agentseal-mcp-intel
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTSEAL_DEBUG | No | Set to 1 for debug logs on stderr | 0 |
| MCP_CONFIG_PATH | No | Extra config file path for check_environment (useful in CI) | |
| AGENTSEAL_API_KEY | No | Pro API key for unlimited access and full findings detail | |
| AGENTSEAL_API_URL | No | Override API base URL | https://agentseal.org |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_registryA | Search the AgentSeal security registry of 3,400+ scanned MCP servers. Returns trust scores (0-100) and security ratings from 265+ automated probes. Useful when the user asks to find, discover, or recommend MCP servers. |
| check_serverA | Check the security of a specific MCP server. Returns a trust score (0-100), risk level, score breakdown, and security findings from 265+ automated probes. Useful before installing or recommending an MCP server. |
| check_environmentA | Scan MCP servers currently installed in your AI tools (Claude Desktop, Cursor, Windsurf) and check each one against the AgentSeal registry. Shows trust scores and flags risky or unknown servers. Only server names are sent to the API - credentials and config values stay local. |
| check_fileA | Analyze an AI config file for hidden security threats: prompt injection, invisible characters, data exfiltration instructions, jailbreak patterns. Supported files: .cursorrules, CLAUDE.md, .github/copilot-instructions.md, .windsurfrules, .mcp.json. Runs entirely locally. |
| submit_serverA | Submit an MCP server that's not in the AgentSeal registry for security scanning. AgentSeal will fetch it, run 265+ security probes, and add results to the public registry. Requires confirmed=true to prevent accidental submissions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct operation: scanning environments, files, specific servers, registry search, and submissions. No functional overlap exists.
All tools follow a consistent 'verb_noun' pattern (check_environment, check_file, check_server, search_registry, submit_server) with clear, action-oriented names.
Five tools precisely cover the core workflows of security scanning: environment audit, file analysis, server checks, registry search, and submission. Neither too few nor too many.
The tool set provides complete lifecycle coverage for the domain: check existing servers (environment, file, server), discover new ones (search_registry), and add missing ones (submit_server). No obvious gaps.