AgentWatchr is answering right now. Last checked 6 min ago. It exposes 4 tools.
Read-only agent identity index with provenance, historical evidence and explained coverage.
AgentWatchr does not always answer
Over the last week it answered 96.9% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add evidence-index --transport http https://agentwatchr.com/mcphttps://agentwatchr.com/mcp[mcp_servers.evidence-index]
url = "https://agentwatchr.com/mcp"{
"mcpServers": {
"evidence-index": {
"url": "https://agentwatchr.com/mcp"
}
}
}{
"servers": {
"evidence-index": {
"type": "http",
"url": "https://agentwatchr.com/mcp"
}
}
}Available tools 4
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_agent
search_agents
get_insights
get_stats
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentwatchr.com/mcp | streamable-http | answering | 3649 ms | 6 min ago |
Alternatives to AgentWatchr
same job, measured the same wayChristian source evidence for AI agents, with provenance, tradition coverage, and citation checks.
Historical borders and dated map events with source attribution and coverage limits.
Read-only evidence for the tools agents run: MCP server records, coverage and policy.
Read-only audit evidence for security, tests, native coverage, runtime failures and repair status.
Hosted, no install: read-only censorship incident records, country index data and coverage.
Evidence-first browser QA with read-only MCP server for AI agent debugging.
Read-only web QA agent: scans a site in a real browser and returns evidence-backed findings
Search public laws and implementation evidence with sources, scope limits and dated coverage.
AgentWatchr — questions
Answers built from our own checks of this server.