A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.
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.
query-guidanceHow to effectively search this knowledge base. Read this before issuing search queries.How to effectively search this knowledge base. Read this before issuing search queries.
No input schema was published for this tool.
memory-protocolGuidelines for what to store in this knowledge base and when. Read this before using the learn tool.Guidelines for what to store in this knowledge base and when. Read this before using the learn tool.
No input schema was published for this tool.
searchRecall relevant knowledge by ranked keyword and semantic (hybrid) relevance. Returns ranked results with heading, snippet, matched terms, level, parent, and sectionType. Sections from the same document receive a sibling score boost when multiple sections match. Use multiple short keyword queries fo…Recall relevant knowledge by ranked keyword and semantic (hybrid) relevance. Returns ranked results with heading, snippet, matched terms, level, parent, and sectionType. Sections from the same document receive a sibling score boost when multiple sections match. Use multiple short keyword queries fo…
No input schema was published for this tool.
learnStore durable knowledge in the agent's second brain.Store durable knowledge in the agent's second brain.
No input schema was published for this tool.
unlearnRemove a section from the knowledge base by its kb-id, or an entire document (and its member sections) by docid.Remove a section from the knowledge base by its kb-id, or an entire document (and its member sections) by docid.
No input schema was published for this tool.
retrieveLow-level fetch of a section or document by identifier. For AI agent workflows, prefer `recall` which includes metadata, context, and back-references.Low-level fetch of a section or document by identifier. For AI agent workflows, prefer `recall` which includes metadata, context, and back-references.
No input schema was published for this tool.
recallExpand remembered context after search. Retrieves full content and context for sections by identifier, returning section text, level, parent, metadata, references, and back-references. Call it on the kbids search returned. Use maxTokens to bound the payload, and format: compact when you only need t…Expand remembered context after search. Retrieves full content and context for sections by identifier, returning section text, level, parent, metadata, references, and back-references. Call it on the kbids search returned. Use maxTokens to bound the payload, and format: compact when you only need t…
No input schema was published for this tool.
statusGet knowledge base status including document count, section count, index size, and cache statistics.Get knowledge base status including document count, section count, index size, and cache statistics.
No input schema was published for this tool.
contentCompose a rendered Markdown document from one or more kbid or docid identifiers.Compose a rendered Markdown document from one or more kbid or docid identifiers.
No input schema was published for this tool.
checkVerify the integrity of the knowledge base. Reports checksum mismatches, orphan sections, broken references, and circular reference chains.Verify the integrity of the knowledge base. Reports checksum mismatches, orphan sections, broken references, and circular reference chains.
No input schema was published for this tool.
rebuildReconstruct all index files from section files and document manifests on disk. Use this to recover from index corruption.Reconstruct all index files from section files and document manifests on disk. Use this to recover from index corruption.
No input schema was published for this tool.
exportExport the knowledge base as a self-contained directory snapshot (sections, documents, catalog -- no indexes).Export the knowledge base as a self-contained directory snapshot (sections, documents, catalog -- no indexes).
No input schema was published for this tool.
skill-learnNo description publishedThis tool published no description. Forge does not invent one.
skill-searchNo description publishedThis tool published no description. Forge does not invent one.
skill-unlearnNo description publishedThis tool published no description. Forge does not invent one.
skill-recallNo description publishedThis tool published no description. Forge does not invent one.
skill-contentNo description publishedThis tool published no description. Forge does not invent one.
agent-learnNo description publishedThis tool published no description. Forge does not invent one.
agent-searchNo description publishedThis tool published no description. Forge does not invent one.
agent-unlearnNo description publishedThis tool published no description. Forge does not invent one.
agent-recallNo description publishedThis tool published no description. Forge does not invent one.
agent-contentNo description publishedThis tool published no description. Forge does not invent one.
auto-capture-reviewPropose knowledge for storage and let the user confirm it, when the host supports elicitation.Propose knowledge for storage and let the user confirm it, when the host supports elicitation.
No input schema was published for this tool.
save_evalsValidate and persist retrieval eval cases drafted via the eval-generate prompt. Rejects cases whose kbids do not resolve, and drops duplicates. Call it only with kbids a search actually returned; invented ids fail the whole batch.Validate and persist retrieval eval cases drafted via the eval-generate prompt. Rejects cases whose kbids do not resolve, and drops duplicates. Call it only with kbids a search actually returned; invented ids fail the whole batch.
No input schema was published for this tool.
reviseThe section to correctThe section to correct
No input schema was published for this tool.
historyList every revision of a section, oldest first, and name the current one. Call it when a kb-id you hold no longer appears in search: revisions are retired, not deleted, so a stale kb-id still leads to the text that replaced it. A section revised once has two revisions; one never revised has one.List every revision of a section, oldest first, and name the current one. Call it when a kb-id you hold no longer appears in search: revisions are retired, not deleted, so a stale kb-id still leads to the text that replaced it. A section revised once has two revisions; one never revised has one.
No input schema was published for this tool.
neighbourhoodList what relates to a section and HOW, so you can decide what to read next. Eight relations: supersedes, superseded-by, parent, child, sibling, references, referenced-by, similar. Seven are recorded facts; only "similar" is inferred from a cosine. Related is not relevant -- judge these against you…List what relates to a section and HOW, so you can decide what to read next. Eight relations: supersedes, superseded-by, parent, child, sibling, references, referenced-by, similar. Seven are recorded facts; only "similar" is inferred from a cosine. Related is not relevant -- judge these against you…
No input schema was published for this tool.
consolidatePropose groups of stored sections that could become one, so a knowledge base of twenty overlapping notes can become a few good ones. Proposes ONLY -- nothing is merged. Each group reports its weakest link. Without an entailment judge kbdb CANNOT tell whether a group disagrees with itself; read ever…Propose groups of stored sections that could become one, so a knowledge base of twenty overlapping notes can become a few good ones. Proposes ONLY -- nothing is merged. Each group reports its weakest link. Without an entailment judge kbdb CANNOT tell whether a group disagrees with itself; read ever…
No input schema was published for this tool.
contradictionsReport pairs of stored sections covering the same ground, to read together before trusting either. Similarity finds pairs; it cannot judge agreement. Without an entailment model every pair reads "related", and no "contradicts" means nothing was asked, not that nothing conflicts.Report pairs of stored sections covering the same ground, to read together before trusting either. Similarity finds pairs; it cannot judge agreement. Without an entailment model every pair reads "related", and no "contradicts" means nothing was asked, not that nothing conflicts.
No input schema was published for this tool.
gapsReport what this knowledge base is repeatedly asked and answers badly, worst first. Call it to decide what to learn next. Ranking is triage, not measurement: the log records how each search went, never whether the answer helped.Report what this knowledge base is repeatedly asked and answers badly, worst first. Call it to decide what to learn next. Ranking is triage, not measurement: the log records how each search went, never whether the answer helped.
No input schema was published for this tool.
mark_resultRecord whether a recalled section answered a query. Accumulates real usage into an eval dataset. Call it once you know whether a result helped, including when it did not -- a wrong answer is the more useful judgement.Record whether a recalled section answered a query. Accumulates real usage into an eval dataset. Call it once you know whether a result helped, including when it did not -- a wrong answer is the more useful judgement.
No input schema was published for this tool.
queryOptional search terms selecting which sections to draft cases for; omitted samples the baseOptional search terms selecting which sections to draft cases for; omitted samples the base
No input schema was published for this tool.
topicOptional subject to check for existing coverage; omitted samples the baseOptional subject to check for existing coverage; omitted samples the base
No input schema was published for this tool.
23 of 33 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.
A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.