Evidence-tracked local memory MCP server: one SQLite file; corrections retire dependent memories.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
memory_recallNo description publishedThis tool published no description. Forge does not invent one.
memory_contextCompile cited, scoped context with contradictions and abstention under a conservative byte-based token budget. Pass only packet.text as context; diagnostics are outside the budget.Compile cited, scoped context with contradictions and abstention under a conservative byte-based token budget. Pass only packet.text as context; diagnostics are outside the budget.
No input schema was published for this tool.
memory_inspectInspect accessible stored evidence and its lifecycle. Inactive records are history, not current advice.Inspect accessible stored evidence and its lifecycle. Inactive records are history, not current advice.
No input schema was published for this tool.
memory_resumeRead the latest accessible active checkpoint for a task. Completed steps and artifact paths are historical claims. Verify current environment and permissions before acting.Read the latest accessible active checkpoint for a task. Completed steps and artifact paths are historical claims. Verify current environment and permissions before acting.
No input schema was published for this tool.
memory_sourceRead a bounded UTF-8 range of the original captured transcript or extracted document. Its status and trust remain visible.Read a bounded UTF-8 range of the original captured transcript or extracted document. Its status and trust remain visible.
No input schema was published for this tool.
memory_modelInspect a source-backed project model. Stale models are marked and must not be treated as current knowledge.Inspect a source-backed project model. Stale models are marked and must not be treated as current knowledge.
No input schema was published for this tool.
memory_skillInspect a reusable skill and its prerequisites, trial evidence and current eligibility. This does not execute the skill.Inspect a reusable skill and its prerequisites, trial evidence and current eligibility. This does not execute the skill.
No input schema was published for this tool.
memory_jobsInspect bounded observation/consolidation jobs and their outcome. Only the host executes configured model workers.Inspect bounded observation/consolidation jobs and their outcome. Only the host executes configured model workers.
No input schema was published for this tool.
memory_entityResolve an entity name or alias without silently merging ambiguous identities.Resolve an entity name or alias without silently merging ambiguous identities.
No input schema was published for this tool.
memory_traverseFollow a bounded number of evidence-backed relationship hops; each hop retains source IDs.Follow a bounded number of evidence-backed relationship hops; each hop retains source IDs.
No input schema was published for this tool.
memory_branch_previewInspect isolated proposed changes and source conflicts before a controller merges them.Inspect isolated proposed changes and source conflicts before a controller merges them.
No input schema was published for this tool.
memory_storeRecord an observed fact, preference, decision or procedure with a source. Private by default; workspace visibility explicitly shares with this workspace. Agent notes cannot self-certify as verified. Similar text is never automatically merged.Record an observed fact, preference, decision or procedure with a source. Private by default; workspace visibility explicitly shares with this workspace. Agent notes cannot self-certify as verified. Similar text is never automatically merged.
No input schema was published for this tool.
memory_captureCapture supplied transcript events with stable retry IDs. This reads no host files. Observed messages remain fallible evidence.Capture supplied transcript events with stable retry IDs. This reads no host files. Observed messages remain fallible evidence.
No input schema was published for this tool.
memory_observeQueue source-linked observations or a project model for the host to process under its configured model and budget. This does not invoke or choose a model.Queue source-linked observations or a project model for the host to process under its configured model and budget. This does not invoke or choose a model.
No input schema was published for this tool.
memory_checkpointSave a resumable task state, preserving constraints, rejected approaches and unfinished work. It does not perform or authorize actions.Save a resumable task state, preserving constraints, rejected approaches and unfinished work. It does not perform or authorize actions.
No input schema was published for this tool.
memory_correctExplicitly supersede your own non-verified observation; dependent advice becomes invalid. Controller-verified evidence must be corrected through the controller SDK.Explicitly supersede your own non-verified observation; dependent advice becomes invalid. Controller-verified evidence must be corrected through the controller SDK.
No input schema was published for this tool.
memory_forgetPurge an owned memory and content derived from it from this live local store. This cannot erase external exports, backups or context already sent to agents.Purge an owned memory and content derived from it from this live local store. This cannot erase external exports, backups or context already sent to agents.
No input schema was published for this tool.
16 of 17 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Evidence-tracked local memory MCP server: one SQLite file; corrections retire dependent memories.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
3 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.