Koskamo

AgentGlass MCP

AgentGlass checks public job application pages before an AI job agent applies. It returns a simple report that helps decide whether to continue or pause for human review. It scans for hidden instructions aimed at AI agents (prompt injection) in resumes and job postings.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

AgentGlass MCP logo, by AgentGlassVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by AgentGlass
MCP endpoint (Streamable HTTP)
https://agentglass.net/mcp
Vendor documentation

What its tools do

1 tool, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (1)

1 of 1 have a description · 0 of 1 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to agentglass.net ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Scan public job application URLs for hidden instructions
  • Check resumes and job postings for prompt injection
  • Decide whether to continue or pause for human review
  • Provide review signals on risk level and verdict

Source and maintenance

Vendor evidenceRegistry 0.1.0
mcp-registry: net.agentglass/agentglass@0.1.0Project website

Protocol and capabilities

Server
agentglass 0.1.0
MCP protocol negotiated in check
2025-06-18
Tools
1 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Tools

1 advertised

scan_job_page — Scan a page for hidden AI instructions
Advertised by the server during the last successful anonymous check.

Scan a public URL, typically a job posting or application page, for hidden text, HTML comments, metadata and script content that try to instruct an AI agent (prompt injection). Returns a risk level (clean, notice, suspicious, high), a short verdict and the evidence, so the agent can decide whether to continue or pause for human review.

scan_job_page input schema
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Public URL to inspect, such as a job application page."
    },
    "timeoutMs": {
      "type": "number",
      "maximum": 45000,
      "minimum": 5000,
      "description": "Optional scan timeout in milliseconds."
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
232 ms
95th percentile latency
232 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 232 ms · metadata changed · 1 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http agentglass-mcp https://agentglass.net/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add agentglass-mcp --url https://agentglass.net/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentglass-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentglass-mcp": {
      "url": "https://agentglass.net/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentglass-mcp": {
      "type": "streamableHttp",
      "url": "https://agentglass.net/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentglass-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentglass-mcp": {
      "type": "http",
      "url": "https://agentglass.net/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http agentglass-mcp https://agentglass.net/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://agentglass.net/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "agentglass-mcp": {
      "serverUrl": "https://agentglass.net/mcp"
    }
  }
}

Let your agent find its tools

Find servers like AgentGlass MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 5,170

Do you run AgentGlass MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing