepalive, and auth_logout.

  • Provided four read-only query tools: block_list_temp, block_list_business, block_get_total_count, and block_get_block_time.

  • Provided a whitelist rule loading and manual confirmation judgment module, which can be directly reused by subsequent write operation tools.

  • Provided seven write operation tools: block_add_business, block_delete_temp, block_delete_business, block_clear_attackers, block_clear_temp, block_clear_business, and block_set_block_time.

  • Provided local JSONL audit logs and check-back results refined by operation type.

  • Supported persistence of login sessions via local JSON files for cross-process login state reuse.

  • Supported local session timeout judgment and automatic keepalive when nearing expiration.

  • Supported default AF account and connection configuration, which can be directly reused by authentication and blocking tools.

  • Provided a minimal tool agent_info to verify the discovery link from AiPy to the MCP service.

  • Integrated the first version of business-level check-back policy; block_clear_attackers has been upgraded to include pre- and post-baseline comparison judgment.

Local Execution

  1. Install dependencies: pip install -r requirements.txt

  2. Start the service: python main.py

  3. After the service starts, a random port number will be printed to standard output.

Risk Control Configuration

  1. examples/whitelist.sample.json provides a local whitelist example.

  2. confirm_mode supports two modes: manual and auto.

  3. WHITELIST_FILE and CONFIRM_MODE can be injected into the runtime environment via manifest.json's user_config.

  4. Clearing operations always require explicit confirmation; bulk additions and deletions require explicit confirmation in manual mode.

  5. LOG_FILE can be used to specify the local JSONL audit log path.

  6. SESSION_FILE can be used to specify the local JSON session persistence path.

  7. SESSION_TIMEOUT_SECONDS and SESSION_REFRESH_WINDOW_SECONDS can be used to control local session timeout and automatic keepalive windows.

Account Configuration

  1. af_host is used to configure the default AF host address.

  2. af_namespace is used to configure the default namespace, defaulting to public.

  3. af_username and af_password are used to configure the default login account.

  4. af_verify_tls is used to configure the default HTTPS certificate verification switch.

  5. Once configured, auth_login, auth_keepalive, auth_logout, and blocking-related tools can directly reuse these default values.

Currently Implemented Tools

  1. agent_info

  2. auth_login

  3. auth_keepalive

  4. auth_logout

  5. account_config_status

  6. block_list_temp

  7. block_list_business

  8. block_get_total_count

  9. block_get_block_time

  10. block_add_business

  11. block_delete_temp

  12. block_delete_business

  13. block_clear_attackers

  14. block_clear_temp

  15. block_clear_business

  16. block_set_block_time

Next Steps

  1. For production deployment, add log rotation and sensitive field classification/masking.

  2. For stronger check-back capabilities, add precise comparison based on business record IDs or operation result objects.

  3. For long-term operation, add an automatic re-authentication strategy after token expiration.

F
license - not found
Not graded
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • F
    license
    A
    quality
    C
    maintenance
    Enables secure SSH access to servers through a gateway with Kerberos authentication, allowing execution of whitelisted commands with pattern-based security controls and server information retrieval.
    5
    2
  • F
    license
    A
    quality
    C
    maintenance
    Enables secure file system operations (read, write, delete) and simulated command execution with server-enforced permission policies, risk assessment, and human-in-the-loop approval.
    5
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables governed agent access to Cortex XSIAM security operations APIs, including XQL log search, issues, cases, endpoints, and assets, with dataset authorization and optional identity-based access control.

View all related MCP servers

Related MCP Connectors

  • Device intelligence for AI agents: Fingerprint events, smart signals, and API key management.

  • Remote MCP for AI waiver checks, exception approvals, expiry review, and audit receipts.

  • An authenticated remote MCP server for user-owned devices and one-shot capability invocation.

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/xiaqijun/AF_MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server