A
licenseA
qualityC
maintenanceEnables an AI agent to run local tools on the user's own machine via stdio, including command execution, workspace file read/write, and system status checks.
5
2
MIT
StealthMark MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@StealthMark MCP Server resolve example.com's agent manifest and tell me what actions it exposes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
StealthMark MCP Server
A Model Context Protocol server that gives AI agents access to the StealthMark API over stdio.
Tools
Tool | What it does | API call |
| Resolves a website's machine-readable agent manifest and its exposed actions. |
|
| Invokes an action a site declares in its agent manifest, by the action's slug. |
|
| Looks up one of your organization's registered agents by ID. |
|
Related MCP server: io.github.readyagentsdev/readyagents
Configuration
Setting | Flag | Environment variable | Default |
API base URL |
|
|
|
API key, sent as a Bearer token |
|
| none |
Flags take precedence over environment variables.
Build and run
npm ci
npm run build
node dist/index.js --api-url=<your StealthMark API URL>Example MCP client entry:
{
"mcpServers": {
"stealthmark": {
"command": "node",
"args": ["/absolute/path/to/stealthmark-mcp-server/dist/index.js"],
"env": {
"STEALTHMARK_API_URL": "<your StealthMark API URL>",
"STEALTHMARK_API_KEY": "<your API key>"
}
}
}
}Development
npm run typecheck
npm testLicense
Available Tools
3 toolsgateway_invokeC
Invoke an action a site declares in its agent manifest, through the StealthMark API.
Inputs: domain (required), action_id (required), parameters (required).
gateway_resolveC
Resolve a website's machine-readable agent manifest and its exposed actions through the StealthMark API.
Inputs: domain (required).
kya_statusA
Look up one of your organization's registered agents (name, status, protocols) through the StealthMark API.
Inputs: agent_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
B3.4/5.0
Scored across 3 tools
Disambiguation5/5
The three tools have clearly distinct purposes: resolving a site manifest, invoking a declared action, and looking up agent status. An agent can easily choose between discovery, execution, and identity lookup without overlap.
Naming Consistency4/5
All names use snake_case and are readable, but the prefixes differ in style: gateway_resolve and gateway_invoke share a gateway_ action pattern, while kya_status uses an acronym-plus-noun pattern. This is a minor deviation rather than a confusing inconsistency.
Tool Count5/5
Three tools is well-scoped for a focused gateway server: resolve, invoke, and status lookup each cover a distinct part of the workflow. There is no obvious tool bloat or trivial single-tool surface.
Completeness3/5
The core resolve-then-invoke workflow is covered, and status lookup supports agent identity checks. However, the agent lifecycle is notably incomplete: there is no way to list registered agents, register a new agent, or update agent details, which may cause dead ends for administrative tasks.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues
Related MCP Connectors
Look up 133 agentic-web standards, live-probe any domain, validate manifests, generate boilerplate.
AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
Verified websites as JSON commands for AI agents over plain curl or MCP.
Context and control for any AI. Agent identity, scoped access, and proof across tools.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceExposes ReadyAgents' local workflow engine and built-in tools over MCP stdio, enabling MCP clients to define, run, inspect, and approve YAML/JSON agent workflows.83 PyPI1Apache 2.0
- AlicenseBqualityBmaintenanceEnables AI clients to connect locally over stdio, discover and read schemas for native page tools, and execute user-authorized operations supplied by websites and independent user scripts.13MIT
molesignal mcpofficial
AlicenseNot gradedqualityBmaintenanceServes MoleSignal's tools over stdio to AI agent tools such as Claude Code, Cursor, Codex, VS Code, or Gemini CLI, enabling them to query logs, metrics, traces, incidents, approvals, deployments, and other capabilities under the user's permissions and organization policy.446 npmApache 2.0
