MCP QUEEN
dev.depfeed/depfeed A
Change intelligence for coding agents: sourced breaking changes for npm, PyPI, and Rust packages.
Dev & Codev0.6.3streamable-httpdepfeed.dev repository
Grade evidence — probed 2026-08-02 15:00 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 734ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo depfeed@0.1.0 |
| tooling | 35 / 35 | tools/list OK: 19 tools e.g. "get_package_updates"; 19/19 described, 19/19 fully-typed schemas, median description 606 chars |
| latency | 7 / 10 | initialize round-trip 734ms |
| provenance | 15 / 15 | description present; repository linked; version 0.6.3; namespace dev.depfeed matches endpoint/repo |
Score 97/100 · latency 734ms · 19 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.
| Dimension | Metric | Status | Evidence | Source |
|---|---|---|---|---|
| citation_quality | citation_capability_advertised | unverified | Metadata/tool descriptions advertise citation or evidence capability: returns NotCovered: that means it isn't in DepFeed's curated tracki plan_upgrade Builds an ordered, source-backed upgrade plan for one npm package - composes check_breaking_changes, get_migration_recipes, get_api_diff, and (if related_packages is given) check_compatibility. No response-level citation benchmark has verified this claim yet. | live_probe |
| security | sensitive_capabilities_declared | concern | 4 discovered tool(s) advertise potentially state-changing or privileged capabilities. Tool names: check_breaking_changes, get_migration_recipes, register_webhook_subscription, list_webhook_subscriptions. Classification is description-based and does not prove exploitability. Observed value: check_breaking_changes, get_migration_recipes, register_webhook_subscription, list_webhook_subscriptions Sample: n=4 | live_probe |
| security | authentication_boundary | observed | Live protocol probe observed auth_state=open. This describes discovery/access behavior; it is not by itself a vulnerability finding. Observed value: open | live_probe |
Machine-readable receipt: /api/trust/dev.depfeed/depfeed.json
Connect your agent
Claude Code:
claude mcp add --transport http depfeed https://depfeed.dev/
Generic MCP client config:
{ "mcpServers": { "depfeed": { "type": "http", "url": "https://depfeed.dev/" } } }
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/dev.depfeed/depfeed · referral link https://mcpqueen.com/go/dev.depfeed/depfeed (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. Copy the ready-made Markdown into your README:
[](https://mcpqueen.com/s/dev.depfeed/depfeed)
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 |
|---|---|---|---|
| 2026-08-02 15:00 | A | 97 | 734ms |