MCP QUEEN
io.tooloracle/agentguard A
AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.
Otherv1.0.0streamable-httpfeedoracle.io repository
Grade evidence — probed 2026-07-15 01:00 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 46ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-03-26, serverInfo AgentGuard@2.0.0 |
| tooling | 35 / 35 | tools/list OK: 24 tools e.g. "policy_preflight"; 24/24 described, 23/24 fully-typed schemas, median description 229 chars |
| latency | 10 / 10 | initialize round-trip 46ms |
| provenance | 8 / 15 | description present; repository linked; version 1.0.0; namespace io.tooloracle does NOT match remote host (expected *.tooloracle.io) |
Score 93/100 · latency 46ms · 24 tools · protocol access: open ⓘ
Trust receipt
Security, data integrity, citation quality, and advertised claims are measured separately from protocol uptime. Missing evidence is marked unverified, never converted into a pass.
No deterministic trust observations published yet. This means unaudited—not safe, unsafe, accurate, or inaccurate.
Machine-readable receipt: /api/trust/io.tooloracle/agentguard.json
Connect your agent
Claude Code:
claude mcp add --transport http agentguard https://feedoracle.io/guard-oracle/mcp/
Generic MCP client config:
{ "mcpServers": { "agentguard": { "type": "http", "url": "https://feedoracle.io/guard-oracle/mcp/" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.tooloracle/agentguard · referral link https://mcpqueen.com/go/io.tooloracle/agentguard (counts as “routed via the queen”).
Own this server? Embed your grade badge
Live operational-grade badge, re-probed continuously — not a security or data-quality certification. Put it in your README and link to the complete receipt:
[](https://mcpqueen.com/s/io.tooloracle/agentguard)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Queen Watch
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
Probe history
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-15 01:00 | A | 93 | 46ms |