Categories › AI & Agents › Agent memory & context
Free verified network knowledge for AI agents: deterministic answers, honest unknowns.
Remote server: your requests and data go to mcp.clideck.com. Claude Code: claude mcp add --transport http clideck-mcp-network-knowledge https://mcp.clideck.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
report_knowledge_gap — Record the original network question for priority research. Provide missing context or explain why an answer was not useful. Feedback alone report_domain_knowledge_gap — Retain the original technical question, independent OS/component versions and missing details for priority learning. Does not alter publisheget_learning_status — Check a learning ID returned by a knowledge query or report_knowledge_gap. Published means the original question has a complete answer; repelist_knowledge_domains — List installed, compatible knowledge domain packs and their declared capabilities.describe_knowledge_domain — Return the context and public-record contracts for one installed knowledge domain.query_domain_knowledge — Run deterministic search in one domain using that pack’s validated context and public-record schema. Network queries may create or update a resolve_network_context — Resolve vendor, model/platform, portable software family, operating system, and version context.query_network_knowledge — Return deterministic, version-scoped commands, diagnostics, and concepts for a network question. Missing or incomplete knowledge may create get_knowledge_provenance — Return safe source metadata for up to five active knowledge revisions.get_network_workflow — Return a deterministic, ordered workflow including safety, verification, and rollback. Missing or incomplete knowledge may create or update request_expert_answer — Create a durable research task when deterministic knowledge has no applicable answer.get_expert_task — Poll an expert research task by opaque ID and access token.continue_expert_task — Provide bounded additional input requested by the researcher.cancel_expert_task — Cancel a non-terminal expert task.submit_feedback — Submit correctness, freshness, safety, or completeness feedback without including private logs.analyze_device_snapshot — Detect vendor, model, operating system, and version from bounded CLI output while redacting sensitive values. Input is not stored.review_network_change — Deterministic advisory review of commands or a configuration diff. It always returns available guidance and never executes a command. Missinverify_network_change — Evaluate bounded before/after outputs against the signed verification plan returned by review_network_change.advise_network_upgrade — Return exact-model, exact-version upgrade prerequisites, risks, checks, and rollback without downloading software. Missing or incomplete knoanalyze_network_path — Build a bounded topology and packet-path graph from supplied CDP, LLDP, route, and traceroute outputs without storing them.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.