Evidence-first food-infrastructure and resilience intelligence on owned Evercraft Fabric.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 4 tools
Each tool targets a distinct operation: comparative ranking, health status, latest snapshot, and bounded investigation. The only mild overlap is between compare_faie_candidates and investigate_faie_evidence, since both run FAIE evidence workflows, but their scope and outputs differ clearly enough.
All names follow a consistent snake_case verb_faie_noun pattern: compare_faie_candidates, get_faie_health, get_faie_signal_snapshot, investigate_faie_evidence. The shared 'faie' segment and predictable verb-first structure make the set easy to scan.
Four tools is well-scoped for a specialized public-safe evidence server. Each tool earns its place without redundancy, and the count is comfortably within the typical 3-15 range.
The surface covers comparative readiness, health monitoring, latest signals, and bounded investigation, which are core to the domain. Minor gaps exist, such as candidate discovery or historical signal access, but the current tools support the main read-only workflows.
Run the same bounded FAIE evidence rubric across 2 to 8 candidate regions or sites. The returned rank is evidence-readiness only, not site suitability or an investment recommendation.
Inputs: question (required), candidates (required), crop, asset_types, +4 more.
Return FAIE resident, source-health, and signal-count status without exposing private investigation content.
Inputs: no named parameters.
Return the latest public-safe FAIE signal snapshot. Read-only and non-transactional.
Inputs: limit.
Run a bounded FAIE evidence investigation. Public MCP investigations are ephemeral previews and do not persist the caller question into the shared investigation archive.
Inputs: question (required), crop, asset_types, region_keys, +4 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Infrastructure and hazard intelligence with provenance, spatial confidence and quality contracts.
Physical-world evidence and operability checks with provenance and explicit data gaps.
Evidence-graded agent-work lanes, bid advice, live agent jobs and a hash-chained evidence ledger.
Agent-first marketplace for real-world assets — agro and energy first; humans approve every write.
Add one secure layer between your agents and this server.