Agent Watch
by agent-watch-api-production.up.railway.app in Developer tools
Monitoring for the agent economy — liveness, latency, trust scoring for MCP endpoints
https://agent-watch-api-production.up.railway.app/mcp/- Tools
- 8
- open to any client
- Uptime
- 100%
- last 30 days
- Response time
- 380 ms
- 515 ms slowest 5%
- Last check
- Passed
- 4 h ago, next in 2 h
Reliability
Status and outage history · Atom feed · Watch with other listings
How to connect
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"agent-watch": {
"type": "http",
"url": "https://agent-watch-api-production.up.railway.app/mcp/"
}
}
}8 tools
- aw_health
Liveness check for the Agent Watch API. Returns ok, service name, and version. Call this first to verify connectivity before using other tools.
- aw_check_endpoint
Probe an MCP or HTTP-402 endpoint now and get its trust verdict. Performs a real MCP initialize handshake (not a ping), measures p50/p95 latency, counts tools, hashes the tool schema (for drift detection), and checks RFC 9728 auth metadata. Returns: alive (bool)…
- aw_census
Full-census summary of the official MCP registry: 7,454 endpoints probed with real MCP handshakes. Returns alive/dead/unknown counts and percentages. States: alive = MCP initialize succeeded; dead = no answer; unknown = answered but auth-gated (401/403/402) or…
- aw_list_monitored
List all endpoints in the Agent Watch census with their registry names. Returns count and the full endpoint list (URLs). Combine with aw_alerts to find which of these are dead. Read-only.
- aw_alerts
Show dead endpoints across the monitored registry (alive=false). Returns up to 500 dead endpoints with names. Use after aw_census or aw_list_monitored to get the actionable dead list. Read-only.
- aw_watch
Add endpoints to your personal watchlist (probed immediately, then every 6h). Plan-limited by the email used at checkout: free 5, Builder ($19/mo) 50, Team ($99/mo) 500 endpoints. Alerts fire on alive→dead transitions and tool-schema drift. Already-watched URLs are…
- skills_list_tool
List this product's skills. Each entry carries the SKILL.md URI, its name and description, verbatim frontmatter, and a per-file sha256 manifest. Read a body with `read_skill`.
- read_skill
Read a product skill file by its skill:// URI. Args: uri: e.g. skill://<product>/<skill-name>/SKILL.md Get valid URIs from `skills_list_tool`.
Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 4 h ago | Passed | 200 | 405 ms |
| 14 h ago | Passed | 200 | 400 ms |
| 23 h ago | Passed | 200 | 339 ms |
| 31 h ago | Passed | 200 | 420 ms |
| 39 h ago | Passed | 200 | 515 ms |
Show 10 older checks
| 2 days ago | Passed | 200 | 336 ms |
| 2 days ago | Passed | 200 | 376 ms |
| 3 days ago | Passed | 200 | 406 ms |
| 3 days ago | Passed | 200 | 337 ms |
| 4 days ago | Passed | 200 | 356 ms |
| 4 days ago | Passed | 200 | 359 ms |
| 5 days ago | Passed | 200 | 343 ms |
| 5 days ago | Passed | 200 | 376 ms |
| 5 days ago | Passed | 200 | 391 ms |
| 6 days ago | Passed | 200 | 389 ms |